Explainability and Deployment
Cross-source consensus on Explainability and Deployment from 1 sources and 5 claims.
1 sources · 5 claims
Uses
How it works
Evidence quality
Other
Highlighted claims
- SHAP will be used for individual predictions and global feature importance. — Development and cross-site validation of machine-learning models for diagnosis and prognosis of stable angina with and without obstructive coronary artery disease: a study protocol
- Final models will be deployed as Shiny web-based clinical risk calculators with local SHAP waterfall explanations. — Development and cross-site validation of machine-learning models for diagnosis and prognosis of stable angina with and without obstructive coronary artery disease: a study protocol
- Subgroup performance and fairness will be audited across sex, age bins, and hospital type. — Development and cross-site validation of machine-learning models for diagnosis and prognosis of stable angina with and without obstructive coronary artery disease: a study protocol
- The calculator will use DP-CTGAN synthetic data to support SHAP values without exposing the original training data. — Development and cross-site validation of machine-learning models for diagnosis and prognosis of stable angina with and without obstructive coronary artery disease: a study protocol
- SHAP will help assess whether models over-rely on patient demographics. — Development and cross-site validation of machine-learning models for diagnosis and prognosis of stable angina with and without obstructive coronary artery disease: a study protocol