EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Algorithmic Fairness in Machine Learning Prediction of Autism Using Electronic Health Records

Amber M Angell, Yongqiu Li, Jiang Bian, Camille Parchment, Larry Yin, Srikar Chamala, Hesamedin Hakimjavadi, Lindsay Thompson, Yi Guo

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti251025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Amber M Angell und 8 weiteren Autor:innen. Beteiligte Einrichtung: University of Southern California, Los Angeles, CA, USA. Hauptthemen laut MEDLINE: Electronic Health Records, Machine Learning, Autism Spectrum Disorder, Algorithms. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efforts to improve early diagnosis of autism spectrum disorder (ASD) in children are beginning to use machine learning (ML) approaches applied to real-world clinical datasets, such as electronic health records (EHRs). However, sex-based disparities in ASD diagnosis highlight the need for fair prediction models that ensure equitable performance across demographic groups for ASD identification. This retrospective case-control study aimed to develop ML-based prediction models for ASD diagnosis using risk factors found in EHRs and assess their algorithmic fairness. The study cohorts included 70,803 children diagnosed with ASD and 212,409 matched controls without ASD. We built logistic regression and Xgboost models and evaluated their performance using standard metrics, including accuracy, recall, precision, F1-score, and area under the curve (AUC). To assess fairness, we examined model performance by sex and calculated fairness-specific metrics, such as equal opportunity (recall parity) and equalized odds, to identify potential biases in model predictions between boys and girls. Our results revealed significant fairness issues in ML models for ASD prediction using EHRs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electronic Health RecordsMachine LearningAutism Spectrum DisorderAlgorithmsHumansMaleFemaleRetrospective StudiesCase-Control StudiesChildChild, Preschool

Stichwörter der Autor:innen

Autismelectronic health recordspredictive modeling

Autor:innen und Institutionen

  • University of Southern California, Los Angeles, CA, USA.
  • University of Florida, Gainesville, FL, USA.
  • Children's Hospital Los Angeles, Los Angeles, CA, USA.
  • Wake Forest University, Winston-Salem, NC, USA.

Zitieren

APA

Angell, A. M., Li, Y., Bian, J., Parchment, C., Yin, L., Chamala, S., Hakimjavadi, H., Thompson, L., & Guo, Y. (2025). Algorithmic Fairness in Machine Learning Prediction of Autism Using Electronic Health Records. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251025

Vancouver

Angell AM, Li Y, Bian J, Parchment C, Yin L, Chamala S, et al. Algorithmic Fairness in Machine Learning Prediction of Autism Using Electronic Health Records. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251025

BibTeX
@article{Angell2025,
  author = {Angell, Amber M and Li, Yongqiu and Bian, Jiang and Parchment, Camille and Yin, Larry and Chamala, Srikar and Hakimjavadi, Hesamedin and Thompson, Lindsay and Guo, Yi},
  title = {Algorithmic Fairness in Machine Learning Prediction of Autism Using Electronic Health Records},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti251025}
}
Kostenlos starten →