Survival-Analysis Risk Model for an Oncology Decision-Support Pilot
Overview
What this challenge is about.
Build Cox, Random Survival Forest, and neural survival models on a cancer cohort and evaluate performance. Get a verifiable certificate.
The scenario
The startup (Series B, around 70 staff, pilots in 9 US comprehensive cancer centers) treats clinician-readable tumor-board briefs as the operational unit of value.
The Brief
What you'll do, and what you'll demonstrate.
Build and clinically frame a survival-analysis risk model for colorectal-cancer 1-year and 3-year mortality suitable for tumor-board discussion.
Earning criteria — what you'll demonstrate
- Apply survival analysis methods to a real censored clinical dataset
- Evaluate survival models with concordance + integrated Brier score
- Frame model output for multidisciplinary clinical discussion
- Report subgroup performance honestly in a clinical setting
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Machine Learning for Healthcare and Biomedicine
Master · Applied Ai
Strong alignment
This challenge maps to Machine Learning for Healthcare and Biomedicine at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Survival Analysis
Apply survival analysis to solve real industry problems and demonstrate production-level capability.
- Risk Stratification
Apply risk stratification to solve real industry problems and demonstrate production-level capability.
- Model Calibration
Apply model calibration to solve real industry problems and demonstrate production-level capability.
- Ehr Modeling
Apply ehr modeling to solve real industry problems and demonstrate production-level capability.
- Model Evaluation
Apply model evaluation to solve real industry problems and demonstrate production-level capability.
- Python
Write clean, efficient Python for data processing, automation, and backend services.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
ML Researcher
Rigorous survival-analysis comparisons on real censored clinical data are the ML-researcher's signature portfolio piece for any oncology-AI team.
This challenge sharpens
- survival-analysis
- model-calibration
- ehr-modeling
Applied AI Scientist
Producing tumor-board-ready briefs alongside the technical evaluation is the applied-AI-scientist's daily craft at oncology decision-support startups.
This challenge sharpens
- risk-stratification
- model-evaluation
- model-calibration
Data Scientist
Honest subgroup reporting on a clinical model is exactly what senior data scientists are graded on in healthtech interviews.
This challenge sharpens
- survival-analysis
- model-evaluation
- ehr-modeling