Fig. 2From: Enhancing prediction of supraspinatus/infraspinatus tendon complex injuries through integration of deep visual features and clinical information: a multicenter two-round assessment studyDemonstration of construction of the ensemble CML-DL scheme. Four CML models including SVM, lasso, decision tress, and random forest were trained to obtain features from clinical characteristics. An ensemble DL scheme and three benchmark DL models were used to merge the image features extracted from shoulder radiographs. Finally, an ensemble CML-DL model was used to integrate the features obtained from images and digital data to predict NIRAC and SRCT. SRCT, significant rotator cuff tear; NIRCA, normal or insignificant rotator cuff abnormality; SVM, support vector machine, DL, deep learning; CML, clinical machine learning; VGG, Visual Geometry GroupBack to article page