P631 Development and validation of a clinical scoring tool for predicting treatment outcomes with vedolizumab in patients with ulcerative colitis
Bibliographic record
Abstract
We created and validated a clinical decision support tool (CDST) for vedolizumab (VDZ) therapy in active ulcerative colitis (UC). To identify factors associated with corticosteroid-free remission (CSFREM; full Mayo score ≤2, no sub-score >1), logistic regression analyses were run on data from the GEMINI 1 VDZ trial for UC (derivation set; n = 620) and used to develop a CDST. Correlations between VDZ exposure, onset of action, and efficacy across predicted-probability groups were explored, and the CDST was externally validated in an observational cohort of VDZ-treated UC patients (validation set; n = 199). Factors independently associated with CSFREM were absence of previous tumour necrosis factor antagonist exposure (+3 points), disease duration ≥2 years (+3 points), baseline endoscopic activity (moderate vs. severe) (+2 points), and baseline albumin concentration (+0.65 points per g/l). Patients were stratified into low (≤26 points), intermediate (>26 to ≤32 points), or high (>32 points) probability of response groups. The higher probability group more rapidly achieved symptom activity reductions and attained higher rates of CSFREM (p < 0.001). In the validation set, a 26-point cut-off value showed high sensitivity (93%) for identifying non-responders. A statistically significant linear relationship was observed between VDZ exposure, probability groups, and efficacy in the derivation set (p < 0.001). In the validation set, only the low–intermediate probability group benefited from VDZ interval shortening for lack of response (p = 0.02). We developed and externally validated a CDST with good discriminative performance for predicting CSFREM with VDZ in UC patients. Pending further validation, this tool could be a helpful aid in identifying patients who would benefit from VDZ interval shortening due to insufficient response. (GEMINI 1: NCT00783718).
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 | 0.010 | 0.030 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".