Machine learning prediction and explanatory models of serious infections in patients with rheumatoid arthritis treated with tofacitinib
Authors' conclusion
Baseline factors associated with SIs in the tofacitinib RA clinical trial program were similar to established SI risk factors associated with advanced treatments for RA. Furthermore, while model performance in predicting SI was similar to other published models, this did not meet the threshold for accurate prediction (AUROC > 0.85).
Study context
- Population
- Patients with rheumatoid arthritis (RA) receiving tofacitinib 5 or 10 mg BID in the tofacitinib RA clinical trials program473 with serious infections (SIs)
- Participants
- 8,404 patients
- Primary endpoint
- Prediction of SI from baseline variables (AUROC)
Methodological detailspooled post hoc analysis of tofacitinib RA clinical trials, 19 clinical trials (phase 2, n = 10; phase 3, n = 6; phase 3b/4, n = 3), logistic regression, support vector machines, random forest, extreme gradient boosting trees, boosted trees, 5-fold cross-validation, 15,310 patient-years of total follow-up
- Pooled post hoc analysis of tofacitinib RA clinical trials
- 19 clinical trials (phase 2, n = 10; phase 3, n = 6; phase 3b/4, n = 3)
- Logistic regression, support vector machines, random forest, extreme gradient boosting trees, boosted trees
- 5-fold cross-validation
- 15,310 patient-years of total follow-up
Primary result
As reported in the abstract
Prediction of SI, all studies
Area under the receiver operating characteristic (AUROC) range across models
0.656 to 0.739
Further findings
Prediction of SI, phase 3 and 3b/4 studies
- AUROC range across models
- 0.599 to 0.730
Prediction of SI, ORAL Surveillance only
- AUROC range across models
- 0.563 to 0.643
Baseline factors associated with SI (logistic regression)
- Age, previous infection and GC use significantly associated with SI
Original publication
Machine learning prediction and explanatory models of serious infections in patients with rheumatoid arthritis treated with tofacitinib. Arthritis Res Ther. Published 27 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →