Applied ML Scientist, Clinical Risk Modelling
Core
Develop statistical and machine learning models on de-identified electronic health record (EHR) data to predict GLP-1 treatment outcomes, specifically discontinuation and post-discontinuation weight regain.
Role type
Applied ML Scientist (Clinical Risk Modelling)
Builds
Retrospective patient cohorts, time-windowed features, and prognostic models for obesity-medicine outcomes.
Domain
Healthcare / Clinical Data Science / Obesity Medicine
Deliverable
production ML models
Required skills
Tabular ML (gradient boosting, regularized regression), Clinical prediction statistics (discrimination, calibration, validation), EHR feature engineering, Python (Pandas, NumPy, scikit-learn), Health data privacy (HIPAA, GDPR)
Preferred skills
Survival or time-to-event modelling, EHR or claims data experience (ICD, RxNorm), Production deployment experience
Technologies
Python, Pandas, NumPy, scikit-learn
Responsibilities
Build retrospective patient cohorts from longitudinal EHR data; Engineer time-windowed features to avoid temporal leakage; Develop and validate models for GLP-1 discontinuation and weight regain; Translate model outputs into interpretable risk tiers; Document datasets and validation results for reproducibility; Collaborate with software engineers for production integration.
