What Iterative Health Published About Continuous Endoscopic Severity Scoring in Ulcerative Colitis
Iterative Health published a piece on 28 October 2026 setting out an AI based approach to measuring how severe ulcerative colitis is at endoscopy, arguing for a continuous score across the colon rather than the conventional practice of grading the single worst lesion. The company frames the current approach as throwing away information that the endoscopy video already contains. This is the company making an argument about how trials should be measured, published on its own site, rather than a regulatory decision, a trial result or a product announcement.
Why the Iterative Health Ulcerative Colitis Scoring Argument Matters to Trial Sponsors
Whoever defines the measurement has a quiet kind of power in drug development. A scoring method decides which drugs look like they worked, and a method that notices smaller changes can make a real but modest treatment effect visible where the old score saw nothing. That is genuinely useful if the method is right, and it is also commercially convenient for the company selling the method. Both things are true at once. What this piece is not: it is not a regulator accepting the score, and it is not evidence that the continuous measure predicts how a patient actually feels or does. Regulators have accepted the worst lesion approach for years, and replacing an accepted endpoint is slow, contested work. Read it as a well argued position from an interested party and look for who else adopts it.
Where the Iterative Health Update Comes From
Iterative Health is the original record behind this update. It tells us what the company published. This brief adds the market context and the method we would use to test the development against other evidence.
Iterative Health original source.
How We Would Research the Iterative Health Ulcerative Colitis Scoring Approach
The source gives us the starting point. This is how we would build the next layer of research around it.
- We would start by asking whether any regulator has accepted a continuous endoscopic score as a trial endpoint, because acceptance is the whole question.
- Then we would look for whether the continuous score tracks how patients say they feel, since a more sensitive number is only better if it means something to a person.
- We would ask a sponsor that has used both methods on the same trial data what changed in the result, because that comparison settles it faster than an argument does.