Beyond Prediction: Longitudinal Reasoning in EHR-Integrated Clinical AI
For clinical AI developers and healthcare practitioners, this work highlights a critical gap in current systems' ability to support longitudinal clinical reasoning, but it is primarily a conceptual analysis without empirical results.
The paper analyzes current clinical AI systems' integration of EHR data and finds they primarily use static, encounter-level representations with limited support for longitudinal reasoning, despite the need for temporal reasoning across patient histories.
We present a structured analysis of how contemporary clinical AI systems integrate electronic health record (EHR) data and the extent to which they support longitudinal clinical reasoning. Drawing on a curated corpus of clinical natural language processing (NLP) and EHR-integrated systems, we develop a coding framework that captures both technical integration strategies and reasoning-relevant representational features, such as trajectory modeling, cross-encounter synthesis, longitudinal analysis, and absence reasoning. We also elicited the experiences of three physicians in their EHR use, including what strengths and weaknesses they found with their institution's current EHR system(s). Our analysis shows that while many systems incorporate EHR data, they predominantly operate on encounter-level or aggregated representations, with limited support for explicit temporal reasoning across patient histories. Reasoning-relevant structures are inconsistently represented, and evaluation paradigms remain largely focused on predictive performance instead of longitudinal interpretability. We argue that current approaches treat EHR data as a static input rather than a substrate for ongoing clinical reasoning, and we outline a framework for understanding how future systems might more effectively align with the temporal and interpretive structure of clinical practice.