Skip to main content
. Author manuscript; available in PMC: 2022 Nov 18.
Published in final edited form as: Inform Med Unlocked. 2022 Oct 6;34:101104. doi: 10.1016/j.imu.2022.101104

Table 3.

Performance metrics for the tested machine learning algorithms. Values represented as mean (S.D.).

Algorithm AUROC Sensitivity Specificity Accuracy Balanced
Accuracy
Featureless 0.50
(0.00)		 1.00
(0.00)		 0.00
(0.00)		 0.68
(0.05)		 0.50
(0.00)
Logistic Regression 0.72
(0.06)		 0.75
(0.06)		 0.62
(0.10)		 0.71
(0.05)		 0.69
(0.06)
Naïve Bayes 0.84
(0.04)		 0.85
(0.04)		 0.76
(0.08)		 0.82
(0.04)		 0.80
(0.04)
Regularized Regression (ElasticNet) 0.89
(0.02)		 0.88
(0.04)		 0.73
(0.07)		 0.83
(0.03)		 0.80
(0.03)
k-nearest Neighbor 0.85
(0.03)		 0.88
(0.05)		 0.60
(0.09)		 0.79
(0.04)		 0.74
(0.04)
Support Vector Machine 0.90
(0.03)		 0.85
(0.04)		 0.86
(0.07)		 0.85
(0.03)		 0.85
(0.04)
Random Forest 0.92
(0.03)		 0.90
(0.03)		 0.82
(0.07)		 0.87
(0.03)		 0.86
(0.04)
Gradient Boosted Trees 0.92
(0.02)		 0.89
(0.04)		 0.82
(0.08)		 0.87
(0.03)		 0.85
(0.04)