At this year’s American College of Gastroenterology (ACG) 2024 Annual Scientific Meeting, researchers, clinicians, and industry leaders came together to showcase breakthroughs in gastroenterology. One of the central themes? The growing role of machine learning (ML) in transforming how inflammatory bowel disease (IBD) is assessed, treated, and studied in clinical trials.
We’ve distilled the highlights of this research into an infographic you can download here. Below is a breakdown of the key insights, including abstracts presented in partnership with leading academic institutions and life sciences organizations.
The Challenge: Limitations in Traditional Endoscopic Assessments
Endoscopic evaluation remains a cornerstone of IBD diagnosis and treatment monitoring. Yet today’s standard methods are:
- Time-consuming and resource-intensive
- Prone to **inter-observer variability**
- Often not reflective of real-world patient populations
As a result, the data driving drug development and treatment strategies can be inconsistent, leading to challenges in both clinical trial execution and patient care.
The Opportunity: ML-Enabled Endoscopic Analysis
At ACG 2024, five abstracts from Iterative Health and partners explored how ML is helping to overcome these barriers by:
- Objectively scoring disease activity from endoscopic videos
- Combining EHR and video data to generate real-world evidence
- Uncovering root causes of variability in human scoring
- Supporting precision medicine in community settings
Core Research Highlights:
Systematic Review on ML Model Performance
Accuracy in predicting endoscopic Mayo scores ranged from 56.8% to 83.3% across six unique test cohorts.
Head-to-Head Algorithm Comparison (Presidential Poster Winner)
Iterative Health’s ML models achieved 81–88% accuracy for response detection and 92–96% for remission scoring.
Real-World Data Study
Linked endoscopic video and EHR data revealed insights into how disease characteristics influence treatment decisions in community settings.
Video Quality and Reader Disagreement
Poor bowel prep was a leading factor in central reader variability, highlighting the need for more standardized assessments.
“Our ongoing research with Iterative Health shows the immense potential of their machine learning tools to refine endoscopic assessments and thereby enhance the drug development process, ultimately improving long-term patient outcomes.” — Dr. David T. Rubin, University of Chicago Medicine
Why It Matters for Clinical Trials and Patient Care
Machine learning models that assess disease severity offer:
- Improved consistency in clinical trial endpoints
- Faster assessments at scale
- Deeper insight into real-world care patterns
- Better patient matching and trial enrollment strategies
These capabilities are especially critical as new IBD therapies enter development and the demand grows for more evidence-based, patient-centric trial designs.
“The goal of our partnership with Iterative Health is to facilitate more evidence-based decision-making on therapy utilization in the real world, and ultimately get a step closer to precision medicine in IBD.” — *Dr. Vijay Yajnik, Vice President, US Medical Affairs, Gastroenterology, Takeda
Explore the Full ACG 2024 Infographic
We’ve compiled the full data, insights, and research abstracts into one downloadable resource.
Download the ACG 2024 Research Infographic
About Iterative Health
Iterative Health is a healthcare technology and services company accelerating the development of GI therapies through AI-powered tools and the largest community-based GI research site network across the US and Europe. Our **Data & Insights** platform leverages machine learning and multimodal data to deliver novel, actionable insights across the clinical development lifecycle.
Whether you’re a sponsor designing a trial or a site navigating complex protocols, we’re here to help make research faster, smarter, and more precise.
About Iterative Health
Iterative Health is a healthcare technology and services company powering the acceleration of clinical research to transform patient outcomes. By combining deep expertise in clinical trials with cutting-edge AI, we empower research teams and study sponsors to expand and expedite access to novel therapeutics for patients in need. Today, Iterative Health is based in Cambridge, Massachusetts, and New York City with 250+ employees world-wide.
To learn more or explore a partnership, please visit our Contact page.