Predictive Model for Outcomes in Inflammatory Bowel Disease Patients Receiving Maintenance Infliximab Therapy
Bibliographic record
Abstract
Abstract Background No models predict future outcomes in inflammatory bowel disease (IBD) patients receiving maintenance infliximab therapy. We created a predictive model for unfavorable outcomes. Methods Adult patients with IBD receiving maintenance infliximab therapy at 2 centers with matched serum infliximab concentrations and blinded histologic scores (Robarts Histopathologic Index [RHI]) were included. The primary endpoint was an unfavorable outcome of active objective inflammation or need for IBD-related surgery or hospitalization at 6–18 months follow-up. Internal variables were identified using univariable analyses, modeling used multivariable analysis, and performance was assessed (area under receiver-operating curve [AUC]) and externally validated. Results In 81 patients, 40.7% developed unfavorable outcomes at follow-up. Infliximab concentration <9.3 µg/mL (odds ratio [OR] 5.3, P = .001) and RHI > 12 (OR 3.4, P = .03) were the only factors associated with developing the primary unfavorable outcome. A prediction score assigning 1 point to each variable had good discrimination and performed similarly on internal (AUC 0.71) and external (AUC 0.73) cohorts. The risk of primary unfavorable outcomes in internal and external cohorts, respectively, was 23% and 15% for a score of 0, 46% and 50% for a score of 1, and 100% and 75% for a score of 2. Infliximab concentration alone performed similar to the 2-predictor model in internal (AUC 0.65, P = .5 vs. 2-predictor model) and external (AUC 0.70, P = .9, vs. 2-predictor model) cohorts. Conclusions Using unbiased variable selection, a 2-predictor model using infliximab concentrations and histology identified IBD patients on maintenance infliximab therapy at high risk of future unfavorable outcomes. For practical applicability, infliximab concentrations alone performed similarly well.
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 | 0.003 | 0.009 |
| 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 | 0.001 | 0.000 |
| Open science | 0.001 | 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".