I'm a medical doctor and data scientist passionate about using AI to transform healthcare. I currently serve as Medical Manager of Innovation and AI at Hapvida NotreDame IntermΓ©dica and am a PhD student in Machine Learning for Public Health at FSP-USP, researching multicalibration and fairness in predictive models to ensure AI is equitable across all populations. π±
- π₯ Medical AI Manager Β· Hapvida NotreDame IntermΓ©dica
- π PhD Student Β· Machine Learning in Public Health Β· FSP-USP (LABDAPS)
- π¬ Research in fairness, multicalibration and dataset shift in health
- π SΓ£o Paulo, Brazil Β· Vegan π±
- βοΈ drfabianofilho@gmail.com
Languages & Frameworks
Machine Learning & AI
Data & Infrastructure
Health & Interoperability
| Project | Description | Stack |
|---|---|---|
| aiscribr | AI-powered clinical documentation assistant β records, transcribes and generates SOAP notes, 100% local and private | Python Β· Whisper Β· Ollama Β· Electron |
| amie-agents | Conversational medical AI assistants inspired by Google DeepMind's AMIE, with multi-agent architecture | MedGemma Β· FastAPI Β· LangChain Β· Ollama |
| datasus-ai-prediction | Predictive ML models trained on DATASUS data for clinical and epidemiological outcome forecasting | Python Β· scikit-learn Β· XGBoost Β· DATASUS |
| datasus-ai-search | Natural language queries over Brazilian epidemiological data (DATASUS) β no SQL needed | Python Β· LLMs Β· DuckDB Β· Streamlit |
| ml-para-medicos | Interactive ML course for healthcare professionals with AI tutor, quizzes and clinical analogies | HTML/JS Β· Claude API Β· AI Tutor Β· Medical Education |
- π A bibliometric network analysis of coronavirus during the first eight months of COVID-19 Β· IJERPH, 2021 Β· 106 citations
- π Strategies for detecting and mitigating dataset shift in ML for health predictions Β· Journal of Biomedical Informatics, 2025
- π Predictive modeling of gestational weight gain: a ML multiclass classification study Β· BMC Pregnancy and Childbirth, 2024
- π Multicenter comparative analysis of local and aggregated data in COVID-19 outcome prediction Β· PLOS Digital Health, 2024
- π° Substack β Medicine and Artificial Intelligence Β· Newsletter on fairness, LLMs and generative AI in medicine
- βοΈ Medium β dadosesaude Β· Educational articles on health data science
- π ML para Medicos β Interactive Course Β· 10-module ML course for physicians with AI tutor and clinical analogies
- π portfolio.fabianofilho.com Β· Full portfolio with career, projects and publications
"Evidence-based medicine, combined with data science, has the power to transform patient care in a personalized and equitable way."