The AI-based Red Density score is correlated with the established and new histological indices for ulcerative colitis in an independent cohort
Bibliographic record
Abstract
Aims Red Density (RD) is an automated endoscopic tool that is developed for the objective evaluation of disease activity in ulcerative colitis (UC). Initial development was based on an algorithm including histological disease activity based on Robarts histological index (RHI). New histological scores for UC have been developed since. We aimed to establish the correlation between RD and the Nancy histological index (NHI) and PICaSSO Histologic Remission Index (PHRI). Methods Patients included in 4 centers in the ongoing PROCEED-UC study (NCT04408703) had assessment with RD in the rectum and sigmoid at baseline, week 52 or early termination visit. RD score ranges between 0 and 255, cut-off for remission was previously determined to be<60.[1] Biopsies were taken according to protocol and scored for the Geboes score (GBS), RHI, NHI, PHRI in a blinded way after initial scoring convention training. Correlation was tested on patient level between mean RD per segment and the different histological indices based on Spearman correlation. Results Ninety-six patients from 4 centers were included representing 2634 RD images from 400 colonic segments with biopsies and corresponding RD score. Mean (±SEM) rectal RD score was 32.7 (±4.54), 33.69 (±5.25) and 64.86 (±31.71) at baseline, w52 and ET, respectively. Mean sigmoidal RD score was 38.13 (±3.68), 42.82 (±11.80) and 77.33 (±24.65) at baseline, week 52 and ET, respectively. There was a significant correlation between the highest mean RD score per patient and the NHI (r=0.60, p<0.0001) and the PHRI (r=0.62, p<0.0001). In the rectum the RD score at all time points correlated significant with NHI (r=0,53, p<0.0001) and PHRI (r=0.63, p<0.0001). Similar correlation was seen in the sigmoid for NHI (r=0.51, p<0.0001) and PHRI (r=0.22, p0.0108). A RD score of<57.5 (AUC 0.7820 (95CI 0.7047 – 0.8593), p<0.0001) was associated with histological remission based on NHI (<2) and a RD score of<64.5 (AUC 0.8133 (95% CI 0.7053 – 0.9212), p<0.0001) with histological remission based on PHRI (=0). The current dataset demonstrated to be stable in line with the previously established RD cut-off with GBS and RHI. [ 1 ] Conclusions In an independent cohort of patients with UC the correlation with the established and new histological indices is confirmed. This confirms the value of RD as objective endoscopic tool for the assessment of histological and endoscopic disease activity. Publication History Article published online: 15 April 2024 © 2024. European Society of Gastrointestinal Endoscopy. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".