Machine Learning Models for Analysis of Vital Signs Dynamics: A Case for Sepsis Onset Prediction
Table 4
Models performance results.
ā
LR
SVM-linear
SVM-RBF
SVM- polynomial
ANN
Sensitivity
0.8182
0.8571
0.7792
0.8442
0.7532
Specificity
0.8718
0.8590
0.9615
0.8974
0.9359
PPV
0.8630
0.8571
0.9524
0.8904
0.9206
NPV
0.8293
0.8590
0.8152
0.8537
0.7935
Accuracy
0.8452
0.8581
0.8710
0.8710
0.8452
AUC
0.8461
0.8581
0.8838
0.8720
0.8571
AUC-PR
0.9169
0.9043
0.9358
0.9353
0.9338
AUC: area under the curve; AUC-PR: area under precision recall curve; LR: logistic regression; PPV: positive predictive value; NPV: negative predictive value.