Skip to main content
. 2020 Oct 27;8(10):e20324. doi: 10.2196/20324

Table 3.

Areas under the precision-recall curve and 95% confidence intervals of hospital admission prediction models according to machine learning models and predictor modalities.

Model type Model 1a Model 2b Model 3c Model 4d
Logistic regression 0.614
(0.578-0.653)		 0.729
(0.700-0.766)		 0.794
(0.764-0.827)		 0.709
(0.667-0.744)
Lasso 0.614
(0.578-0.654)		 0.766
(0.737-0.795)		 0.829
(0.805-0.853)		 0.820
(0.793-0.845)
Random forest 0.580
(0.550-0.615)		 0.734
(0.703-0.770)		 0.828
(0.802-0.853)		 0.828
(0.801-0.851)
Gradient boosting machine 0.609
(0.580-0.647)		 0.766
(0.734-0.799)		 0.831
(0.804-0.855)		 0.828
(0.803-0.852)

aModel 1: Age and sex.

bModel 2: Age, sex, and chief complaint.

cModel 3: Age, sex, chief complaint, and vital signs.

dModel 4: Age, sex, chief complaint, vital signs, and past medical history.