Operation-Mechanism Alignment for Reliable Clinical Reasoning over Electronic Health Records
Year: 2026
Type: conference-paper
Abstract: Clinical reasoning over electronic health records (EHRs) involves heterogeneous operations, including text interpretation, numerical computation, temporal filtering, and guidelinebased aggregation.However, many existing LLM-based approaches still cast these heterogeneous operations as a single end-to-end generation process, obscuring their different reliability requirements and making intermediate failures difficult to inspect.We therefore propose a framework based on operationmechanism alignment that represents clinical reasoning as a directed acyclic graph of typed operations, where each node is assigned to the execution mechanism best suited to its reliability requirements.The framework also preserves structured evidence provenance for intermediate results.Across six clinician-annotated binary decision tasks, the framework outperforms direct prompting, single-step retrievalaugmented prompting, and chain-of-thought baselines, supporting operation-mechanism alignment as a practical design principle for reliable clinical reasoning over EHRs.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W7166824009