A five-course series completed through Stanford University School of Medicine, focused on how AI is deployed responsibly across real-world care workflows. This includes payment model interpretation, EHR data modeling, bias mitigation, and machine learning implementation for diagnostics, prediction, & clinical simulation.
- Inference Trace: GenAI’s 2nd Opinion | Full Capstone Repository
- Deployed ClinicalBERT QA pipeline via FastAPI w/ OAuth2, TLS, FHIR-formatted logs & SHAP; CI/CD via GitHub Actions
- Introduction to Healthcare AI
- Care delivery models, ML case framing, clinical adoption barriers
- Medical Data for Machine Learning
- EHR structures, bias, missingness, cohort construction
- Machine Learning Deployment in Healthcare
- Model selection, performance evaluation, deployment tradeoffs
- Clinical Risk Prediction & Diagnostics
- Stratification, interpretability, workflows, and validation
- AI in the Real World: Simulation & Ethics
- Care journeys, regulation, fairness, and prospective trials
- Risk Stratification & Diagnostic Modeling
- Bias-Aware ML on EHR Data
- Clinical Deployment (FastAPI, OAuth2, CI/CD)
- HIPAA-Compliant Architecture Design
- Regulatory & Ethical Framing for AI Tools