Skip to main content
. 2021 Dec 18;21:650. doi: 10.1186/s12903-021-02016-x

Table 4.

Results of supervised machine learning methods, utilizing all features with cystatin S levels; second machine learning model

All features Feed-forward neural network XGBoost Random forest SVM
Accuracy (%) 90.9 89.2 85.7 85.4
Sensitivity (%) 100 93.3 93.3 86.6
Specificity (%) 72.1 84.6 76.9 84.6