Home▸AI & Machine Learning▸Why Doctors Won't Trust a Black Box: SHAP and Explainable AI in Healthcare

🩺 Why Doctors Won't Trust a Black Box: SHAP and Explainable AI

An explanation of how SHAP values turn opaque model scores into feature-by-feature reasoning that clinicians and patients can actually interrogate, using a UK stroke-risk model as a worked example.

AI & Machine Learning3DAdvanced60 FPS

A UK stroke-risk model's prediction is decomposed into a 3D SHAP waterfall: a baseline population risk, followed by stacked bars showing exactly how much each clinical feature pushed the score up or down to reach the final prediction.

🔬 What It Demonstrates

SHAP values split a single opaque risk score into additive, per-feature contributions rooted in Shapley game theory. Red bars raise predicted risk above the population baseline; purple bars lower it — and they always sum exactly to the final prediction.

🎮 How to Use

Pick a preset patient or drag the age, blood pressure, glucose and BMI sliders yourself, toggle smoking status, and watch every bar resize and recolour live. Click any bar to read its exact contribution.

💡 Did You Know?

Because SHAP values are additive and consistent, a clinician can check whether a model's reasoning matches known medicine — e.g. that hypertension should raise risk — before ever trusting its number.

⚙ Under the hood

An explanation of how SHAP values turn opaque model scores into feature-by-feature reasoning that clinicians and patients can actually interrogate, using a UK stroke-risk model as a worked example.

Artificial IntelligenceMachine LearningExplainable AISHAP ValuesHealthcareMedical DiagnosisThree.js

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install