Postoperative infection prediction
Explainable machine learning and strategic data imputation for predicting surgical-site infections from real-world clinical data.
Postoperative infections, including surgical-site infections (SSIs), remain a major source of morbidity and healthcare cost. This line of work develops explainable machine-learning models that predict postoperative infections from routinely-collected clinical records, with principled handling of missing data so the predictions are actionable in real hospital workflows.
Selected publications
- Guillen-Ramirez, H. et al. Prediction of postoperative infections by strategic data imputation and explainable machine learning. Journal of the American Medical Informatics Association 32(11), 1706–1717 (2025). doi:10.1093/jamia/ocaf145
- Blatter, T. U. et al. End-of-surgery prediction of postoperative infectious complications from intraoperative vital-sign dynamics. npj Digital Medicine (2026). doi:10.1038/s41746-026-02707-1