Machine learning-based prediction model of acute kidney injury in patients with acute respiratory distress syndrome

Table 4 Evaluation indicators in extra validation set of XGBoost_HPO and other models

Model	Accuracy	Sensitivity	Specificity	PPV	NPV	F1_score
XGBoost	0.724	0.789	0.688	0.590	0.851	0.675
LightGBM	0.723	0.793	0.683	0.582	0.856	0.671
Logistic_ Regression	0.677	0.709	0.660	0.537	0.803	0.610
KNN	0.578	0.662	0.531	0.440	0.739	0.529
SOFA	0.699	0.531	0.734	0.293	0.883	0.378

KNN, K-nearest neighbor; XGBoost, eXtreme gradient boosting; HPO, hyperparameter optimization; LightGBM, light gradients boosting machine; PPV, positive prediction value; NPV, negative prediction value; SOFA, sequential organ failure assessment

ISSN: 1471-2466