Harnessing electronic medical records to advance research on multiple sclerosis

Abstract

Background: Electronic medical records (EMR) data are increasingly used in research, but no studies have yet evaluated similarity between EMR and research-quality data and between characteristics of an EMR multiple sclerosis (MS) population and known natural MS history.

Objectives: To (1) identify MS patients in an EMR system and extract clinical data, (2) compare EMR-extracted data with gold-standard research data, and (3) compare EMR MS population characteristics to expected MS natural history.

Methods: Algorithms were implemented to identify MS patients from the University of California San Francisco EMR, de-identify the data and extract clinical variables. EMR-extracted data were compared to research cohort data in a subset of patients.

Results: We identified 4142 MS patients via search of the EMR and extracted their clinical data with good accuracy. EMR and research values showed good concordance for Expanded Disability Status Scale (EDSS), timed-25-foot walk, and subtype. We replicated several expected MS epidemiological features from MS natural history including higher EDSS for progressive versus relapsing-remitting patients and for male versus female patients and increased EDSS with age at examination and disease duration.

Conclusion: Large real-world cohorts algorithmically extracted from the EMR can expand opportunities for MS clinical research.

Keywords: Electronic medical records; natural language processing.