Almost Clinical: Linguistic properties of synthetic electronic health records

2026-01-03

arXiv.org

AI Summary

This study presents the first systematic linguistic evaluation of synthetic electronic health records (EHRs) generated by large language models (LLMs) in the domain of mental health, assessing their linguistic fidelity and clinical appropriateness. Focusing on four clinical genres—assessment, communication, referral, and care planning—the analysis employs qualitative and quantitative methods to examine how well synthetic texts replicate authentic clinical discourse across dimensions such as agency, modality, and information flow. Findings indicate that while generated texts closely approximate real EHRs in terminology and coherence, they exhibit systematic deviations in register consistency, clinical specificity, and diagnostic accuracy. These results reveal a persistent register shift in current LLM-generated medical texts, offering critical linguistic insights for the responsible clinical deployment of synthetic EHRs.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

This study evaluates the linguistic and clinical suitability of synthetic electronic health records in mental health. First, we describe the rationale and the methodology for creating the synthetic corpus. Second, we examine expressions of agency, modality, and information flow across four clinical genres (Assessments, Correspondence, Referrals and Care plans) with the aim to understand how LLMs grammatically construct medical authority and patient agency through linguistic choices. While LLMs produce coherent, terminology-appropriate texts that approximate clinical practice, systematic divergences remain, including registerial shifts, insufficient clinical specificity, and inaccuracies in medication use and diagnostic procedures. The results show both the potential and limitations of synthetic corpora for enabling large-scale linguistic research otherwise impossible with genuine patient records.

Problem

• synthetic electronic health records
• linguistic properties
• mental health
• clinical suitability
• patient agency

Innovation

• synthetic electronic health records
• large language models
• clinical linguistics
• patient agency
• medical discourse analysis