sEHR-CE: Language modelling of structured EHR data for efficient and generalizable patient cohort expansion
This addresses the challenge of efficiently and generalizably expanding patient cohorts for clinical research by improving phenotyping accuracy without relying on curated maps.
The paper tackled the problem of inaccurate and incomplete clinical term mappings in electronic health records by proposing sEHR-CE, a transformer-based framework that uses textual descriptors to unify terminologies and fine-tunes language models, resulting in more accurate disease phenotype predictions than non-text and single terminology approaches.
Electronic health records (EHR) offer unprecedented opportunities for in-depth clinical phenotyping and prediction of clinical outcomes. Combining multiple data sources is crucial to generate a complete picture of disease prevalence, incidence and trajectories. The standard approach to combining clinical data involves collating clinical terms across different terminology systems using curated maps, which are often inaccurate and/or incomplete. Here, we propose sEHR-CE, a novel framework based on transformers to enable integrated phenotyping and analyses of heterogeneous clinical datasets without relying on these mappings. We unify clinical terminologies using textual descriptors of concepts, and represent individuals' EHR as sections of text. We then fine-tune pre-trained language models to predict disease phenotypes more accurately than non-text and single terminology approaches. We validate our approach using primary and secondary care data from the UK Biobank, a large-scale research study. Finally, we illustrate in a type 2 diabetes use case how sEHR-CE identifies individuals without diagnosis that share clinical characteristics with patients.