Fig. 1

Performance of ML-based classifiers predicting HAND. The in-house metadataset constructed from an extensive literature search was divided into the training and testing subdatasets. Five ML classifiers and their stacked classifier were trained using the training subdataset, and their accuracies were evaluated using the testing subdataset. Stacking algorithm was XGBT. a Classifiers trained using all features. b Classifiers trained with three minimal features. Dots represent ML attempts with different random seeds. SVM, support vector machine; RF, random forest; GBM, gradient boosting machine; XGBL, extreme gradient boosting with linear booster; XGBT, extreme gradient boosting with tree booster; Stack, the stacked classifier