The AI revolution in gastroenterology is closer than we think
This transcript has been edited for clarity.
What is artificial intelligence (AI)? This technological term refers to the ability of a computer to perform tasks usually associated with humans. An example of AI is the ability of computers to learn, a very complicated cognitive function that mimics the human mind. In machine learning, a computer can “learn” data, such as pattern recognition from medical images, without ever programming itself.
In recent years, researchers have been working to apply AI to the field of gastroenterology, with great success.
colorectal cancer is the second leading cause of cancer death in the U.S. As gastroenterologists, we are all excited about the potential use of the power of AI to help us with image analysis during colonoscopies to help identify polyps. Computer Aided Detection Software is being used to improve detection rates of adenoma polyps. By removing these polyps during colonoscopy procedures, we can prevent colon cancer in our patients.
The US Food and Drug Administration (FDA) recently approved a really cool technology called GI Genius. This is an artificial intelligence/machine learning program that helps detect polyps in real time, with a little square box highlighting the polyp, like those radars fixed on military targets in airplane movies like top gun.
AI can be used to find both malignant lesions and premalignant lesions. A recent meta-analysis of barua and colleaguesincluding five randomized controlled trials and 4311 patients, showed that the adenoma detection rate was much better with a combination of computer-assisted detection software with colonoscopy (29.6%) compared with colonoscopy alone (19.3%). .
Computer-assisted screening with colonoscopy can also improve the detection of small or tiny polyps < 5 mm in size.
Use of AI in gastrointestinal and liver diseases
We have also shown that AI can help gastroenterologists detect dysplasia, esophagus cancerand gastric cancers when using esophagogastroduodenoscopyor the upper endoscopes that we use to look at the patient’s esophagus and stomach.
Liver disease causes 2 million deaths worldwide, and the prevalence of non-alcoholic fatty liver disease is 25%. We have also been using AI to help make liver diagnoses for several years using ultrasound technology, to help analyze the severity of fatty liver disease and determine the stage of liver fibrosis. AI can help radiologists and gastroenterologists interpret ultrasound images and differentiate between benign and Liver cancer.
This is important because of the potential element of human error caused by exhaustion from reading a large volume of images or challenges with interpretation. Currently, we are using AI algorithms such as traditional machine learning and deep learning. These are really important AI applications because ultrasound is widely available and really cheap.
Radiomics is a type of machine learning that is popular in CT, MRI, and ultrasound. This AI in images can help clinicians identify complicated patterns that are difficult to recognize with the human eye.
Machine learning has also been used to distinguish ulcerative colitis since Crohn’s disease in pediatric patients.
The artificial neural network has also been used to predict how often patients with Inflammatory bowel disease they’re going to break out, with a fairly high level of precision, by analyzing data from our health records. We hope that in the future clinicians will be able to use AI to select successful medical therapies for patients with ulcerative colitis and Crohn’s disease.
The artificial neural network has also been used to predict 1-year mortality with 90% accuracy in patients with cirrhosis. This could help us with Liver transplant future evaluations.
We can also use AI to predict prognosis after thermal ablation of liver cancer. With the help of AI in liver cancer, we can predict the curative potential using transarterial chemoembolization.
AI can also be used to improve the diagnostic capabilities of endoscopic ultrasound, which is a type of ultrasound probe attached to an endoscope to detect pancreatic cancer and intraductal papillary mucinous neoplasms. AI has also been used to help gastroenterologists detect pancreatic cancer based on both endoscopic ultrasound and serum markers. We are hopeful that in the future, AI can help us detect pancreatic cancer at earlier stages and help us save patients’ lives.
Oncologists can now use AI-powered endoscopic ultrasound to provide additional information about rectal cancer before surgery and to improve treatment.
A technology ready for use in prime time
The FDA has developed regulatory plans to closely evaluate and approve updates and modifications to AI software technology. AI software producers will be able to update software for oscilloscopes, ultrasound, CT and MRI scans remotely and instantly over Wi-Fi, just like our smartphone devices are constantly being updated today.
Now here’s something really cool. AI can now help us monitor patients from home, the holy grail of medicine. For example, we have the ability to measure fecal calprotectin, an inflammatory marker in patients with inflammatory bowel disease, using smartphones, which could help us better recognize the beginnings of a flare before our patient feels sick, and provide doctors the opportunity to intervene sooner.
This is an incredibly exciting and revolutionary time within gastroenterology. Technological advances in imaging capabilities and computing power allow us to synergistically detect precancerous lesions and cancer more easily while performing endoscopy. Gastroenterologists are ready to embrace these emerging technologies as they become ready for prime-time clinical use.
Benjamin H. Levy III, MD, is a board-certified gastroenterologist from the University of Chicago. His clinical projects focus on disparities in medical care and the development of colon cancer screening campaigns. Previously, as the division chief of gastroenterology at Mount Sinai Hospital, Dr. Levy organized a gastroenterology clinic for refugees resettling in Chicago. He is a member of the American College of Gastroenterology (ACG) Public Relations Committee and the FDA Related Affairs Committee. During the COVID-19 pandemic, Dr. Levy started an international health education campaign called “Concerts and Cocktails” that brought together musicians with doctors and nurses on the front lines. He subsequently was selected to be a TEDxWrigleyville speaker for “Humanity: An Inside View of the Pandemic.” An avid cellist, Dr. Levy most recently served as co-chair of the Chicago Symphony Orchestra’s Soundpost Series. In 2021, he started Tune It Up: A Concert to Raise Colorectal Cancer Awareness with ACG.