Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes
Journal of the American Medical Informatics Association · 20.05.2024 · 31 (6) · 1313-1321
DOI: 10.1093/jamia/ocae080 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 16.04.2024. Verfasst von Gondy Leroy und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Management Information Systems, The University of Arizona, Tucson, AZ 85621, United States. Hauptthemen laut MEDLINE: Deep Learning, Autism Spectrum Disorder, Electronic Health Records, Algorithms. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CDC HHS, CDC Cooperative, Centers for Disease Control.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Management Information Systems, The University of Arizona, Tucson, AZ 85621, United States.
- Department of Pediatrics, The University of Arizona, Tucson, AZ 85621, United States.
- Department of Psychology, The University of Arizona, Tucson, AZ 85621, United States.
- Department of Computer Science, The University of Arizona, Tucson, AZ 85621, United States.
ORCID-Profile: Gondy Leroy
Förderung
- CDC HHS
- CDC Cooperative
- Centers for Disease Control
- NIMH NIH HHS
- NCBDD CDC HHS
- Prevention Autism and Developmental Disabilities Monitoring
- National Institute of Mental Health
Zitieren
APA
Leroy, G., Andrews, J. G., KeAlohi-Preece, M., Jaswani, A., Song, H., Galindo, M. K., & Rice, S. A. (2024). Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes. Journal of the American Medical Informatics Association, 31(6), 1313-1321. https://doi.org/10.1093/jamia/ocae080
Vancouver
Leroy G, Andrews JG, KeAlohi-Preece M, Jaswani A, Song H, Galindo MK, et al. Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes. Journal of the American Medical Informatics Association. 2024;31(6):1313-1321. doi:10.1093/jamia/ocae080
BibTeX
@article{Leroy2024,
author = {Leroy, Gondy and Andrews, Jennifer G and KeAlohi-Preece, Madison and Jaswani, Ajay and Song, Hyunju and Galindo, Maureen Kelly and Rice, Sydney A},
title = {Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes},
journal = {Journal of the American Medical Informatics Association},
year = {2024},
volume = {31},
number = {6},
pages = {1313--1321},
doi = {10.1093/jamia/ocae080}
}
EUVIMED