Model performance
Exact saved notebook outputs · Cell 29 · Higher is better
MACHINE LEARNING · HEALTHCARE · EXPLAINABLE AI
Understanding why matters.
Explore stroke prediction models and the features behind their decisions.
Built by Richard Huang / UCL · COMP0172
Random Forest · max depth 5
High sensitivity, with a substantial false-positive tradeoff.
01 / BENCHMARK
One held-out test set. Five configurations. See the tradeoffs beyond accuracy.
Exact saved notebook outputs · Cell 29 · Higher is better
| Model | AUC | Recall | Precision | F1 | Accuracy |
|---|
02 / UNDER THE HOOD
Original SHAP visualizations, extracted directly from the project notebook.
03 / RESEARCH CONTEXT
A transparent view of the original experiment, including its limitations.
Drop ID and the single “Other” gender row; 5,109 records remain. Split 80/20 with random state 42. Fit mean BMI imputation on training data.
Classifier pipelines use one-hot encoding, numerical scaling and RandomOverSampler. The notebook also contains a separate SMOTE experiment.
Inspect original SHAP feature importance, beeswarm and age dependence plots. Saved outputs are presented as historical experiment results.
This demo presents saved research results; it does not run live patient predictions. The notebook contains execution-state inconsistencies and no exported fitted model. Reproducible retraining, calibration, subgroup evaluation and external validation would be needed before considering clinical use. Not a medical device or diagnostic tool.
LET’S BUILD SOMETHING EXPLAINABLE
Explore my work in machine learning, healthcare AI and data science.
Visit Richard’s portfolio ↗