Early prediction of acquiring acute kidney injury for older inpatients using most effective laboratory test results

Table 2 The F1-score of our approach and the three machine learning methods at 0 to 5-days prior to AKI events

Prediction Time	Our approach	Logistic Regression	Random Forest	AdaBoostM1
AKI Time-0	0.875	0.780	0.745	0.762
AKI Time-1	0.759	0.736	0.686	0.723
AKI Time-2	0.695	0.649	0.605	0.662
AKI Time-3	0.654	0.621	0.588	0.621
AKI Time-4	0.659	0.624	0.590	0.635
AKI Time-5	0.646	0.610	0.572	0.623

ISSN: 1472-6947