Heart disease risk: an explainable classifier

A logistic-regression model trained on 734 patients from the Kaggle Heart Failure Prediction dataset. It runs entirely in your browser: nothing you enter leaves this page.

Educational demo, not medical advice. This model has only been tested on 184 rows of one public dataset. It is not a diagnostic tool and must not be used to make decisions about anyone's health.

Patient measurements

Predicted probability of heart disease

–

What drives this prediction

← lowers riskraises risk →

    Each bar is that input's contribution to the model's log-odds, measured against an average patient in the training data.

    Code, notebook, and model card: github.com/Nardy11/Heart_Failure_prediction