Using a natural language processing toolkit to classify electronic health records by psychiatric diagnosis.

Autor:	Hutto A; Department of Psychiatry, University of North Carolina School of Medicine, Chapel Hill, NC, USA., Zikry TM; Department of Biostatistics, University of North Carolina Gillings School of Global Public Health, Chapel Hill, NC, USA., Bohac B; North Carolina Translational and Clinical Sciences Institute, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA., Rose T; Department of Psychiatry, University of North Carolina School of Medicine, Chapel Hill, NC, USA.; Department of Health Sciences, University of North Carolina School of Medicine, Chapel Hill, NC, USA., Staebler J; Department of Health Sciences, University of North Carolina School of Medicine, Chapel Hill, NC, USA., Slay J; Department of Health Sciences, University of North Carolina School of Medicine, Chapel Hill, NC, USA., Cheever CR; University of North Carolina School of Medicine, Chapel Hill, NC, USA., Kosorok MR; Department of Biostatistics, University of North Carolina Gillings School of Global Public Health, Chapel Hill, NC, USA.; Department of Statistics and Operations Research, University of North Carolina, Chapel Hill, NC, USA., Nash RP; Department of Psychiatry, University of North Carolina School of Medicine, Chapel Hill, NC, USA.
Jazyk:	angličtina
Zdroj:	Health informatics journal [Health Informatics J] 2024 Oct-Dec; Vol. 30 (4), pp. 14604582241296411.
DOI:	10.1177/14604582241296411
Abstrakt:	Objective: We analyzed a natural language processing (NLP) toolkit's ability to classify unstructured EHR data by psychiatric diagnosis. Expertise can be a barrier to using NLP. We employed an NLP toolkit (CLARK) created to support studies led by investigators with a range of informatics knowledge. Methods: The EHR of 652 patients were manually reviewed to establish Depression and Substance Use Disorder (SUD) labeled datasets, which were split into training and evaluation datasets. We used CLARK to train depression and SUD classification models using training datasets; model performance was analyzed against evaluation datasets. Results: The depression model accurately classified 69% of records (sensitivity = 0.68, specificity = 0.70, F1 = 0.68). The SUD model accurately classified 84% of records (sensitivity = 0.56, specificity = 0.92, F1 = 0.57). Conclusion: The depression model performed a more balanced job, while the SUD model's high specificity was paired with a low sensitivity. NLP applications may be especially helpful when combined with a confidence threshold for manual review. Competing Interests: Declaration of conflicting interestsThe author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu