Skip to main content
. 2019 Sep 20;101(23):e127. doi: 10.2106/JBJS.18.01197

Fig. 3.

Fig. 3

The support vector machine (SVM) achieved the highest accuracy, at 97.6%, with use of leave-one-out cross-validation. The k-nearest neighbors (kNN) reached an accuracy of 92.7%. The linear discriminant analysis (LDA) achieved an accuracy of 87.8%. The decision tree had a 70.7% accuracy. The naive Bayes reached the lowest accuracy, at 65.9%.