Skip to main content

Table 2 Definitions of evaluation metrics

From: Predictive modeling for 14-day unplanned hospital readmission risk by using machine learning algorithms

Notation/evaluation index

Description/definition

TP

True positive. The number of patients who had unplanned readmission and were also predicted to have unplanned readmission by the model

FP

False positive. The number of patients who did not have unplanned readmission but were predicted to have unplanned readmission by the model

TN

True negative. The number of patients who did not have unplanned readmission and were also not predicted to have unplanned readmission by the model

FN

False negative. The number of patients who had unplanned readmission but were not predicted to have unplanned readmission by the model

Precision

TP/(TP + FP)

Recall

TP/(TP + FN)

F1-score

The harmonic mean of precision and recall. The formula is as follows: F1 = 2 / (1 / Precision + 1 / Recall)

AUROC

Area under the receiver operating characteristic curve

AUPRC

Area under the precision–recall curve