Structured Clinical Reasoning with Foundation Models

Foundation models have demonstrated strong capabilities across a wide range of clinical tasks, yet their application to longitudinal electronic health records (EHRs) remains limited by the difficulty of evaluating clinically grounded reasoning, maintaining consistent patient-state representations over time, and predicting future clinical events within large, weakly structured outcome spaces. My research addresses these challenges by introducing structured methods for clinical AI across evaluation, inference, and prediction. I develop an ontology-grounded evaluation framework that jointly assesses factual correctness and patient-contextual grounding, enabling systematic identification of clinically meaningful reasoning errors beyond conventional accuracy metrics. I further investigate protocol-constrained longitudinal reasoning through persistent patient-state representations that evolve with incoming clinical evidence, improving temporal consistency, calibration, and interpretability over extended patient trajectories. Finally, I reformulate longitudinal prediction as reasoning within structured hypothesis spaces by combining medical coding hierarchies with data-driven temporal and cross-modal associations to construct patient-specific candidate outcomes before inference. Together, these studies demonstrate how explicit clinical structure can be incorporated throughout the clinical AI pipeline, integrating biomedical knowledge, longitudinal patient states, and structured hypothesis spaces to improve the reliability, interpretability, and clinical grounding of foundation models for longitudinal decision support.

Bio

I am a PhD student at TU Dresden and the Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), and I am currently completing my doctoral studies. My research interests lie in explainable AI, machine learning, NLP, and graph representation learning. My recent research focuses on developing structured and interpretable AI methods for complex temporal and high-stakes domains, including counterfactual explainability for dynamic graphs, explainable machine learning for aviation safety, and foundation models for reasoning over structured and longitudinal clinical data. I have published at leading AI conferences, including ICML, KDD, AAAI, and ACL.