Brett Beaulieu-Jones, PhD, is an Assistant Professor of Medicine in the Section of Biomedical Data Science at the University of Chicago. A computer scientist by training, he specializes in biomedical informatics and machine learning for healthcare, using electronic health records and other real-world clinical data to improve care delivery, clinical decision making, and health system operations.
Dr. Beaulieu-Jones’s research focuses on interpretable clinical AI, foundation models for electronic health records, and methods that ensure responsible, reproducible use of clinical data. He is a recipient of a National Institutes of Health Pathway to Independence Award from the National Institute of Neurological Disorders and Stroke and serves on the editorial board of Nature Communications Medicine. He earned his PhD from the Perelman School of Medicine at the University of Pennsylvania and completed postdoctoral training before serving as an instructor in biomedical informatics at Harvard Medical School. He is a founding board member of the Association for Health Learning and Inference and prior chair and vice-chair. He joined the University of Chicago in 2022.
Computational challenges arising in algorithmic fairness and health equity with generative AI.
Computational challenges arising in algorithmic fairness and health equity with generative AI. Nat Comput Sci. 2025 Sep; 5(9):698-700.
PMID: 40379962
Heterogeneous Effect of Automated Alerts on Mortality.
Heterogeneous Effect of Automated Alerts on Mortality. medRxiv. 2025 Aug 13.
PMID: 40832403
ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning.
ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning. ArXiv. 2025 Aug 12.
PMID: 40395940
ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning.
ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning. Proc Mach Learn Res. 2025 Aug; 298.
PMID: 41394314
Predicting Resection Weights of Reduction Mammaplasty: A Multi-Institutional Retrospective Analysis Using Machine Learning.
Predicting Resection Weights of Reduction Mammaplasty: A Multi-Institutional Retrospective Analysis Using Machine Learning. Plast Reconstr Surg. 2026 01 01; 157(1):9-17.
PMID: 40527313
Synthetic data distillation enables the extraction of clinical information at scale.
Synthetic data distillation enables the extraction of clinical information at scale. NPJ Digit Med. 2025 May 10; 8(1):267.
PMID: 40348936
The MI-CLAIM-GEN checklist for generative artificial intelligence in health.
The MI-CLAIM-GEN checklist for generative artificial intelligence in health. Nat Med. 2025 May; 31(5):1394-1398.
PMID: 39915678
Enriched phenotypes in rare variant carriers suggest pathogenic mechanisms in rare disease patients.
Enriched phenotypes in rare variant carriers suggest pathogenic mechanisms in rare disease patients. BioData Min. 2025 Jan 17; 18(1):6.
PMID: 39825393
Leveraging Foundational Models in Computational Biology: Validation, Understanding, and Innovation.
Leveraging Foundational Models in Computational Biology: Validation, Understanding, and Innovation. Pac Symp Biocomput. 2025; 30:702-705.
PMID: 39670407
Phenotypic overlap between rare disease patients and variant carriers in a large population cohort informs biological mechanisms.
Phenotypic overlap between rare disease patients and variant carriers in a large population cohort informs biological mechanisms. medRxiv. 2024 Apr 19.
PMID: 38699301