Introduction
The American Journal of Machine Learning in Healthcare (AJMLH) is a peer-reviewed, open-access journal publishing research at the intersection of artificial intelligence, data science, and clinical/health systems. We welcome rigorously validated models, translational studies, deployment case reports, and methodological advances that improve patient outcomes, safety, equity, and efficiency.
Scope includes supervised/unsupervised/deep learning, multimodal data fusion (EHR, imaging, signals, genomics), foundation models and LLMs for clinical use, decision support and triage, predictive and prognostic modeling, causal inference, privacy-preserving ML, federated learning, model governance and auditing, bias/fairness and generalizability, and real-world evaluation (prospective, silent trials, RCTs).
Submissions undergo double-blind peer review. Authors are encouraged to share code, data (where legal/ethical), model cards, and reporting checklists (e.g., CONSORT-AI, SPIRIT-AI, TRIPOD-AI).
Recently Published Articles
Multimodal Sepsis Prediction with EHR + Waveform Fusion: A Prospective Silent Trial
Volume 1, Issue 1
Fairness Auditing for Chest X-ray Models: Distribution Shift and Subgroup Performance
Volume 1, Issue 1
Federated Learning for Diabetic Retinopathy Screening Across 12 Clinics
Volume 1, Issue 1