Fig 1.
The overall workflow including participant selection, outcome assessment, and machine learning pipeline.
Table 1.
Descriptive analysis of participants demographic information.
Fig 2.
Comparison of model performance on test datasets with area under the receiver operating characteristic curve.
(A) Performance on test datasets of the three algorithms in the primary cohort. (B) Performance on test datasets of the three algorithms in the secondary cohort. *XGBoost: extreme gradient boosting, LR: logistic regression, MLP: multilayer perceptron.
Table 2.
Fairness metrics for XGBoost across and race and gender.
Fig 3.
Distribution of the SHAP values for the top 10 features based on the highest mean absolute SHAP value (left panels) and their mean absolute contribution of the top 10 features, ranked by their average SHAP value (right panels).
Each test sample is depicted as a point for every feature, with the x-axis indicating whether the feature’s effect on the model’s prediction is positive (red on the right) or negative (blue on the right). The color of each point reflects the feature’s value, and this color scale is adjusted individually according to the value range present in the dataset. (A). SHAP values and feature importance for the primary cohort using XGBoost. (B). SHAP values and feature importance for the secondary cohort using XGBoost.