AI for Healthcare & Clinical Decision Support
Developing interpretable AI systems that enhance clinical decision-making through predictive modeling, personalized medicine, and knowledge-driven healthcare analytics.
This research area focuses on creating AI systems that can assist healthcare providers in making better clinical decisions while maintaining interpretability and trust. The work spans from developing novel neural architectures for clinical event prediction to building knowledge graph-enhanced systems for personalized healthcare.
Key innovations include attention-based models that can explain their predictions, personalized knowledge graphs that capture patient-specific medical contexts, and fairness-aware machine learning models that ensure equitable healthcare outcomes across diverse populations.
The research addresses critical challenges in healthcare AI including model interpretability, clinical workflow integration, and bias mitigation, with demonstrated impact through deployments in real clinical settings.
GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs (ICLR 2024)
Improving Medical Machine Learning Models with Generative Balancing for Equity and Excellence (npj Digital Medicine, 2025)
RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism (NIPS 2016)
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks (ML4HC 2016)
Interested in This Research Area?
We welcome collaborations with researchers, clinicians, and industry partners working in ai for healthcare & clinical decision support. Our lab is always looking for motivated students and postdocs to join our team.