TBD Meeting (5257-19)

SAN FRANCISCO – As a tool for the screening and diagnosis of diseases in the gastrointestinal (GI) tract, artificial intelligence (AI) is advancing rapidly, according to a review of this technology presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Much of the focus of the update was on screening colonoscopy, but the same principles are relevant and being pursued for other GI conditions, such as dysplasia screening in patients with Barrett’s esophagus and the assessment of mucosal healing in inflammatory bowel disease, according to Michael F. Byrne, MD, a clinical professor in the division of gastroenterology at Vancouver General Hospital.

“There are many technologies [to improve screening and diagnosis of GI diseases], but I believe these will struggle if they do not also have some kind of built-in machine intelligence,” Dr. Byrne said. In addition to his practice in gastroenterology, Dr. Byrne is CEO of Satis Operations and founder of AI4GI, a commercial joint venture focused on clinical applications of AI in colon polyp disease.

In this context, AI is being built on the principle of deep learning, which employs neural networks or a set of algorithms that permits a computer to recognize patterns when “trained” with data. In the machine learning process, the computer can use a large number of features in the task of discrimination.

This might suggest that AI could, in turn, train physicians to recognize the same features, but this underestimates the complexity and sophistication of machine learning, according to Dr. Byrne. The current status of machine learning for screening colonoscopy underscores this point.

“A computer can consider a thousand features when evaluating a polyp, which is way beyond what we can do,” Dr. Byrne said. Even with advances to improve visualization in screening colonoscopy, such as improved resolution and better lighting, the reason that AI is expected to prevail is that “the human eye is just not accurate enough.”

Many groups have developed advanced machine learning systems for screening colonoscopy. Dr. Byrne reviewed some of the early work done in Japan and that performed with a system in development by his group. In a study with the AI4GI model, published recently in Gut (2019;68:94-100), greater than 94% accuracy was achieved in distinguishing adenomas from hyperplastic polyps using histopathology as a gold standard.

Because of the ability of machine learning to see what the human eye cannot, Dr. Byrne predicts that AI-centric classification will replace current polyp classification systems, which could offer categories that are more clinically useful and reliable.

However, the work in screening colonoscopy is just the beginning, according to Dr. Byrne. “The opportunity of machine learning goes way beyond polyps.”

Recognizing dysplasia associated with Barrett’s esophagus has parallels with identifying adenomatous polyps in screening colonoscopy, but Dr. Byrne also discussed machine learning as an “optical biopsy” for evaluating the mucosa of patients with IBD. No longer a screening approach, the characterization of IBD tissue could help with therapeutic decisions.

With an AI approach to optical biopsy, “there is a great opportunity to assign an inflammatory burden in IBD,” he suggested, explaining how evidence of disease activity could guide escalation or de-escalation of treatment within the context of the treat-to-target approach to prolonging remission.

Overall, there is abundant evidence that “optical biopsy is feasible,” Dr. Byrne said. He indicated that clinical applications are approaching quickly. While he acknowledged that the technology “will need a human in the loop” as it enters clinical practice initially, he believes that this technology will play a significant role in GI practice because of the clear limitations of the human eye in assessing endoscopic images of GI tissue.

SAN FRANCISCO – As a tool for the screening and diagnosis of diseases in the gastrointestinal (GI) tract, artificial intelligence (AI) is advancing rapidly, according to a review of this technology presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Much of the focus of the update was on screening colonoscopy, but the same principles are relevant and being pursued for other GI conditions, such as dysplasia screening in patients with Barrett’s esophagus and the assessment of mucosal healing in inflammatory bowel disease, according to Michael F. Byrne, MD, a clinical professor in the division of gastroenterology at Vancouver General Hospital.

“There are many technologies [to improve screening and diagnosis of GI diseases], but I believe these will struggle if they do not also have some kind of built-in machine intelligence,” Dr. Byrne said. In addition to his practice in gastroenterology, Dr. Byrne is CEO of Satis Operations and founder of AI4GI, a commercial joint venture focused on clinical applications of AI in colon polyp disease.

In this context, AI is being built on the principle of deep learning, which employs neural networks or a set of algorithms that permits a computer to recognize patterns when “trained” with data. In the machine learning process, the computer can use a large number of features in the task of discrimination.

This might suggest that AI could, in turn, train physicians to recognize the same features, but this underestimates the complexity and sophistication of machine learning, according to Dr. Byrne. The current status of machine learning for screening colonoscopy underscores this point.

“A computer can consider a thousand features when evaluating a polyp, which is way beyond what we can do,” Dr. Byrne said. Even with advances to improve visualization in screening colonoscopy, such as improved resolution and better lighting, the reason that AI is expected to prevail is that “the human eye is just not accurate enough.”

Many groups have developed advanced machine learning systems for screening colonoscopy. Dr. Byrne reviewed some of the early work done in Japan and that performed with a system in development by his group. In a study with the AI4GI model, published recently in Gut (2019;68:94-100), greater than 94% accuracy was achieved in distinguishing adenomas from hyperplastic polyps using histopathology as a gold standard.

Because of the ability of machine learning to see what the human eye cannot, Dr. Byrne predicts that AI-centric classification will replace current polyp classification systems, which could offer categories that are more clinically useful and reliable.

However, the work in screening colonoscopy is just the beginning, according to Dr. Byrne. “The opportunity of machine learning goes way beyond polyps.”

Recognizing dysplasia associated with Barrett’s esophagus has parallels with identifying adenomatous polyps in screening colonoscopy, but Dr. Byrne also discussed machine learning as an “optical biopsy” for evaluating the mucosa of patients with IBD. No longer a screening approach, the characterization of IBD tissue could help with therapeutic decisions.

With an AI approach to optical biopsy, “there is a great opportunity to assign an inflammatory burden in IBD,” he suggested, explaining how evidence of disease activity could guide escalation or de-escalation of treatment within the context of the treat-to-target approach to prolonging remission.

Overall, there is abundant evidence that “optical biopsy is feasible,” Dr. Byrne said. He indicated that clinical applications are approaching quickly. While he acknowledged that the technology “will need a human in the loop” as it enters clinical practice initially, he believes that this technology will play a significant role in GI practice because of the clear limitations of the human eye in assessing endoscopic images of GI tissue.

SAN FRANCISCO – As a tool for the screening and diagnosis of diseases in the gastrointestinal (GI) tract, artificial intelligence (AI) is advancing rapidly, according to a review of this technology presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Much of the focus of the update was on screening colonoscopy, but the same principles are relevant and being pursued for other GI conditions, such as dysplasia screening in patients with Barrett’s esophagus and the assessment of mucosal healing in inflammatory bowel disease, according to Michael F. Byrne, MD, a clinical professor in the division of gastroenterology at Vancouver General Hospital.

“There are many technologies [to improve screening and diagnosis of GI diseases], but I believe these will struggle if they do not also have some kind of built-in machine intelligence,” Dr. Byrne said. In addition to his practice in gastroenterology, Dr. Byrne is CEO of Satis Operations and founder of AI4GI, a commercial joint venture focused on clinical applications of AI in colon polyp disease.

In this context, AI is being built on the principle of deep learning, which employs neural networks or a set of algorithms that permits a computer to recognize patterns when “trained” with data. In the machine learning process, the computer can use a large number of features in the task of discrimination.

This might suggest that AI could, in turn, train physicians to recognize the same features, but this underestimates the complexity and sophistication of machine learning, according to Dr. Byrne. The current status of machine learning for screening colonoscopy underscores this point.

“A computer can consider a thousand features when evaluating a polyp, which is way beyond what we can do,” Dr. Byrne said. Even with advances to improve visualization in screening colonoscopy, such as improved resolution and better lighting, the reason that AI is expected to prevail is that “the human eye is just not accurate enough.”

Many groups have developed advanced machine learning systems for screening colonoscopy. Dr. Byrne reviewed some of the early work done in Japan and that performed with a system in development by his group. In a study with the AI4GI model, published recently in Gut (2019;68:94-100), greater than 94% accuracy was achieved in distinguishing adenomas from hyperplastic polyps using histopathology as a gold standard.

Because of the ability of machine learning to see what the human eye cannot, Dr. Byrne predicts that AI-centric classification will replace current polyp classification systems, which could offer categories that are more clinically useful and reliable.

However, the work in screening colonoscopy is just the beginning, according to Dr. Byrne. “The opportunity of machine learning goes way beyond polyps.”

Recognizing dysplasia associated with Barrett’s esophagus has parallels with identifying adenomatous polyps in screening colonoscopy, but Dr. Byrne also discussed machine learning as an “optical biopsy” for evaluating the mucosa of patients with IBD. No longer a screening approach, the characterization of IBD tissue could help with therapeutic decisions.

With an AI approach to optical biopsy, “there is a great opportunity to assign an inflammatory burden in IBD,” he suggested, explaining how evidence of disease activity could guide escalation or de-escalation of treatment within the context of the treat-to-target approach to prolonging remission.

Overall, there is abundant evidence that “optical biopsy is feasible,” Dr. Byrne said. He indicated that clinical applications are approaching quickly. While he acknowledged that the technology “will need a human in the loop” as it enters clinical practice initially, he believes that this technology will play a significant role in GI practice because of the clear limitations of the human eye in assessing endoscopic images of GI tissue.

SAN FRANCISCO – Predictive analytics of large quantities of data using machine learning present a powerful tool for improving therapeutic choices, according to a summary of work performed in inflammatory bowel disease (IBD) and presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

This type of work is relevant to many fields of medicine, but studies conducted in IBD have provided particularly compelling evidence that predictive analytics will improve outcomes and lead to more cost effective delivery of care, according to Akbar K. Waljee, MD, MSc, an associate professor in the division of gastroenterology at University of Michigan, Ann Arbor, and a staff physician and researcher at the VA Ann Arbor Healthcare system.

“We collect large amounts of clinical data every day in the delivery of health care, but we are now only just beginning to leverage [these] data to guide treatment,” Dr. Waljee said. He has now published several papers on the role of precision analytics of big data to improve treatment choices in IBD, as well as other diseases. These analyses are relevant for determining both who to treat with a certain drug and who to not treat with it.

In one example, data from 1,080 IBD patients taking thiopurines were used to develop a machine learning algorithm that analyzed multiple readily available variables, such as a complete blood count with differential and a chemistry panel, to predict whether someone was or was not in remission. This was then used to compare the mean yearly clinical event rates (new steroids prescriptions, hospitalizations, and abdominal surgeries) between the two groups (1.08 vs. 3.95 events) to show the associated clinical benefit of using this algorithm.

“The heterogeneity of response to therapies for IBD is well established. If machine learning predicts effective choices, there will be an opportunity to accelerate the time to disease control, as well as save costs by avoiding therapies not likely to be effective,” Dr. Waljee explained.

In another example, an algorithm was developed to predict the likelihood of achieving a corticosteroid-free biologic remission at 1 year in Crohn’s disease patients when patients were evaluated 6 weeks after initiating the gut-selective biologic vedolizumab. Again, it was based on an analysis of numerous variables, including laboratory data, sex, and race. Based on the model drawn from the analysis of 472 patients, 35.8% of the patients predicted to be in corticosteroid-free biologic remission at 1 year achieved this endpoint, whereas only 6.7% of the patients predicted to fail achieved the endpoint.

“This suggests that we can use an algorithm relatively early in the course of this biologic to predict who is going to respond,” reported Dr. Waljee. Again, patients with a low likelihood of response at 6 weeks can be started on an alternative treatment, which could potentially accelerate the time to disease control and avoid the costs of an ineffective and expensive treatment.

IBD is a particularly attractive focus of precision analytics with big data. IBD has a relatively unpredictable relapsing/remitting course and a heterogeneous response to available therapies. Algorithms predictive of response circumvent the inherent delays from evaluating disease control over an extended period.

“With ever increasing concern about costs of care and access to care, these treatment algorithms promise to use resources more efficiently,” Dr. Waljee said.

SAN FRANCISCO – Predictive analytics of large quantities of data using machine learning present a powerful tool for improving therapeutic choices, according to a summary of work performed in inflammatory bowel disease (IBD) and presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

This type of work is relevant to many fields of medicine, but studies conducted in IBD have provided particularly compelling evidence that predictive analytics will improve outcomes and lead to more cost effective delivery of care, according to Akbar K. Waljee, MD, MSc, an associate professor in the division of gastroenterology at University of Michigan, Ann Arbor, and a staff physician and researcher at the VA Ann Arbor Healthcare system.

“We collect large amounts of clinical data every day in the delivery of health care, but we are now only just beginning to leverage [these] data to guide treatment,” Dr. Waljee said. He has now published several papers on the role of precision analytics of big data to improve treatment choices in IBD, as well as other diseases. These analyses are relevant for determining both who to treat with a certain drug and who to not treat with it.

In one example, data from 1,080 IBD patients taking thiopurines were used to develop a machine learning algorithm that analyzed multiple readily available variables, such as a complete blood count with differential and a chemistry panel, to predict whether someone was or was not in remission. This was then used to compare the mean yearly clinical event rates (new steroids prescriptions, hospitalizations, and abdominal surgeries) between the two groups (1.08 vs. 3.95 events) to show the associated clinical benefit of using this algorithm.

“The heterogeneity of response to therapies for IBD is well established. If machine learning predicts effective choices, there will be an opportunity to accelerate the time to disease control, as well as save costs by avoiding therapies not likely to be effective,” Dr. Waljee explained.

In another example, an algorithm was developed to predict the likelihood of achieving a corticosteroid-free biologic remission at 1 year in Crohn’s disease patients when patients were evaluated 6 weeks after initiating the gut-selective biologic vedolizumab. Again, it was based on an analysis of numerous variables, including laboratory data, sex, and race. Based on the model drawn from the analysis of 472 patients, 35.8% of the patients predicted to be in corticosteroid-free biologic remission at 1 year achieved this endpoint, whereas only 6.7% of the patients predicted to fail achieved the endpoint.

“This suggests that we can use an algorithm relatively early in the course of this biologic to predict who is going to respond,” reported Dr. Waljee. Again, patients with a low likelihood of response at 6 weeks can be started on an alternative treatment, which could potentially accelerate the time to disease control and avoid the costs of an ineffective and expensive treatment.

IBD is a particularly attractive focus of precision analytics with big data. IBD has a relatively unpredictable relapsing/remitting course and a heterogeneous response to available therapies. Algorithms predictive of response circumvent the inherent delays from evaluating disease control over an extended period.

“With ever increasing concern about costs of care and access to care, these treatment algorithms promise to use resources more efficiently,” Dr. Waljee said.

SAN FRANCISCO – Predictive analytics of large quantities of data using machine learning present a powerful tool for improving therapeutic choices, according to a summary of work performed in inflammatory bowel disease (IBD) and presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

This type of work is relevant to many fields of medicine, but studies conducted in IBD have provided particularly compelling evidence that predictive analytics will improve outcomes and lead to more cost effective delivery of care, according to Akbar K. Waljee, MD, MSc, an associate professor in the division of gastroenterology at University of Michigan, Ann Arbor, and a staff physician and researcher at the VA Ann Arbor Healthcare system.

“We collect large amounts of clinical data every day in the delivery of health care, but we are now only just beginning to leverage [these] data to guide treatment,” Dr. Waljee said. He has now published several papers on the role of precision analytics of big data to improve treatment choices in IBD, as well as other diseases. These analyses are relevant for determining both who to treat with a certain drug and who to not treat with it.

In one example, data from 1,080 IBD patients taking thiopurines were used to develop a machine learning algorithm that analyzed multiple readily available variables, such as a complete blood count with differential and a chemistry panel, to predict whether someone was or was not in remission. This was then used to compare the mean yearly clinical event rates (new steroids prescriptions, hospitalizations, and abdominal surgeries) between the two groups (1.08 vs. 3.95 events) to show the associated clinical benefit of using this algorithm.

“The heterogeneity of response to therapies for IBD is well established. If machine learning predicts effective choices, there will be an opportunity to accelerate the time to disease control, as well as save costs by avoiding therapies not likely to be effective,” Dr. Waljee explained.

In another example, an algorithm was developed to predict the likelihood of achieving a corticosteroid-free biologic remission at 1 year in Crohn’s disease patients when patients were evaluated 6 weeks after initiating the gut-selective biologic vedolizumab. Again, it was based on an analysis of numerous variables, including laboratory data, sex, and race. Based on the model drawn from the analysis of 472 patients, 35.8% of the patients predicted to be in corticosteroid-free biologic remission at 1 year achieved this endpoint, whereas only 6.7% of the patients predicted to fail achieved the endpoint.

“This suggests that we can use an algorithm relatively early in the course of this biologic to predict who is going to respond,” reported Dr. Waljee. Again, patients with a low likelihood of response at 6 weeks can be started on an alternative treatment, which could potentially accelerate the time to disease control and avoid the costs of an ineffective and expensive treatment.

IBD is a particularly attractive focus of precision analytics with big data. IBD has a relatively unpredictable relapsing/remitting course and a heterogeneous response to available therapies. Algorithms predictive of response circumvent the inherent delays from evaluating disease control over an extended period.

“With ever increasing concern about costs of care and access to care, these treatment algorithms promise to use resources more efficiently,” Dr. Waljee said.

SAN FRANCISCO – The gastroenterology device field has matured technically in recent years, with plenty of innovation in applications to antireflux, obesity, and colorectal polyp detection, among others, but barriers to adoption remain. The most pressing is reimbursement, which is a process that is often opaque and off-putting, especially for small companies that lack the capital to bull their way through the obstacles.

Vidyard Video

Reimbursement decisions get made on a case-by-case basis, “and a lot of times there’s a finite number of dollars in the health care system, and CMS [Centers for Medicare & Medicaid Services] and other entities are trying to limit how many things we can have. They look at data and summaries that can be somewhat biased. Plus the way the methodology works in surveying physicians is not very clear, so the overall process needs more clarity,” said Sri Komanduri, MD, AGAF, professor of medicine and surgery at Northwestern University, Chicago, and vice chair of the AGA Center for GI Innovation and Technology, in an interview at the 2019 AGA Tech Summit sponsored by the AGA Center for GI Innovation and Technology.

The 2019 summit highlighted new technologies in its annual Shark Tank competition and brought experts from industry, academia, and regulatory agencies to San Francisco for 2 days of presentations on the challenges and opportunities in gastroenterology devices.

Lack of clarity is indeed a key challenge, agreed V. Raman Muthusamy, MD, AGAF, director of endoscopy at the University of California, Los Angeles, Health System, professor of clinical medicine at UCLA, and chair of the AGA Center for GI Innovation and Technology. “Maybe you designed a trial that you think will be adequate but the person who is ultimately making the decision on coverage doesn’t think it’s adequate, so having societies and payers really speak together with industry and innovators to get this information early rather than late could save a lot of time and money, and ultimately get these products to patients sooner,” Dr. Muthusamy said in an interview.

And he insists that the technology is ready, as evidenced in part by the Shark Tank contestants and this year’s winner. There is more to come. In the immediate future, Dr. Muthusamy anticipates use of artificial intelligence to enhance polyp detection, and perhaps assessing larger polyps. “Computers can aid us in reading things, particularly in analyzing large amounts of data which may look similar to finding a needle in a haystack, whether that’s dysplasia in a field of normal tissue, or it’s identifying a small locus of blood in an otherwise bloodless field.”

He also expects more expansion of technologies that will allow endoscopists to perform techniques that were once limited to surgeons, such as making endoscopic submucosal dissection easier to perform. “We continue to see development of endoscopic platforms that are going to allow us to become endoscopic surgeons,” said Dr. Muthusamy.

Interventional ultrasound should continue to gain traction, and Dr. Muthusamy hopes to see an endoscopic antireflux device that could provide patients a middle-ground option between medication and surgery.

But these innovations still face many obstacles to reaching patients. Getting Food and Drug Administration approval, getting a code, and reimbursement are all daunting roadblocks. “You clear one hurdle only to run into another, and if you get one of these steps wrong, and they say you have to redo a trial, you’re talking potentially millions of dollars and several years,” said Dr. Muthusamy.

That could stifle innovation, particularly among small companies. “That may be why you see a lot of smaller companies get acquired early – they don’t have the sort of capital to sustain the long road to the finish,” he said.

However, Dr. Muthusamy believes there is room for optimism, as evidenced by progress at the FDA. “If we can make the level of changes in the next decade in the reimbursement process that we’ve made in the regulatory process in the last decade, we’ll have made some real progress.”

The AGA Center for GI Innovation and Technology is working behind the scenes to guide the FDA, payers, and industry in overcoming the overcoming the obstacles inherent in the device development, approval, and adoption process. The center’s goal is to continue to advance innovation in GI, while making sure the needs of gastroenterologists and patients are met with each new technology that comes to market.

SAN FRANCISCO – The gastroenterology device field has matured technically in recent years, with plenty of innovation in applications to antireflux, obesity, and colorectal polyp detection, among others, but barriers to adoption remain. The most pressing is reimbursement, which is a process that is often opaque and off-putting, especially for small companies that lack the capital to bull their way through the obstacles.

Vidyard Video

Reimbursement decisions get made on a case-by-case basis, “and a lot of times there’s a finite number of dollars in the health care system, and CMS [Centers for Medicare & Medicaid Services] and other entities are trying to limit how many things we can have. They look at data and summaries that can be somewhat biased. Plus the way the methodology works in surveying physicians is not very clear, so the overall process needs more clarity,” said Sri Komanduri, MD, AGAF, professor of medicine and surgery at Northwestern University, Chicago, and vice chair of the AGA Center for GI Innovation and Technology, in an interview at the 2019 AGA Tech Summit sponsored by the AGA Center for GI Innovation and Technology.

The 2019 summit highlighted new technologies in its annual Shark Tank competition and brought experts from industry, academia, and regulatory agencies to San Francisco for 2 days of presentations on the challenges and opportunities in gastroenterology devices.

Lack of clarity is indeed a key challenge, agreed V. Raman Muthusamy, MD, AGAF, director of endoscopy at the University of California, Los Angeles, Health System, professor of clinical medicine at UCLA, and chair of the AGA Center for GI Innovation and Technology. “Maybe you designed a trial that you think will be adequate but the person who is ultimately making the decision on coverage doesn’t think it’s adequate, so having societies and payers really speak together with industry and innovators to get this information early rather than late could save a lot of time and money, and ultimately get these products to patients sooner,” Dr. Muthusamy said in an interview.

And he insists that the technology is ready, as evidenced in part by the Shark Tank contestants and this year’s winner. There is more to come. In the immediate future, Dr. Muthusamy anticipates use of artificial intelligence to enhance polyp detection, and perhaps assessing larger polyps. “Computers can aid us in reading things, particularly in analyzing large amounts of data which may look similar to finding a needle in a haystack, whether that’s dysplasia in a field of normal tissue, or it’s identifying a small locus of blood in an otherwise bloodless field.”

He also expects more expansion of technologies that will allow endoscopists to perform techniques that were once limited to surgeons, such as making endoscopic submucosal dissection easier to perform. “We continue to see development of endoscopic platforms that are going to allow us to become endoscopic surgeons,” said Dr. Muthusamy.

Interventional ultrasound should continue to gain traction, and Dr. Muthusamy hopes to see an endoscopic antireflux device that could provide patients a middle-ground option between medication and surgery.

But these innovations still face many obstacles to reaching patients. Getting Food and Drug Administration approval, getting a code, and reimbursement are all daunting roadblocks. “You clear one hurdle only to run into another, and if you get one of these steps wrong, and they say you have to redo a trial, you’re talking potentially millions of dollars and several years,” said Dr. Muthusamy.

That could stifle innovation, particularly among small companies. “That may be why you see a lot of smaller companies get acquired early – they don’t have the sort of capital to sustain the long road to the finish,” he said.

However, Dr. Muthusamy believes there is room for optimism, as evidenced by progress at the FDA. “If we can make the level of changes in the next decade in the reimbursement process that we’ve made in the regulatory process in the last decade, we’ll have made some real progress.”

The AGA Center for GI Innovation and Technology is working behind the scenes to guide the FDA, payers, and industry in overcoming the overcoming the obstacles inherent in the device development, approval, and adoption process. The center’s goal is to continue to advance innovation in GI, while making sure the needs of gastroenterologists and patients are met with each new technology that comes to market.

SAN FRANCISCO – The gastroenterology device field has matured technically in recent years, with plenty of innovation in applications to antireflux, obesity, and colorectal polyp detection, among others, but barriers to adoption remain. The most pressing is reimbursement, which is a process that is often opaque and off-putting, especially for small companies that lack the capital to bull their way through the obstacles.

Vidyard Video

Reimbursement decisions get made on a case-by-case basis, “and a lot of times there’s a finite number of dollars in the health care system, and CMS [Centers for Medicare & Medicaid Services] and other entities are trying to limit how many things we can have. They look at data and summaries that can be somewhat biased. Plus the way the methodology works in surveying physicians is not very clear, so the overall process needs more clarity,” said Sri Komanduri, MD, AGAF, professor of medicine and surgery at Northwestern University, Chicago, and vice chair of the AGA Center for GI Innovation and Technology, in an interview at the 2019 AGA Tech Summit sponsored by the AGA Center for GI Innovation and Technology.

The 2019 summit highlighted new technologies in its annual Shark Tank competition and brought experts from industry, academia, and regulatory agencies to San Francisco for 2 days of presentations on the challenges and opportunities in gastroenterology devices.

Lack of clarity is indeed a key challenge, agreed V. Raman Muthusamy, MD, AGAF, director of endoscopy at the University of California, Los Angeles, Health System, professor of clinical medicine at UCLA, and chair of the AGA Center for GI Innovation and Technology. “Maybe you designed a trial that you think will be adequate but the person who is ultimately making the decision on coverage doesn’t think it’s adequate, so having societies and payers really speak together with industry and innovators to get this information early rather than late could save a lot of time and money, and ultimately get these products to patients sooner,” Dr. Muthusamy said in an interview.

And he insists that the technology is ready, as evidenced in part by the Shark Tank contestants and this year’s winner. There is more to come. In the immediate future, Dr. Muthusamy anticipates use of artificial intelligence to enhance polyp detection, and perhaps assessing larger polyps. “Computers can aid us in reading things, particularly in analyzing large amounts of data which may look similar to finding a needle in a haystack, whether that’s dysplasia in a field of normal tissue, or it’s identifying a small locus of blood in an otherwise bloodless field.”

He also expects more expansion of technologies that will allow endoscopists to perform techniques that were once limited to surgeons, such as making endoscopic submucosal dissection easier to perform. “We continue to see development of endoscopic platforms that are going to allow us to become endoscopic surgeons,” said Dr. Muthusamy.

Interventional ultrasound should continue to gain traction, and Dr. Muthusamy hopes to see an endoscopic antireflux device that could provide patients a middle-ground option between medication and surgery.

But these innovations still face many obstacles to reaching patients. Getting Food and Drug Administration approval, getting a code, and reimbursement are all daunting roadblocks. “You clear one hurdle only to run into another, and if you get one of these steps wrong, and they say you have to redo a trial, you’re talking potentially millions of dollars and several years,” said Dr. Muthusamy.

That could stifle innovation, particularly among small companies. “That may be why you see a lot of smaller companies get acquired early – they don’t have the sort of capital to sustain the long road to the finish,” he said.

However, Dr. Muthusamy believes there is room for optimism, as evidenced by progress at the FDA. “If we can make the level of changes in the next decade in the reimbursement process that we’ve made in the regulatory process in the last decade, we’ll have made some real progress.”

The AGA Center for GI Innovation and Technology is working behind the scenes to guide the FDA, payers, and industry in overcoming the overcoming the obstacles inherent in the device development, approval, and adoption process. The center’s goal is to continue to advance innovation in GI, while making sure the needs of gastroenterologists and patients are met with each new technology that comes to market.

SAN FRANCISCO – All five innovative startups pitched at the Shark Tank at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology, are in advanced stages of development, but only one is given the opportunity to be declared the winner of the competition. The ideas ranged from a smart toilet for early disease detection to a unique strategy for obesity phenotyping, but the winner by both official decision and popular vote was a smartphone app to help patients with inflammatory bowel disease (IBD) manage the condition.

“As always, this year’s Shark Tank was a highlight of the AGA Tech Summit and represents the progress our field is making when it comes to innovation. Our panel of sharks was focused on understanding the problem each innovation solved – that’s the key when determining if an idea is novel or innovation for innovation’s sake. We were impressed with all of the technologies presented, but ultimately chose the Oshi Health IBD app as our winner because of the impact it is already having on improving the health and care of IBD patients,” said V. Raman Muthusamy, MD, AGAF, chair of the AGA Center for GI Innovation and Technology.
 

The winner: Oshi pitches “all-in-one” IBD app

By both popular vote from those attending the AGA Tech Summit as well as the six-member Shark Tank panel, Oshi Health was selected as the 2019 Shark Tank winner for its IBD app. The app was designed to help patients track symptoms, a first step in understanding flare patterns, which differ substantially between patients and emphasize the need for a personalized plan for controlling disease.

Vidyard Video

“Since we launched last June at DDW^® we have had 40,000 downloads. We are the number one IBD management app,” reported Dan Weinstein, MBA, CEO of Oshi Health.

The available app represents the first of three phases as the functionality is expanded. Currently, in addition to using the app as a tracking tool, patients can find resources to learn about their disease and to communicate with other patients about their experiences. In a second phase, information gathered by the app will be made available to physicians to provide accurate current information about disease status to better individualize therapy.

Ultimately, the app is expected to guide treatment based on information it has collected on symptom patterns and other data collected over time, although this application is further down the road and will require regulatory approval if it is designed to provide clinical advice as expected, according to Mr. Weinstein.

However, benefits have already been seen. Mr. Weinstein cited data that associated the app with a 40% improvement in medication adherence and a nearly 60-day reduction in flare duration. Calling the app “the next chapter in treat-to-target” IBD management, he believes that this is an important step forward in digital health that will improve IBD outcomes. The Shark Tank panel agreed.
 

Runners-up: Other potential innovations to improve GI health

With or without Shark Tank endorsement, the other four startups described in the competition are moving forward. Each is designed to address an important unmet need with the potential to improve patient outcomes, which is a criterion for their inclusion in the competition.

 

 

The smart toilet seat

One involves a technologically advanced toilet seat. The new seat is based on the fact that fecal matter provides insight into a broad array of disease states, but specimen collection is a hurdle for a variety of reasons, including patient resistance. A toilet seat developed by Toi Labs, called TrueLoo, is equipped with lighting and cameras that captures images of bowel movements and urination for subsequent analysis.

“The toilet seat sees what the eye cannot,” according to Vikram Kashyap, CEO of Toi Labs. He believes it has major potential for early detection of conditions ranging from dehydration to gastrointestinal cancer.

Vidyard Video

Others agree. According to Mr. Kashyap, executives of a chain of senior living facilities have already expressed interest in installing this seat to better monitor health among residents. The seat is bolted into position in place of any standard toilet seat. It collects images and data that are transmitted directly to a cellular network.

“Using our technology, the goal is to catch disease states early before they progress,” said Mr. Kashyap, who called the surveillance system a low-cost disease-screening tool. He believes the smart toilet seat could be of the most important disease detection devices developed in recent years.

AI to aid screening endoscopy

A third entrant in this year’s Shark Tank described a strategy to employ artificial intelligence (AI) to aid endoscopists in screening for dysplasia. The tool is called Ultivision and is being developed by a startup called Docbot. The CEO, Andrew Ninh, and a senior executive, Jason B. Samarasena, MD, outlined an idea that could be used in either screening colonoscopy or in surveillance of Barrett’s esophagus).

“Dysplasia is difficult to find. It is subtle and it is often missed. With better detection of dysplasia, artificial intelligence offers an opportunity to reduce risk of cancer,” Dr. Samarasena said.

The tool integrates seamlessly with existing endoscopic tools, according to Mr. Ninh. As tissue is visualized, the AI is programmed to highlight suspected dysplasia with a colored box to alert the endoscopist. The colonoscopy application is a more advanced stage of development and might be submitted for regulatory approval this year, he said. The same technology will be adapted for Barrett’s esophagus.

“It is like facial recognition for dysplasia,” said Dr. Samarasena.
 

Obesity phenotyping tool

A fourth Shark Tank entrant employs technology to phenotype obese patients to better tailor therapy. The Pheno Test, developed by Phenomix Sciences, applies “multi-omics” to a blood-based test to separate patients with obesity into four phenotypes. When therapy is tailored to the phenotype, weight loss is greater, according to Andres J. Acosta, MD, PhD, assistant professor of medicine and consultant in gastroenterology and hepatology at Mayo Clinic, Rochester, Minn.

In an initial study that compared weight loss in 55 patients treated based on phenotype with 175 patients managed with standard of care, the total body weight loss “more than doubled,” Dr. Acosta reported.

According to Dr. Acosta, obesity is driven by very different mechanisms. He described the four major phenotypes identified with his test as hungry brain (satiation signal is impaired), hungry gut (signals to eat are upregulated), emotional hunger (psychological reasons drive eating behavior), and slow metabolism (failure to burn fat at normal rates).

With the blood test, which utilizes hormones, metabolites, DNA, and other biomarkers to separate these phenotypes, treatment can be tailored appropriately, according to Dr. Acosta. His company is now seeking Food and Drug Administration clearance of the test, which he believes will have a major impact on obesity control.
 

 

 

Capsule diagnostic tool

The final entrant selected to participate in this year’s Shark Tank described an ingestible capsule that diagnoses diseases by detecting gases as it descends the gastrointestinal tract. The Atmo Gas Capsule from Atmo Biosciences measures gases at the source, accelerating the diagnosis of such diseases as irritable bowel syndrome (IBS) and IBD.

“By measuring gases at their source, the accuracy is far better than a breath test,” said Malcolm Hebblewhite, MBA, CEO of Atmo Biosciences. The capsule is an alternative to more invasive and expensive diagnostic tools and it is highly accurate.

Providing examples, Mr. Hebblewhite said that elevated levels of oxygen suggest a disorder of motility while an elevated level of carbon dioxide and hydrogen suggest IBS. The capsule transmits data to a small receiver and then on to a smartphone.

“The real-time data is displayed for the user with more complex information accessible by the practitioner remotely via the cloud,” Mr. Hebblewhite said. He cited several papers that have already been published documenting the potential of this technology.

“The capsule is a single-use disposable device that is not retrieved,” according to Mr. Hebblewhite. He reported that his company plans to pursue the diagnosis of motility as an initial clinical application. The diagnosis of IBS and other GI conditions will follow. Clinical studies are already planned.

SAN FRANCISCO – All five innovative startups pitched at the Shark Tank at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology, are in advanced stages of development, but only one is given the opportunity to be declared the winner of the competition. The ideas ranged from a smart toilet for early disease detection to a unique strategy for obesity phenotyping, but the winner by both official decision and popular vote was a smartphone app to help patients with inflammatory bowel disease (IBD) manage the condition.

“As always, this year’s Shark Tank was a highlight of the AGA Tech Summit and represents the progress our field is making when it comes to innovation. Our panel of sharks was focused on understanding the problem each innovation solved – that’s the key when determining if an idea is novel or innovation for innovation’s sake. We were impressed with all of the technologies presented, but ultimately chose the Oshi Health IBD app as our winner because of the impact it is already having on improving the health and care of IBD patients,” said V. Raman Muthusamy, MD, AGAF, chair of the AGA Center for GI Innovation and Technology.
 

The winner: Oshi pitches “all-in-one” IBD app

By both popular vote from those attending the AGA Tech Summit as well as the six-member Shark Tank panel, Oshi Health was selected as the 2019 Shark Tank winner for its IBD app. The app was designed to help patients track symptoms, a first step in understanding flare patterns, which differ substantially between patients and emphasize the need for a personalized plan for controlling disease.

Vidyard Video

“Since we launched last June at DDW^® we have had 40,000 downloads. We are the number one IBD management app,” reported Dan Weinstein, MBA, CEO of Oshi Health.

The available app represents the first of three phases as the functionality is expanded. Currently, in addition to using the app as a tracking tool, patients can find resources to learn about their disease and to communicate with other patients about their experiences. In a second phase, information gathered by the app will be made available to physicians to provide accurate current information about disease status to better individualize therapy.

Ultimately, the app is expected to guide treatment based on information it has collected on symptom patterns and other data collected over time, although this application is further down the road and will require regulatory approval if it is designed to provide clinical advice as expected, according to Mr. Weinstein.

However, benefits have already been seen. Mr. Weinstein cited data that associated the app with a 40% improvement in medication adherence and a nearly 60-day reduction in flare duration. Calling the app “the next chapter in treat-to-target” IBD management, he believes that this is an important step forward in digital health that will improve IBD outcomes. The Shark Tank panel agreed.
 

Runners-up: Other potential innovations to improve GI health

With or without Shark Tank endorsement, the other four startups described in the competition are moving forward. Each is designed to address an important unmet need with the potential to improve patient outcomes, which is a criterion for their inclusion in the competition.

 

 

The smart toilet seat

One involves a technologically advanced toilet seat. The new seat is based on the fact that fecal matter provides insight into a broad array of disease states, but specimen collection is a hurdle for a variety of reasons, including patient resistance. A toilet seat developed by Toi Labs, called TrueLoo, is equipped with lighting and cameras that captures images of bowel movements and urination for subsequent analysis.

“The toilet seat sees what the eye cannot,” according to Vikram Kashyap, CEO of Toi Labs. He believes it has major potential for early detection of conditions ranging from dehydration to gastrointestinal cancer.

Vidyard Video

Others agree. According to Mr. Kashyap, executives of a chain of senior living facilities have already expressed interest in installing this seat to better monitor health among residents. The seat is bolted into position in place of any standard toilet seat. It collects images and data that are transmitted directly to a cellular network.

“Using our technology, the goal is to catch disease states early before they progress,” said Mr. Kashyap, who called the surveillance system a low-cost disease-screening tool. He believes the smart toilet seat could be of the most important disease detection devices developed in recent years.

AI to aid screening endoscopy

A third entrant in this year’s Shark Tank described a strategy to employ artificial intelligence (AI) to aid endoscopists in screening for dysplasia. The tool is called Ultivision and is being developed by a startup called Docbot. The CEO, Andrew Ninh, and a senior executive, Jason B. Samarasena, MD, outlined an idea that could be used in either screening colonoscopy or in surveillance of Barrett’s esophagus).

“Dysplasia is difficult to find. It is subtle and it is often missed. With better detection of dysplasia, artificial intelligence offers an opportunity to reduce risk of cancer,” Dr. Samarasena said.

The tool integrates seamlessly with existing endoscopic tools, according to Mr. Ninh. As tissue is visualized, the AI is programmed to highlight suspected dysplasia with a colored box to alert the endoscopist. The colonoscopy application is a more advanced stage of development and might be submitted for regulatory approval this year, he said. The same technology will be adapted for Barrett’s esophagus.

“It is like facial recognition for dysplasia,” said Dr. Samarasena.
 

Obesity phenotyping tool

A fourth Shark Tank entrant employs technology to phenotype obese patients to better tailor therapy. The Pheno Test, developed by Phenomix Sciences, applies “multi-omics” to a blood-based test to separate patients with obesity into four phenotypes. When therapy is tailored to the phenotype, weight loss is greater, according to Andres J. Acosta, MD, PhD, assistant professor of medicine and consultant in gastroenterology and hepatology at Mayo Clinic, Rochester, Minn.

In an initial study that compared weight loss in 55 patients treated based on phenotype with 175 patients managed with standard of care, the total body weight loss “more than doubled,” Dr. Acosta reported.

According to Dr. Acosta, obesity is driven by very different mechanisms. He described the four major phenotypes identified with his test as hungry brain (satiation signal is impaired), hungry gut (signals to eat are upregulated), emotional hunger (psychological reasons drive eating behavior), and slow metabolism (failure to burn fat at normal rates).

With the blood test, which utilizes hormones, metabolites, DNA, and other biomarkers to separate these phenotypes, treatment can be tailored appropriately, according to Dr. Acosta. His company is now seeking Food and Drug Administration clearance of the test, which he believes will have a major impact on obesity control.
 

 

 

Capsule diagnostic tool

The final entrant selected to participate in this year’s Shark Tank described an ingestible capsule that diagnoses diseases by detecting gases as it descends the gastrointestinal tract. The Atmo Gas Capsule from Atmo Biosciences measures gases at the source, accelerating the diagnosis of such diseases as irritable bowel syndrome (IBS) and IBD.

“By measuring gases at their source, the accuracy is far better than a breath test,” said Malcolm Hebblewhite, MBA, CEO of Atmo Biosciences. The capsule is an alternative to more invasive and expensive diagnostic tools and it is highly accurate.

Providing examples, Mr. Hebblewhite said that elevated levels of oxygen suggest a disorder of motility while an elevated level of carbon dioxide and hydrogen suggest IBS. The capsule transmits data to a small receiver and then on to a smartphone.

“The real-time data is displayed for the user with more complex information accessible by the practitioner remotely via the cloud,” Mr. Hebblewhite said. He cited several papers that have already been published documenting the potential of this technology.

“The capsule is a single-use disposable device that is not retrieved,” according to Mr. Hebblewhite. He reported that his company plans to pursue the diagnosis of motility as an initial clinical application. The diagnosis of IBS and other GI conditions will follow. Clinical studies are already planned.

SAN FRANCISCO – All five innovative startups pitched at the Shark Tank at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology, are in advanced stages of development, but only one is given the opportunity to be declared the winner of the competition. The ideas ranged from a smart toilet for early disease detection to a unique strategy for obesity phenotyping, but the winner by both official decision and popular vote was a smartphone app to help patients with inflammatory bowel disease (IBD) manage the condition.

“As always, this year’s Shark Tank was a highlight of the AGA Tech Summit and represents the progress our field is making when it comes to innovation. Our panel of sharks was focused on understanding the problem each innovation solved – that’s the key when determining if an idea is novel or innovation for innovation’s sake. We were impressed with all of the technologies presented, but ultimately chose the Oshi Health IBD app as our winner because of the impact it is already having on improving the health and care of IBD patients,” said V. Raman Muthusamy, MD, AGAF, chair of the AGA Center for GI Innovation and Technology.
 

The winner: Oshi pitches “all-in-one” IBD app

By both popular vote from those attending the AGA Tech Summit as well as the six-member Shark Tank panel, Oshi Health was selected as the 2019 Shark Tank winner for its IBD app. The app was designed to help patients track symptoms, a first step in understanding flare patterns, which differ substantially between patients and emphasize the need for a personalized plan for controlling disease.

Vidyard Video

“Since we launched last June at DDW^® we have had 40,000 downloads. We are the number one IBD management app,” reported Dan Weinstein, MBA, CEO of Oshi Health.

The available app represents the first of three phases as the functionality is expanded. Currently, in addition to using the app as a tracking tool, patients can find resources to learn about their disease and to communicate with other patients about their experiences. In a second phase, information gathered by the app will be made available to physicians to provide accurate current information about disease status to better individualize therapy.

Ultimately, the app is expected to guide treatment based on information it has collected on symptom patterns and other data collected over time, although this application is further down the road and will require regulatory approval if it is designed to provide clinical advice as expected, according to Mr. Weinstein.

However, benefits have already been seen. Mr. Weinstein cited data that associated the app with a 40% improvement in medication adherence and a nearly 60-day reduction in flare duration. Calling the app “the next chapter in treat-to-target” IBD management, he believes that this is an important step forward in digital health that will improve IBD outcomes. The Shark Tank panel agreed.
 

Runners-up: Other potential innovations to improve GI health

With or without Shark Tank endorsement, the other four startups described in the competition are moving forward. Each is designed to address an important unmet need with the potential to improve patient outcomes, which is a criterion for their inclusion in the competition.

 

 

The smart toilet seat

One involves a technologically advanced toilet seat. The new seat is based on the fact that fecal matter provides insight into a broad array of disease states, but specimen collection is a hurdle for a variety of reasons, including patient resistance. A toilet seat developed by Toi Labs, called TrueLoo, is equipped with lighting and cameras that captures images of bowel movements and urination for subsequent analysis.

“The toilet seat sees what the eye cannot,” according to Vikram Kashyap, CEO of Toi Labs. He believes it has major potential for early detection of conditions ranging from dehydration to gastrointestinal cancer.

Vidyard Video

Others agree. According to Mr. Kashyap, executives of a chain of senior living facilities have already expressed interest in installing this seat to better monitor health among residents. The seat is bolted into position in place of any standard toilet seat. It collects images and data that are transmitted directly to a cellular network.

“Using our technology, the goal is to catch disease states early before they progress,” said Mr. Kashyap, who called the surveillance system a low-cost disease-screening tool. He believes the smart toilet seat could be of the most important disease detection devices developed in recent years.

AI to aid screening endoscopy

A third entrant in this year’s Shark Tank described a strategy to employ artificial intelligence (AI) to aid endoscopists in screening for dysplasia. The tool is called Ultivision and is being developed by a startup called Docbot. The CEO, Andrew Ninh, and a senior executive, Jason B. Samarasena, MD, outlined an idea that could be used in either screening colonoscopy or in surveillance of Barrett’s esophagus).

“Dysplasia is difficult to find. It is subtle and it is often missed. With better detection of dysplasia, artificial intelligence offers an opportunity to reduce risk of cancer,” Dr. Samarasena said.

The tool integrates seamlessly with existing endoscopic tools, according to Mr. Ninh. As tissue is visualized, the AI is programmed to highlight suspected dysplasia with a colored box to alert the endoscopist. The colonoscopy application is a more advanced stage of development and might be submitted for regulatory approval this year, he said. The same technology will be adapted for Barrett’s esophagus.

“It is like facial recognition for dysplasia,” said Dr. Samarasena.
 

Obesity phenotyping tool

A fourth Shark Tank entrant employs technology to phenotype obese patients to better tailor therapy. The Pheno Test, developed by Phenomix Sciences, applies “multi-omics” to a blood-based test to separate patients with obesity into four phenotypes. When therapy is tailored to the phenotype, weight loss is greater, according to Andres J. Acosta, MD, PhD, assistant professor of medicine and consultant in gastroenterology and hepatology at Mayo Clinic, Rochester, Minn.

In an initial study that compared weight loss in 55 patients treated based on phenotype with 175 patients managed with standard of care, the total body weight loss “more than doubled,” Dr. Acosta reported.

According to Dr. Acosta, obesity is driven by very different mechanisms. He described the four major phenotypes identified with his test as hungry brain (satiation signal is impaired), hungry gut (signals to eat are upregulated), emotional hunger (psychological reasons drive eating behavior), and slow metabolism (failure to burn fat at normal rates).

With the blood test, which utilizes hormones, metabolites, DNA, and other biomarkers to separate these phenotypes, treatment can be tailored appropriately, according to Dr. Acosta. His company is now seeking Food and Drug Administration clearance of the test, which he believes will have a major impact on obesity control.
 

 

 

Capsule diagnostic tool

The final entrant selected to participate in this year’s Shark Tank described an ingestible capsule that diagnoses diseases by detecting gases as it descends the gastrointestinal tract. The Atmo Gas Capsule from Atmo Biosciences measures gases at the source, accelerating the diagnosis of such diseases as irritable bowel syndrome (IBS) and IBD.

“By measuring gases at their source, the accuracy is far better than a breath test,” said Malcolm Hebblewhite, MBA, CEO of Atmo Biosciences. The capsule is an alternative to more invasive and expensive diagnostic tools and it is highly accurate.

Providing examples, Mr. Hebblewhite said that elevated levels of oxygen suggest a disorder of motility while an elevated level of carbon dioxide and hydrogen suggest IBS. The capsule transmits data to a small receiver and then on to a smartphone.

“The real-time data is displayed for the user with more complex information accessible by the practitioner remotely via the cloud,” Mr. Hebblewhite said. He cited several papers that have already been published documenting the potential of this technology.

“The capsule is a single-use disposable device that is not retrieved,” according to Mr. Hebblewhite. He reported that his company plans to pursue the diagnosis of motility as an initial clinical application. The diagnosis of IBS and other GI conditions will follow. Clinical studies are already planned.

SAN FRANCISCO – A telemedicine platform that connects patients to registered dietitians is providing a solution for a number of interrelated unmet needs, according to a description at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Although not limited to patients with gastrointestinal diseases, the applications of this platform are illustrative of the value to both patients and the physicians who prescribe diet as part of the management of chronic conditions, according to Jonah Cohen, MD, who is a founder of the digital therapeutics company Nutrimedy, which created the platform for virtual nutritional counseling.

“As gastroenterologists, we are experts in the function of the gastrointestinal tract but not necessarily in nutrition. Most physicians get very little training in this area,” said Dr. Cohen, who is a gastroenterologist affiliated with Harvard Medical School and Beth Israel Deaconess Medical Center in Boston.

Even for those physicians who have expertise and an interest in nutrition, dietary counseling requires a substantial investment of time and continuity to affect behavior change. Helping patients develop an effective diet and implementation strategy to which they are willing to adhere is not a simple task. It requires recognizing and managing nuanced preferences and tastes. For most patients, frequent engagement with an expert is essential to remain on track.

“Nutrimedy’s proprietary matching system connects patients to their ideal dietitian who will help establish a specific nutrition plan for their medical conditions through video visits, unlimited messaging, photo food logs, recipes, and biometric trackers,” Dr. Cohen explained. “The key to the success of these relationships is based on the ease of clinical touch points we’re able to achieve through telenutrition when patients can ask questions, make modifications, and get positive feedback on their own time.”

Launched in 2016, Nutrimedy now has over 1,000 dietitians on its roster and a HIPAA-compliant device-agnostic platform to deliver best-in-class nutritional care remotely.

“The breadth of expertise of our providers enables us to provide medical nutrition therapy across a range of conditions, including irritable bowel syndrome (IBS), celiac disease, acid reflux, fatty liver disease, and gastroparesis to name just several, for patients anytime, anywhere,” according to Dr. Cohen.

In many places within the United States, there are few expert nutritionists with the specific expertise needed to manage a disease condition like IBS through low FODMAP (fermentable oligosaccharides, disaccharides, monosaccharides, and polyols) diet, and thus appointments are often hard to get for these providers, according to Dr. Cohen. Moreover, he explained that office visits are not just inconvenient but can be an obstacle to a successfully implemented dietary plan.

Other challenges may include cultural or language barriers. Dr. Cohen gave the example of Sophia, a busy mother of two with IBS, who is vegetarian, eats predominantly Spanish cuisine, lives in rural Massachusetts, and speaks Spanish. She prefers not to take medications and hopes to better manage her condition with a low FODMAP diet.

Nutrimedy draws on its roster of registered dietitians to find a good match for patients like Sophia. “Our vision is that everyone deserves to have an expert literally in their back pocket to help them on their journey to better health through food as medicine,” Dr. Cohen explained. He called Nutrimedy “a turn-key solution for GI practices who want to improve medical nutrition therapy for their patients.”

According to Dr. Cohen, Nutrimedy has already proven effective for its core mission of making effective nutritional counseling easier to obtain, and is now working to extend its reach. For example, Dr. Cohen said that the company has actively engaged with employers to provide corporate wellness solutions, and it is partnering with pharmaceutical and other life sciences companies who offer therapies relevant to nutritional health where Nutrimedy has potential to serve as a digital therapeutic companion.

“In almost every chronic condition, diet plays an important role in disease prevention or management,” said Dr. Cohen who believes his company is participating in the effort to reduce the burden of chronic disease related to poor diet. “I feel that in 2019 we’re at a tipping point where health care entities are finally recognizing that we can transform wellness in America through healthier eating.” He believes that Nutrimedy is poised “to play a part in this revolution.

SAN FRANCISCO – A telemedicine platform that connects patients to registered dietitians is providing a solution for a number of interrelated unmet needs, according to a description at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Although not limited to patients with gastrointestinal diseases, the applications of this platform are illustrative of the value to both patients and the physicians who prescribe diet as part of the management of chronic conditions, according to Jonah Cohen, MD, who is a founder of the digital therapeutics company Nutrimedy, which created the platform for virtual nutritional counseling.

“As gastroenterologists, we are experts in the function of the gastrointestinal tract but not necessarily in nutrition. Most physicians get very little training in this area,” said Dr. Cohen, who is a gastroenterologist affiliated with Harvard Medical School and Beth Israel Deaconess Medical Center in Boston.

Even for those physicians who have expertise and an interest in nutrition, dietary counseling requires a substantial investment of time and continuity to affect behavior change. Helping patients develop an effective diet and implementation strategy to which they are willing to adhere is not a simple task. It requires recognizing and managing nuanced preferences and tastes. For most patients, frequent engagement with an expert is essential to remain on track.

“Nutrimedy’s proprietary matching system connects patients to their ideal dietitian who will help establish a specific nutrition plan for their medical conditions through video visits, unlimited messaging, photo food logs, recipes, and biometric trackers,” Dr. Cohen explained. “The key to the success of these relationships is based on the ease of clinical touch points we’re able to achieve through telenutrition when patients can ask questions, make modifications, and get positive feedback on their own time.”

Launched in 2016, Nutrimedy now has over 1,000 dietitians on its roster and a HIPAA-compliant device-agnostic platform to deliver best-in-class nutritional care remotely.

“The breadth of expertise of our providers enables us to provide medical nutrition therapy across a range of conditions, including irritable bowel syndrome (IBS), celiac disease, acid reflux, fatty liver disease, and gastroparesis to name just several, for patients anytime, anywhere,” according to Dr. Cohen.

In many places within the United States, there are few expert nutritionists with the specific expertise needed to manage a disease condition like IBS through low FODMAP (fermentable oligosaccharides, disaccharides, monosaccharides, and polyols) diet, and thus appointments are often hard to get for these providers, according to Dr. Cohen. Moreover, he explained that office visits are not just inconvenient but can be an obstacle to a successfully implemented dietary plan.

Other challenges may include cultural or language barriers. Dr. Cohen gave the example of Sophia, a busy mother of two with IBS, who is vegetarian, eats predominantly Spanish cuisine, lives in rural Massachusetts, and speaks Spanish. She prefers not to take medications and hopes to better manage her condition with a low FODMAP diet.

Nutrimedy draws on its roster of registered dietitians to find a good match for patients like Sophia. “Our vision is that everyone deserves to have an expert literally in their back pocket to help them on their journey to better health through food as medicine,” Dr. Cohen explained. He called Nutrimedy “a turn-key solution for GI practices who want to improve medical nutrition therapy for their patients.”

According to Dr. Cohen, Nutrimedy has already proven effective for its core mission of making effective nutritional counseling easier to obtain, and is now working to extend its reach. For example, Dr. Cohen said that the company has actively engaged with employers to provide corporate wellness solutions, and it is partnering with pharmaceutical and other life sciences companies who offer therapies relevant to nutritional health where Nutrimedy has potential to serve as a digital therapeutic companion.

“In almost every chronic condition, diet plays an important role in disease prevention or management,” said Dr. Cohen who believes his company is participating in the effort to reduce the burden of chronic disease related to poor diet. “I feel that in 2019 we’re at a tipping point where health care entities are finally recognizing that we can transform wellness in America through healthier eating.” He believes that Nutrimedy is poised “to play a part in this revolution.

SAN FRANCISCO – A telemedicine platform that connects patients to registered dietitians is providing a solution for a number of interrelated unmet needs, according to a description at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Although not limited to patients with gastrointestinal diseases, the applications of this platform are illustrative of the value to both patients and the physicians who prescribe diet as part of the management of chronic conditions, according to Jonah Cohen, MD, who is a founder of the digital therapeutics company Nutrimedy, which created the platform for virtual nutritional counseling.

“As gastroenterologists, we are experts in the function of the gastrointestinal tract but not necessarily in nutrition. Most physicians get very little training in this area,” said Dr. Cohen, who is a gastroenterologist affiliated with Harvard Medical School and Beth Israel Deaconess Medical Center in Boston.

Even for those physicians who have expertise and an interest in nutrition, dietary counseling requires a substantial investment of time and continuity to affect behavior change. Helping patients develop an effective diet and implementation strategy to which they are willing to adhere is not a simple task. It requires recognizing and managing nuanced preferences and tastes. For most patients, frequent engagement with an expert is essential to remain on track.

“Nutrimedy’s proprietary matching system connects patients to their ideal dietitian who will help establish a specific nutrition plan for their medical conditions through video visits, unlimited messaging, photo food logs, recipes, and biometric trackers,” Dr. Cohen explained. “The key to the success of these relationships is based on the ease of clinical touch points we’re able to achieve through telenutrition when patients can ask questions, make modifications, and get positive feedback on their own time.”

Launched in 2016, Nutrimedy now has over 1,000 dietitians on its roster and a HIPAA-compliant device-agnostic platform to deliver best-in-class nutritional care remotely.

“The breadth of expertise of our providers enables us to provide medical nutrition therapy across a range of conditions, including irritable bowel syndrome (IBS), celiac disease, acid reflux, fatty liver disease, and gastroparesis to name just several, for patients anytime, anywhere,” according to Dr. Cohen.

In many places within the United States, there are few expert nutritionists with the specific expertise needed to manage a disease condition like IBS through low FODMAP (fermentable oligosaccharides, disaccharides, monosaccharides, and polyols) diet, and thus appointments are often hard to get for these providers, according to Dr. Cohen. Moreover, he explained that office visits are not just inconvenient but can be an obstacle to a successfully implemented dietary plan.

Other challenges may include cultural or language barriers. Dr. Cohen gave the example of Sophia, a busy mother of two with IBS, who is vegetarian, eats predominantly Spanish cuisine, lives in rural Massachusetts, and speaks Spanish. She prefers not to take medications and hopes to better manage her condition with a low FODMAP diet.

Nutrimedy draws on its roster of registered dietitians to find a good match for patients like Sophia. “Our vision is that everyone deserves to have an expert literally in their back pocket to help them on their journey to better health through food as medicine,” Dr. Cohen explained. He called Nutrimedy “a turn-key solution for GI practices who want to improve medical nutrition therapy for their patients.”

According to Dr. Cohen, Nutrimedy has already proven effective for its core mission of making effective nutritional counseling easier to obtain, and is now working to extend its reach. For example, Dr. Cohen said that the company has actively engaged with employers to provide corporate wellness solutions, and it is partnering with pharmaceutical and other life sciences companies who offer therapies relevant to nutritional health where Nutrimedy has potential to serve as a digital therapeutic companion.

“In almost every chronic condition, diet plays an important role in disease prevention or management,” said Dr. Cohen who believes his company is participating in the effort to reduce the burden of chronic disease related to poor diet. “I feel that in 2019 we’re at a tipping point where health care entities are finally recognizing that we can transform wellness in America through healthier eating.” He believes that Nutrimedy is poised “to play a part in this revolution.

SAN FRANCISCO – Patients are being better prepared for medical procedures, such as screening colonoscopy, through a new service based on smartphone texts that remind patients of steps to take prior to their procedure, according to a description at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

“The reminders mean fewer no shows and fewer cancellations, but in the case of colonoscopy we are also seeing better rates of adequate bowel prep and lower rates of aborted procedures,” reported Andy Pfau, chief operating officer, RxHealth, New York.

The texts are based on a patient-care pathway integrated with the electronic medical record (EMR) system. In the case of colonoscopy, once a physician creates an appointment in the EMR for a colonoscopy and selects the bowel prep, the system takes over, automatically obtaining access to the patient’s cell phone number in order to send reminder texts at intervals relevant to their appointment.

“The texts provide links to additional information so that patients are not only reminded to begin their bowel prep but can access instructions and supportive educational material,” Mr. Pfau explained.

“The messaging is not just limited to reminders. We can provide driving and parking instructions. We have also partnered with ride sharing companies to make it easier for patients to get to the facility. We can adjust the platform in a variety of ways to help patients show up prepared for the procedure,” he added.

The commercial tool, known as RxUniverse, was a spin off of a program developed at the Icahn School of Medicine at Mount Sinai. The problem of no shows and the importance of bowel prep makes this service particularly attractive in colonoscopy, according to Mr. Pfau, who cited data associating this tool with a 34% improvement in bowel preps and a more than 90% rate of patient satisfaction.

The same approach can and already is being employed in other procedures in GI, such as guiding patients scheduled for an upper endoscopy.

“We see a large role for this tool in comprehensive care plans because it is versatile and could be applied to a variety of care pathways, including forms of telemedicine, where timely communication through smartphone messaging could help patients adhere to goals of treatment,” Mr. Pfau said.

The tool can already be integrated with four EMR systems, including EPIC, but Mr. Pfau said the tool will ultimately be EMR agonistic according to current plans. While the company spun out of Mount Sinai in late 2016, RxHealth began marketing the RxUniverse prescription platform in earnest in 2018.

“In the last eight or so months, growth has been exponential,” Mr. Pfau said. In addition to growth in the U.S., the program is now being marketed overseas. He named several large medical systems that have already adopted the technology, including the Arizona Centers for Digestive Health and Yale New Haven Health. The American Gastroenterological Association, recognizing the value of this innovation for GI, has also partnered with RxHealth to help bring this product to its members.

As the automated pathway is integrated into existing EMR systems, the per-patient cost of the pathway is relatively low, according to Mr. Pfau. In situations in which the service increases the proportion of procedures completed successfully, it is reasonable to expect a highly favorable return on investment.

“There is a lot of interest in the potential of mobile devices to be employed in various ways to communicate and inform patients. This is part of that, and we think it is just the beginning. We are looking at a number of ways in which we can expand the platform and make it even more valuable,” Mr. Pfau said.

SAN FRANCISCO – Patients are being better prepared for medical procedures, such as screening colonoscopy, through a new service based on smartphone texts that remind patients of steps to take prior to their procedure, according to a description at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

“The reminders mean fewer no shows and fewer cancellations, but in the case of colonoscopy we are also seeing better rates of adequate bowel prep and lower rates of aborted procedures,” reported Andy Pfau, chief operating officer, RxHealth, New York.

The texts are based on a patient-care pathway integrated with the electronic medical record (EMR) system. In the case of colonoscopy, once a physician creates an appointment in the EMR for a colonoscopy and selects the bowel prep, the system takes over, automatically obtaining access to the patient’s cell phone number in order to send reminder texts at intervals relevant to their appointment.

“The texts provide links to additional information so that patients are not only reminded to begin their bowel prep but can access instructions and supportive educational material,” Mr. Pfau explained.

“The messaging is not just limited to reminders. We can provide driving and parking instructions. We have also partnered with ride sharing companies to make it easier for patients to get to the facility. We can adjust the platform in a variety of ways to help patients show up prepared for the procedure,” he added.

The commercial tool, known as RxUniverse, was a spin off of a program developed at the Icahn School of Medicine at Mount Sinai. The problem of no shows and the importance of bowel prep makes this service particularly attractive in colonoscopy, according to Mr. Pfau, who cited data associating this tool with a 34% improvement in bowel preps and a more than 90% rate of patient satisfaction.

The same approach can and already is being employed in other procedures in GI, such as guiding patients scheduled for an upper endoscopy.

“We see a large role for this tool in comprehensive care plans because it is versatile and could be applied to a variety of care pathways, including forms of telemedicine, where timely communication through smartphone messaging could help patients adhere to goals of treatment,” Mr. Pfau said.

The tool can already be integrated with four EMR systems, including EPIC, but Mr. Pfau said the tool will ultimately be EMR agonistic according to current plans. While the company spun out of Mount Sinai in late 2016, RxHealth began marketing the RxUniverse prescription platform in earnest in 2018.

“In the last eight or so months, growth has been exponential,” Mr. Pfau said. In addition to growth in the U.S., the program is now being marketed overseas. He named several large medical systems that have already adopted the technology, including the Arizona Centers for Digestive Health and Yale New Haven Health. The American Gastroenterological Association, recognizing the value of this innovation for GI, has also partnered with RxHealth to help bring this product to its members.

As the automated pathway is integrated into existing EMR systems, the per-patient cost of the pathway is relatively low, according to Mr. Pfau. In situations in which the service increases the proportion of procedures completed successfully, it is reasonable to expect a highly favorable return on investment.

“There is a lot of interest in the potential of mobile devices to be employed in various ways to communicate and inform patients. This is part of that, and we think it is just the beginning. We are looking at a number of ways in which we can expand the platform and make it even more valuable,” Mr. Pfau said.

SAN FRANCISCO – Patients are being better prepared for medical procedures, such as screening colonoscopy, through a new service based on smartphone texts that remind patients of steps to take prior to their procedure, according to a description at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

“The reminders mean fewer no shows and fewer cancellations, but in the case of colonoscopy we are also seeing better rates of adequate bowel prep and lower rates of aborted procedures,” reported Andy Pfau, chief operating officer, RxHealth, New York.

The texts are based on a patient-care pathway integrated with the electronic medical record (EMR) system. In the case of colonoscopy, once a physician creates an appointment in the EMR for a colonoscopy and selects the bowel prep, the system takes over, automatically obtaining access to the patient’s cell phone number in order to send reminder texts at intervals relevant to their appointment.

“The texts provide links to additional information so that patients are not only reminded to begin their bowel prep but can access instructions and supportive educational material,” Mr. Pfau explained.

“The messaging is not just limited to reminders. We can provide driving and parking instructions. We have also partnered with ride sharing companies to make it easier for patients to get to the facility. We can adjust the platform in a variety of ways to help patients show up prepared for the procedure,” he added.

The commercial tool, known as RxUniverse, was a spin off of a program developed at the Icahn School of Medicine at Mount Sinai. The problem of no shows and the importance of bowel prep makes this service particularly attractive in colonoscopy, according to Mr. Pfau, who cited data associating this tool with a 34% improvement in bowel preps and a more than 90% rate of patient satisfaction.

The same approach can and already is being employed in other procedures in GI, such as guiding patients scheduled for an upper endoscopy.

“We see a large role for this tool in comprehensive care plans because it is versatile and could be applied to a variety of care pathways, including forms of telemedicine, where timely communication through smartphone messaging could help patients adhere to goals of treatment,” Mr. Pfau said.

The tool can already be integrated with four EMR systems, including EPIC, but Mr. Pfau said the tool will ultimately be EMR agonistic according to current plans. While the company spun out of Mount Sinai in late 2016, RxHealth began marketing the RxUniverse prescription platform in earnest in 2018.

“In the last eight or so months, growth has been exponential,” Mr. Pfau said. In addition to growth in the U.S., the program is now being marketed overseas. He named several large medical systems that have already adopted the technology, including the Arizona Centers for Digestive Health and Yale New Haven Health. The American Gastroenterological Association, recognizing the value of this innovation for GI, has also partnered with RxHealth to help bring this product to its members.

As the automated pathway is integrated into existing EMR systems, the per-patient cost of the pathway is relatively low, according to Mr. Pfau. In situations in which the service increases the proportion of procedures completed successfully, it is reasonable to expect a highly favorable return on investment.

“There is a lot of interest in the potential of mobile devices to be employed in various ways to communicate and inform patients. This is part of that, and we think it is just the beginning. We are looking at a number of ways in which we can expand the platform and make it even more valuable,” Mr. Pfau said.

SAN FRANCISCO – It is now reasonable to conclude that many of the endoscopic devices and procedures developed for the treatment of gastroesophageal reflux disease (GERD) offer good short-term efficacy, leaving only the task to understand how these fit with competing options to improve quality of life long term, according to a state-of-the-art summary at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

“The quality of the data for many of these devices has improved substantially, putting us in a much better place than we were in 4 or 5 years ago in considering their role,” reported Michael F. Vaezi, MD, PhD, professor of medicine, Vanderbilt University, Nashville, Tenn.

Over the past 15 years, an array of endoscopic approaches to treatment of GERD has received FDA approval. Examples of the very different techniques include plication devices that can suture, staple, or otherwise prevent reflux at the gastroesophageal junction (GEJ), and interventions aimed at the lower esophageal sphincter (LES), where placement of magnets or radiofrequency ablation has been employed to achieve a tighter defense against transient reflux episodes.

Despite FDA approval, the supportive evidence for many of these endoscopic interventions was criticized. In some cases, the number of patients evaluated in pivotal studies was considered too small. In others, there were objections to methodology, particularly to the choice of control arm. In all cases, there has been concern that follow-up was insufficient to confirm persistent benefit. Many of these criticisms are dissipating under the weight of more data.

“For most of the currently available, FDA-approved devices, there is now a substantial body of at least short-term data showing efficacy and safety,” reported Dr. Vaezi, who is a coauthor of an expert review now being prepared for publication. “This includes evidence that they improve quality of life, reduce the need for acid-suppressing therapy, and reduce esophageal acid exposure.”

Additional follow-up represents the final hurdle for understanding how these endoscopic interventions fit for extended symptom control. The long-term efficacy of the current standards of chronic proton pump inhibitor (PPI) therapy and surgical fundoplication has been established. Among these options, the choice is indefinite pharmacologic therapy or a surgical procedure. Endoscopic devices add additional options, but not with clear conclusions to be drawn on persistence of benefit.

Patient selection is an important consideration. Dr. Vaezi outlined three groups of patients: Patients who have responded to once-daily PPIs and are doing well, but would prefer not to take them indefinitely; PPI non-responders; and patients with improved heartburn but no improvement in regurgitation. Responders are reasonable candidates for endoscopic interventions, but non-responders are not, according to Dr. Vaezi. “You’re exposing the patient to the risk without the benefit, because they don’t have reflux. It’s something else,” he said.

Patients with improved heartburn but no change in regurgitation may be a candidate for endoscopic devices, as long as the clinician rules out non-reflux causes such as achalasia or gastroparesis.

“In patients being considered for alternative nonmedical therapy, it is essential to show that their symptoms are acid related. Those who do not respond to a PPI have traditionally not been good surgical candidates because the lack of a response suggests that acid reflux is not the source of their complaints. For patients being considered for an endoscopic treatment, we must apply the same time proven strategy. At this point, what is uncertain about the device therapies is the long-term durability for reflux control,” Dr. Vaezi said.

PPIs are effective for acid control, so the reason to consider an invasive treatment strategy is to avoid chronic PPI treatment. This is an increasingly attractive goal for many patients as a result of well-publicized case-control studies associating PPI use with a variety of increased risks, such as osteoporosis, chronic kidney disease, and gastrointestinal infections, but many gastroenterologists have been slow to recommend endoscopic interventions due to enduring concerns about safety and efficacy.

From his survey of the evidence, Dr. Vaezi characterized himself as “cautiously optimistic” that many of the endoscopic interventions will be included among standard options for durable GERD treatment.

SAN FRANCISCO – It is now reasonable to conclude that many of the endoscopic devices and procedures developed for the treatment of gastroesophageal reflux disease (GERD) offer good short-term efficacy, leaving only the task to understand how these fit with competing options to improve quality of life long term, according to a state-of-the-art summary at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

“The quality of the data for many of these devices has improved substantially, putting us in a much better place than we were in 4 or 5 years ago in considering their role,” reported Michael F. Vaezi, MD, PhD, professor of medicine, Vanderbilt University, Nashville, Tenn.

Over the past 15 years, an array of endoscopic approaches to treatment of GERD has received FDA approval. Examples of the very different techniques include plication devices that can suture, staple, or otherwise prevent reflux at the gastroesophageal junction (GEJ), and interventions aimed at the lower esophageal sphincter (LES), where placement of magnets or radiofrequency ablation has been employed to achieve a tighter defense against transient reflux episodes.

Despite FDA approval, the supportive evidence for many of these endoscopic interventions was criticized. In some cases, the number of patients evaluated in pivotal studies was considered too small. In others, there were objections to methodology, particularly to the choice of control arm. In all cases, there has been concern that follow-up was insufficient to confirm persistent benefit. Many of these criticisms are dissipating under the weight of more data.

“For most of the currently available, FDA-approved devices, there is now a substantial body of at least short-term data showing efficacy and safety,” reported Dr. Vaezi, who is a coauthor of an expert review now being prepared for publication. “This includes evidence that they improve quality of life, reduce the need for acid-suppressing therapy, and reduce esophageal acid exposure.”

Additional follow-up represents the final hurdle for understanding how these endoscopic interventions fit for extended symptom control. The long-term efficacy of the current standards of chronic proton pump inhibitor (PPI) therapy and surgical fundoplication has been established. Among these options, the choice is indefinite pharmacologic therapy or a surgical procedure. Endoscopic devices add additional options, but not with clear conclusions to be drawn on persistence of benefit.

Patient selection is an important consideration. Dr. Vaezi outlined three groups of patients: Patients who have responded to once-daily PPIs and are doing well, but would prefer not to take them indefinitely; PPI non-responders; and patients with improved heartburn but no improvement in regurgitation. Responders are reasonable candidates for endoscopic interventions, but non-responders are not, according to Dr. Vaezi. “You’re exposing the patient to the risk without the benefit, because they don’t have reflux. It’s something else,” he said.

Patients with improved heartburn but no change in regurgitation may be a candidate for endoscopic devices, as long as the clinician rules out non-reflux causes such as achalasia or gastroparesis.

“In patients being considered for alternative nonmedical therapy, it is essential to show that their symptoms are acid related. Those who do not respond to a PPI have traditionally not been good surgical candidates because the lack of a response suggests that acid reflux is not the source of their complaints. For patients being considered for an endoscopic treatment, we must apply the same time proven strategy. At this point, what is uncertain about the device therapies is the long-term durability for reflux control,” Dr. Vaezi said.

PPIs are effective for acid control, so the reason to consider an invasive treatment strategy is to avoid chronic PPI treatment. This is an increasingly attractive goal for many patients as a result of well-publicized case-control studies associating PPI use with a variety of increased risks, such as osteoporosis, chronic kidney disease, and gastrointestinal infections, but many gastroenterologists have been slow to recommend endoscopic interventions due to enduring concerns about safety and efficacy.

From his survey of the evidence, Dr. Vaezi characterized himself as “cautiously optimistic” that many of the endoscopic interventions will be included among standard options for durable GERD treatment.

SAN FRANCISCO – It is now reasonable to conclude that many of the endoscopic devices and procedures developed for the treatment of gastroesophageal reflux disease (GERD) offer good short-term efficacy, leaving only the task to understand how these fit with competing options to improve quality of life long term, according to a state-of-the-art summary at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

“The quality of the data for many of these devices has improved substantially, putting us in a much better place than we were in 4 or 5 years ago in considering their role,” reported Michael F. Vaezi, MD, PhD, professor of medicine, Vanderbilt University, Nashville, Tenn.

Over the past 15 years, an array of endoscopic approaches to treatment of GERD has received FDA approval. Examples of the very different techniques include plication devices that can suture, staple, or otherwise prevent reflux at the gastroesophageal junction (GEJ), and interventions aimed at the lower esophageal sphincter (LES), where placement of magnets or radiofrequency ablation has been employed to achieve a tighter defense against transient reflux episodes.

Despite FDA approval, the supportive evidence for many of these endoscopic interventions was criticized. In some cases, the number of patients evaluated in pivotal studies was considered too small. In others, there were objections to methodology, particularly to the choice of control arm. In all cases, there has been concern that follow-up was insufficient to confirm persistent benefit. Many of these criticisms are dissipating under the weight of more data.

“For most of the currently available, FDA-approved devices, there is now a substantial body of at least short-term data showing efficacy and safety,” reported Dr. Vaezi, who is a coauthor of an expert review now being prepared for publication. “This includes evidence that they improve quality of life, reduce the need for acid-suppressing therapy, and reduce esophageal acid exposure.”

Additional follow-up represents the final hurdle for understanding how these endoscopic interventions fit for extended symptom control. The long-term efficacy of the current standards of chronic proton pump inhibitor (PPI) therapy and surgical fundoplication has been established. Among these options, the choice is indefinite pharmacologic therapy or a surgical procedure. Endoscopic devices add additional options, but not with clear conclusions to be drawn on persistence of benefit.

Patient selection is an important consideration. Dr. Vaezi outlined three groups of patients: Patients who have responded to once-daily PPIs and are doing well, but would prefer not to take them indefinitely; PPI non-responders; and patients with improved heartburn but no improvement in regurgitation. Responders are reasonable candidates for endoscopic interventions, but non-responders are not, according to Dr. Vaezi. “You’re exposing the patient to the risk without the benefit, because they don’t have reflux. It’s something else,” he said.

Patients with improved heartburn but no change in regurgitation may be a candidate for endoscopic devices, as long as the clinician rules out non-reflux causes such as achalasia or gastroparesis.

“In patients being considered for alternative nonmedical therapy, it is essential to show that their symptoms are acid related. Those who do not respond to a PPI have traditionally not been good surgical candidates because the lack of a response suggests that acid reflux is not the source of their complaints. For patients being considered for an endoscopic treatment, we must apply the same time proven strategy. At this point, what is uncertain about the device therapies is the long-term durability for reflux control,” Dr. Vaezi said.

PPIs are effective for acid control, so the reason to consider an invasive treatment strategy is to avoid chronic PPI treatment. This is an increasingly attractive goal for many patients as a result of well-publicized case-control studies associating PPI use with a variety of increased risks, such as osteoporosis, chronic kidney disease, and gastrointestinal infections, but many gastroenterologists have been slow to recommend endoscopic interventions due to enduring concerns about safety and efficacy.

From his survey of the evidence, Dr. Vaezi characterized himself as “cautiously optimistic” that many of the endoscopic interventions will be included among standard options for durable GERD treatment.

SAN FRANCISCO – Dr. Michael Docktor, a pediatric gastroenterologist at Boston Hospital, described myriad digital tools that physicians – especially gastroenterologists – as well as patients are now using. Some tools may be implemented to track stool output or diet for diseases like irritable bowel syndrome or Crohn’s disease, he said in an interview at the AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

There are patient-facing applications that provide data that can be used by both patients and their physicians to better understand the disease. These data can help in diagnosis and management and give the GI doctor a “window into the 99% of the time that they aren’t with the patient.” Other apps can build a timeline of the disease that can help the patient get a better understanding of their disease and learn to distinguish a flare from a bad day with poor food choices. Dr. Docktor described the AGA Tech Summit as a place to try out new ideas and work with like-minded doctors.

SAN FRANCISCO – Dr. Michael Docktor, a pediatric gastroenterologist at Boston Hospital, described myriad digital tools that physicians – especially gastroenterologists – as well as patients are now using. Some tools may be implemented to track stool output or diet for diseases like irritable bowel syndrome or Crohn’s disease, he said in an interview at the AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

There are patient-facing applications that provide data that can be used by both patients and their physicians to better understand the disease. These data can help in diagnosis and management and give the GI doctor a “window into the 99% of the time that they aren’t with the patient.” Other apps can build a timeline of the disease that can help the patient get a better understanding of their disease and learn to distinguish a flare from a bad day with poor food choices. Dr. Docktor described the AGA Tech Summit as a place to try out new ideas and work with like-minded doctors.

SAN FRANCISCO – Dr. Michael Docktor, a pediatric gastroenterologist at Boston Hospital, described myriad digital tools that physicians – especially gastroenterologists – as well as patients are now using. Some tools may be implemented to track stool output or diet for diseases like irritable bowel syndrome or Crohn’s disease, he said in an interview at the AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

There are patient-facing applications that provide data that can be used by both patients and their physicians to better understand the disease. These data can help in diagnosis and management and give the GI doctor a “window into the 99% of the time that they aren’t with the patient.” Other apps can build a timeline of the disease that can help the patient get a better understanding of their disease and learn to distinguish a flare from a bad day with poor food choices. Dr. Docktor described the AGA Tech Summit as a place to try out new ideas and work with like-minded doctors.

SAN FRANCISCO – The potential power of machine learning to improve therapeutic choices in inflammatory bowel disease (IBD) is at the threshold of clinical applications, according to data presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Joel Austell/MDedge News

This type of work is relevant to many fields of medicine, but studies conducted in IBD have provided particularly compelling evidence that predictive analytics will improve outcomes and lead to more cost-effective delivery of care, according to Akbar K. Waljee, MD, MSc, an associate professor in the division of gastroenterology, University of Michigan, Ann Arbor, and a staff physician and researcher at the VA Ann Arbor Healthcare System.

Having now published several papers on the role of precision analytics and big data to improve treatment choices in IBD as well as other diseases, Dr. Waljee said, “We collect large amounts of clinical data every day in the delivery of health care but we are now only just beginning to leverage [these] data to guide treatment.”

Based on the experience in IBD, these analyses are relevant for selecting who to treat and not to treat with a given drug.

In one study of how this technology can be applied, data from 1,080 IBD patients taking thiopurines were used to develop a machine learning algorithm that analyzed multiple readily available variables, such as a complete blood count with differential and a chemistry panel, to predict if the patient was in remission. The area under the receiver operating characteristics curve (AuROC) was 0.79 or much higher than previous prediction using drug metabolites, according to Dr. Waljee.

The mean yearly rate of clinical events (new steroid prescriptions, hospitalizations, and abdominal surgeries) was then compared between those who did and those who did not have an algorithm-predicted remission. The lower mean rate in those predicted to be in remission (1.08 vs. 3.95 events) provided support for the conclusions that the algorithm is clinically viable.

“The heterogeneity of response to therapies for IBD is well established. If machine learning predicts effective choices, there will be an opportunity to accelerate the time to disease control as well as save costs by avoiding therapies not likely to be effective,” Dr. Waljee explained.

In another example, the focus was on predicting response to vedolizumab, a monoclonal antibody targeted at a gut-specific mediator of inflammation. In this case, machine learning was applied to predicting corticosteroid-free remission at 1 year in patients with Crohn’s disease patients evaluated 6 weeks after initiating therapy. The machine-learning algorithm was based on an analysis of numerous variables, including laboratory data, sex, and race. Based on the model drawn from the analysis of 472 patients, 35.8% of the patients predicted to be in corticosteroid-free biologic remission at 1 year achieved this endpoint, whereas only 6.7% of the patients predicted to fail achieved the endpoint.

“This suggests that we can use an algorithm relatively early in the course of this biologic to predict who is going to respond,” reported Dr. Waljee. Again, patients with a low likelihood of response at 6 weeks can be started on an alternative therapy, potentially accelerating the time to disease control and avoiding the costs of ineffective and expensive treatments.

IBD is a particularly attractive focus of precision analytics with big data. IBD has a relatively unpredictable relapsing-remitting course and a variable heterogeneous response to available therapies. Algorithms predictive of response circumvent the inherent delays from evaluating disease control over an extended period.

“With ever increasing concern about costs of care and access to care, these treatment algorithms promise to use resources more efficiently,” Dr. Waljee said.

SAN FRANCISCO – The potential power of machine learning to improve therapeutic choices in inflammatory bowel disease (IBD) is at the threshold of clinical applications, according to data presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Joel Austell/MDedge News

This type of work is relevant to many fields of medicine, but studies conducted in IBD have provided particularly compelling evidence that predictive analytics will improve outcomes and lead to more cost-effective delivery of care, according to Akbar K. Waljee, MD, MSc, an associate professor in the division of gastroenterology, University of Michigan, Ann Arbor, and a staff physician and researcher at the VA Ann Arbor Healthcare System.

Having now published several papers on the role of precision analytics and big data to improve treatment choices in IBD as well as other diseases, Dr. Waljee said, “We collect large amounts of clinical data every day in the delivery of health care but we are now only just beginning to leverage [these] data to guide treatment.”

Based on the experience in IBD, these analyses are relevant for selecting who to treat and not to treat with a given drug.

In one study of how this technology can be applied, data from 1,080 IBD patients taking thiopurines were used to develop a machine learning algorithm that analyzed multiple readily available variables, such as a complete blood count with differential and a chemistry panel, to predict if the patient was in remission. The area under the receiver operating characteristics curve (AuROC) was 0.79 or much higher than previous prediction using drug metabolites, according to Dr. Waljee.

The mean yearly rate of clinical events (new steroid prescriptions, hospitalizations, and abdominal surgeries) was then compared between those who did and those who did not have an algorithm-predicted remission. The lower mean rate in those predicted to be in remission (1.08 vs. 3.95 events) provided support for the conclusions that the algorithm is clinically viable.

“The heterogeneity of response to therapies for IBD is well established. If machine learning predicts effective choices, there will be an opportunity to accelerate the time to disease control as well as save costs by avoiding therapies not likely to be effective,” Dr. Waljee explained.

In another example, the focus was on predicting response to vedolizumab, a monoclonal antibody targeted at a gut-specific mediator of inflammation. In this case, machine learning was applied to predicting corticosteroid-free remission at 1 year in patients with Crohn’s disease patients evaluated 6 weeks after initiating therapy. The machine-learning algorithm was based on an analysis of numerous variables, including laboratory data, sex, and race. Based on the model drawn from the analysis of 472 patients, 35.8% of the patients predicted to be in corticosteroid-free biologic remission at 1 year achieved this endpoint, whereas only 6.7% of the patients predicted to fail achieved the endpoint.

“This suggests that we can use an algorithm relatively early in the course of this biologic to predict who is going to respond,” reported Dr. Waljee. Again, patients with a low likelihood of response at 6 weeks can be started on an alternative therapy, potentially accelerating the time to disease control and avoiding the costs of ineffective and expensive treatments.

IBD is a particularly attractive focus of precision analytics with big data. IBD has a relatively unpredictable relapsing-remitting course and a variable heterogeneous response to available therapies. Algorithms predictive of response circumvent the inherent delays from evaluating disease control over an extended period.

“With ever increasing concern about costs of care and access to care, these treatment algorithms promise to use resources more efficiently,” Dr. Waljee said.

SAN FRANCISCO – The potential power of machine learning to improve therapeutic choices in inflammatory bowel disease (IBD) is at the threshold of clinical applications, according to data presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

Joel Austell/MDedge News

This type of work is relevant to many fields of medicine, but studies conducted in IBD have provided particularly compelling evidence that predictive analytics will improve outcomes and lead to more cost-effective delivery of care, according to Akbar K. Waljee, MD, MSc, an associate professor in the division of gastroenterology, University of Michigan, Ann Arbor, and a staff physician and researcher at the VA Ann Arbor Healthcare System.

Having now published several papers on the role of precision analytics and big data to improve treatment choices in IBD as well as other diseases, Dr. Waljee said, “We collect large amounts of clinical data every day in the delivery of health care but we are now only just beginning to leverage [these] data to guide treatment.”

Based on the experience in IBD, these analyses are relevant for selecting who to treat and not to treat with a given drug.

In one study of how this technology can be applied, data from 1,080 IBD patients taking thiopurines were used to develop a machine learning algorithm that analyzed multiple readily available variables, such as a complete blood count with differential and a chemistry panel, to predict if the patient was in remission. The area under the receiver operating characteristics curve (AuROC) was 0.79 or much higher than previous prediction using drug metabolites, according to Dr. Waljee.

The mean yearly rate of clinical events (new steroid prescriptions, hospitalizations, and abdominal surgeries) was then compared between those who did and those who did not have an algorithm-predicted remission. The lower mean rate in those predicted to be in remission (1.08 vs. 3.95 events) provided support for the conclusions that the algorithm is clinically viable.

“The heterogeneity of response to therapies for IBD is well established. If machine learning predicts effective choices, there will be an opportunity to accelerate the time to disease control as well as save costs by avoiding therapies not likely to be effective,” Dr. Waljee explained.

In another example, the focus was on predicting response to vedolizumab, a monoclonal antibody targeted at a gut-specific mediator of inflammation. In this case, machine learning was applied to predicting corticosteroid-free remission at 1 year in patients with Crohn’s disease patients evaluated 6 weeks after initiating therapy. The machine-learning algorithm was based on an analysis of numerous variables, including laboratory data, sex, and race. Based on the model drawn from the analysis of 472 patients, 35.8% of the patients predicted to be in corticosteroid-free biologic remission at 1 year achieved this endpoint, whereas only 6.7% of the patients predicted to fail achieved the endpoint.

“This suggests that we can use an algorithm relatively early in the course of this biologic to predict who is going to respond,” reported Dr. Waljee. Again, patients with a low likelihood of response at 6 weeks can be started on an alternative therapy, potentially accelerating the time to disease control and avoiding the costs of ineffective and expensive treatments.

IBD is a particularly attractive focus of precision analytics with big data. IBD has a relatively unpredictable relapsing-remitting course and a variable heterogeneous response to available therapies. Algorithms predictive of response circumvent the inherent delays from evaluating disease control over an extended period.

“With ever increasing concern about costs of care and access to care, these treatment algorithms promise to use resources more efficiently,” Dr. Waljee said.