Code, data and results for: Same prediction, different explanations — agreement, faithfulness, stability and error-signal value of post-hoc explanations for clinical prediction models

This archive contains the analysis code, input data, per-patient outputs and figures for a study of post-hoc explanations of clinical prediction models. Four public clinical datasets were used: breast cancer (WDBC), Cleveland heart disease, South African heart disease and Pima diabetes. On each, we trained logistic regression, an explainable boosting machine, random forest and XGBoost. Held-out predictions for 120 patients per dataset were explained with KernelSHAP, LIME and occlusion (5760 explanations). We evaluated the explanations' top-3 feature agreement, deletion-based faithfulness and stability under reruns and input perturbation. We also tested whether disagreement between explanations identifies misclassified predictions, compared with model confidence, using patient-level (cluster-bootstrap) inference. Running code/run_all.sh reproduces all results, tables and figures from the raw data; see README.md. The datasets come from the Penn Machine Learning Benchmarks repository (commit 7c1f4bd) and originate from the UCI Machine Learning Repository and the original studies cited in the README. This record accompanies a manuscript submitted to the Journal of the American Medical Informatics Association (JAMIA).