DOSSIER: Fact Checking in Electronic Health Records While Preserving Patient Privacy

Abstract

Given a particular claim about a specific document, the fact checking problem is to determine if the claim is true and, if so, provide corroborating evidence. The problem is motivated by contexts where a document is too lengthy to quickly read and find an answer. This paper focuses on electronic health records, or a medical dossier, where a physician has a pointed claim to make about the record. Prior methods that rely on directly prompting an LLM may suffer from hallucinations and violate privacy constraints. We present a system, DOSSIER, that verifies claims related to the tabular data within a document. For a clinical record, the tables include timestamped vital signs, medications, and labs. DOSSIER weaves together methods for tagging medical entities within a claim, converting natural language to SQL, and utilizing biomedical knowledge graphs, in order to identify rows across multiple tables that prove the answer. A distinguishing and desirable characteristic of DOSSIER is that no private medical records are shared with an LLM. An extensive experimental evaluation is conducted over a large corpus of medical records demonstrating improved accuracy over five baselines. Our methods provide hope that physicians can privately, quickly, and accurately fact check a claim in an evidence-based fashion.