Machine Learning in Critical Care
SHAP values were used to bridge complex model outputs to clinically interpretable feature contributions. Combining traditional Cox regression with four ML algorithms enhances both validity and clinical relevance of mortality prediction. XG…
1 sources - 4 claims
SHAP values were used to bridge complex model outputs to clinically interpretable feature contributions. Combining traditional Cox regression with four ML algorithms enhances both validity and clinical relevance of mortality prediction. XGBoost achieved the best performance among the four ML algorithms tested, with AUC values of 0.798, 0.870, and 0.903 for 360-day, 90-day, and 30-day mortality respectively. LASSO regression was used to identify the strongest independent predictors and minimise overfitting by shrinking weak coefficients to exactly zero.