Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes.

Autor:	Leroy G; Department of Management Information Systems, The University of Arizona, Tucson, AZ 85621, United States., Andrews JG; Department of Pediatrics, The University of Arizona, Tucson, AZ 85621, United States., KeAlohi-Preece M; Department of Psychology, The University of Arizona, Tucson, AZ 85621, United States., Jaswani A; Department of Management Information Systems, The University of Arizona, Tucson, AZ 85621, United States., Song H; Department of Computer Science, The University of Arizona, Tucson, AZ 85621, United States., Galindo MK; Department of Pediatrics, The University of Arizona, Tucson, AZ 85621, United States., Rice SA; Department of Pediatrics, The University of Arizona, Tucson, AZ 85621, United States.
Jazyk:	angličtina
Zdroj:	Journal of the American Medical Informatics Association : JAMIA [J Am Med Inform Assoc] 2024 May 20; Vol. 31 (6), pp. 1313-1321.
DOI:	10.1093/jamia/ocae080
Abstrakt:	Objective: Machine learning (ML) is increasingly employed to diagnose medical conditions, with algorithms trained to assign a single label using a black-box approach. We created an ML approach using deep learning that generates outcomes that are transparent and in line with clinical, diagnostic rules. We demonstrate our approach for autism spectrum disorders (ASD), a neurodevelopmental condition with increasing prevalence. Methods: We use unstructured data from the Centers for Disease Control and Prevention (CDC) surveillance records labeled by a CDC-trained clinician with ASD A1-3 and B1-4 criterion labels per sentence and with ASD cases labels per record using Diagnostic and Statistical Manual of Mental Disorders (DSM5) rules. One rule-based and three deep ML algorithms and six ensembles were compared and evaluated using a test set with 6773 sentences (N = 35 cases) set aside in advance. Criterion and case labeling were evaluated for each ML algorithm and ensemble. Case labeling outcomes were compared also with seven traditional tests. Results: Performance for criterion labeling was highest for the hybrid BiLSTM ML model. The best case labeling was achieved by an ensemble of two BiLSTM ML models using a majority vote. It achieved 100% precision (or PPV), 83% recall (or sensitivity), 100% specificity, 91% accuracy, and 0.91 F-measure. A comparison with existing diagnostic tests shows that our best ensemble was more accurate overall. Conclusions: Transparent ML is achievable even with small datasets. By focusing on intermediate steps, deep ML can provide transparent decisions. By leveraging data redundancies, ML errors at the intermediate level have a low impact on final outcomes. (© The Author(s) 2024. Published by Oxford University Press on behalf of the American Medical Informatics Association.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu