Risk Profiling with Explainability
Risk Profiling with Explainability
Risk profiling with explainability leverages AI to predict patient health risks while providing transparent, interpretable insights. By combining predictive analytics with explainable models, clinicians can make informed decisions, enhance trust, and improve outcomes. This approach ensures accountability, reduces biases, and supports data-driven healthcare interventions.
Publications
- Liu, Yu, et al. "SurvUnc: A Meta-Model Based Uncertainty Quantification Framework for Survival Analysis." Proceedings of the 31th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2025. paper, code
- Mesinovic, Munib, et al. "DynaGraph: Interpretable Multi-Label Prediction from EHRs via Dynamic Graph Learning and Contrastive Augmentation." arXiv preprint arXiv:2503.22257 (2025). paper
- Mesinovic, Munib, Peter Watkinson, and Tingting Zhu. "DySurv: dynamic deep learning model for survival analysis with conditional variational inference." Journal of the American Medical Informatics Association (2024): ocae271. paper
- Ghosheh, Ghadeer O., Jin Li, and Tingting Zhu. "IGNITE: Individualized GeNeration of Imputations in Time-series Electronic health records." arXiv preprint arXiv:2401.04402 (2024). paper
- Mesinovic, Munib, Peter Watkinson, and Tingting Zhu. "Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities." arXiv preprint arXiv:2308.08407 (2023). paper
- Mesinovic, Munib, Peter Watkinson, and Tingting Zhu. "XMI-ICU: Explainable Machine Learning Model for Pseudo-Dynamic Prediction of Mortality in the ICU for Heart Attack Patients." arXiv preprint arXiv:2305.06109 (2023). paper