Can antiepileptic drug efficacy be studied from electronic health records? A review of current approaches

SUMMARY As automated data extraction and natural language processing (NLP) are rapidly evolving, applicability to harness large data to improve healthcare delivery is garnering great interest. Assessing antiepileptic drug (AED) efficacy remains a barrier to improving epilepsy care. In this review, we examined automatic electronic health record (EHR) extraction methodologies pertinent to epilepsy examining AED efficacy. We also reviewed more generalizable NLP pipelines to extract other critical patient variables. Our review found varying reports of performance measures. Whereas automated data extraction pipelines are a crucial advancement, this review calls attention to standardizing NLP methodology and accuracy reporting for greater generalizability. Moreover, the use of crowdsourcing competitions to spur innovative NLP pipelines would further advance this field. HIGHLIGHTS Automated data extraction is rapidly evolving and can be harnessed to efficiently mine the electronic health record. Natural language processing (NLP) of unstructured text improves data extraction accuracy when added to ICD coding and structured fields. We review these techniques specific to epilepsy and highlight strengths as well as areas of further improvement.