Fig. 2: Feature selection and model performance comparison. | npj Digital Medicine

Fig. 2: Feature selection and model performance comparison.

From: A Causal and interpretable machine learning framework for postcranioplasty risk prediction and surgical decision support

Fig. 2: Feature selection and model performance comparison.The alternative text for this image may have been generated using AI.

a Feature importance ridge plot for variable selection based on Boruta. b Variable Venn diagram screened by four methods. (c) Bubble plots for comparing machine learning model performance based on the AB_score. DC-CP interval the time interval (in months) between decompressive craniectomy (DC) and cranioplasty (CP), GOS Glasgow Outcome Scale, GCS Glasgow Coma Scale, BI Barthel Index, HBV hepatitis B virus infection, CHD coronary heart disease, N-P drainage postoperative placement of subcutaneous negative-pressure drainage tubes, Pre-op V-P preoperative ventriculoperitoneal shunt status, Pre-op preoperative, GAM generalized additive model, LR logistic regression, GBDT gradient-boosted decision tree, KNN k-nearest neighbor, LightGBM light gradient boosting machine, RotF rotation forest, XGBoost extreme gradient boosting, NB naive Bayes, AdaBoost adaptive boosting, MLP multilayer perceptron, SVM support vector machine, DT decision tree, ExtraTrees extremely randomized trees, GPC Gaussian process classifier, RF random forest.

Back to article page