Problem
Research questions and friction points this paper is trying to address.
epilepsy
psychogenic non-epileptic seizures
misdiagnosis
diagnostic delay
electronic health records
EpiScreen: Early Epilepsy Detection from Electronic Health Records with Large Language Models
🤖 AI Summary
This study addresses the clinical challenge of distinguishing between epileptic seizures and psychogenic nonepileptic seizures, which often present similarly and lead to misdiagnosis and delayed treatment. It proposes the first application of a large language model (LLM) to this differential diagnosis task by fine-tuning the model to analyze clinical narratives in electronic health records, thereby developing a low-cost, scalable tool for early screening. Evaluated on both the MIMIC-IV database and a private cohort from the University of Minnesota, the approach achieved AUCs of 0.875 and 0.980, respectively. Furthermore, it significantly improved neurologists’ diagnostic accuracy by up to 10.9%, offering an effective decision-support solution particularly valuable in resource-limited settings.
📝 Abstract
Epilepsy and psychogenic non-epileptic seizures often present with similar seizure-like manifestations but require fundamentally different management strategies. Misdiagnosis is common and can lead to prolonged diagnostic delays, unnecessary treatments, and substantial patient morbidity. Although prolonged video-electroencephalography is the diagnostic gold standard, its high cost and limited accessibility hinder timely diagnosis. Here, we developed a low-cost, effective approach, EpiScreen, for early epilepsy detection by utilizing routinely collected clinical notes from electronic health records. Through fine-tuning large language models on labeled notes, EpiScreen achieved an AUC of up to 0.875 on the MIMIC-IV dataset and 0.980 on a private cohort of the University of Minnesota. In a clinician-AI collaboration setting, EpiScreen-assisted neurologists outperformed unaided experts by up to 10.9%. Overall, this study demonstrates that EpiScreen supports early epilepsy detection, facilitating timely and cost-effective screening that may reduce diagnostic delays and avoid unnecessary interventions, particularly in resource-limited regions.
Innovation
Methods, ideas, or system contributions that make the work stand out.
large language models
epilepsy detection
electronic health records
early diagnosis
clinician-AI collaboration
🔎 Similar Papers
No similar papers found.
