Extracting seizure control metrics from clinic notes of patients with epilepsy: A natural language processing approach.

Autor: Fernandes M; Department of Neurology, Massachusetts General Hospital (MGH), Boston, MA, United States; Harvard Medical School, Boston, MA, United States. Electronic address: mbentofernandes@mgh.harvard.edu., Cardall A; Department of Neurology, Massachusetts General Hospital (MGH), Boston, MA, United States; Harvard Medical School, Boston, MA, United States., Moura LM; Department of Neurology, Massachusetts General Hospital (MGH), Boston, MA, United States; Harvard Medical School, Boston, MA, United States., McGraw C; Department of Neurology, Massachusetts General Hospital (MGH), Boston, MA, United States; Harvard Medical School, Boston, MA, United States., Zafar SF; Department of Neurology, Massachusetts General Hospital (MGH), Boston, MA, United States; Harvard Medical School, Boston, MA, United States., Westover MB; Harvard Medical School, Boston, MA, United States; Beth Israel Deaconess Medical Center (BIDMC), Boston, MA, United States.
Jazyk: angličtina
Zdroj: Epilepsy research [Epilepsy Res] 2024 Nov; Vol. 207, pp. 107451. Date of Electronic Publication: 2024 Sep 10.
DOI: 10.1016/j.eplepsyres.2024.107451
Abstrakt: Objectives: Monitoring seizure control metrics is key to clinical care of patients with epilepsy. Manually abstracting these metrics from unstructured text in electronic health records (EHR) is laborious. We aimed to abstract the date of last seizure and seizure frequency from clinical notes of patients with epilepsy using natural language processing (NLP).
Methods: We extracted seizure control metrics from notes of patients seen in epilepsy clinics from two hospitals in Boston. Extraction was performed with the pretrained model RoBERTa_for_seizureFrequency_QA, for both date of last seizure and seizure frequency, combined with regular expressions. We designed the algorithm to categorize the timing of last seizure ("today", "1-6 days ago", "1-4 weeks ago", "more than 1-3 months ago", "more than 3-6 months ago", "more than 6-12 months ago", "more than 1-2 years ago", "more than 2 years ago") and seizure frequency ("innumerable", "multiple", "daily", "weekly", "monthly", "once per year", "less than once per year"). Our ground truth consisted of structured questionnaires filled out by physicians. Model performance was measured using the areas under the receiving operating characteristic curve (AUROC) and precision recall curve (AUPRC) for categorical labels, and median absolute error (MAE) for ordinal labels, with 95 % confidence intervals (CI) estimated via bootstrapping.
Results: Our cohort included 1773 adult patients with a total of 5658 visits with reported seizure control metrics, seen in epilepsy clinics between December 2018 and May 2022. The cohort average age was 42 years old, the majority were female (57 %), White (81 %) and non-Hispanic (85 %). The models achieved an MAE (95 % CI) for date of last seizure of 4 (4.00-4.86) weeks, and for seizure frequency of 0.02 (0.02-0.02) seizures per day.
Conclusions: Our NLP approach demonstrates that the extraction of seizure control metrics from EHR is feasible allowing for large-scale EHR research.
Competing Interests: Declaration of Competing Interest Dr. M. Brandon Westover has private equity as co-founder of Beacon Biosignals and receives compensation for consulting and scientific advisory roles. No competing interests.
(Copyright © 2024 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: