J Clin Med Res

Journal of Clinical Medicine Research, ISSN 1918-3003 print, 1918-3011 online, Open Access

Article copyright, the authors; Journal compilation copyright, J Clin Med Res and Elmer Press Inc

Journal website https://www.jocmr.org

Original Article

Volume 15, Number 3, March 2023, pages 133-138

Using Machine Learning Algorithms to Predict Patient Portal Use Among Emergency Department Patients With Diabetes Mellitus

Figure

Figure 1. Feature importance scores.

Tables

**Table 1.** Performance Measures of the Six Classifiers Before Feature Selection (All 18 Variables Used in the Model)
Classifier	Accuracy	Sensitivity	Specificity	AUC
AUC: area under the receiver operating characteristic curve.
Logistic regression	0.8242	0.7542	0.9727	0.8034
Random forest	0.9876	0.9454	0.9969	0.9712
Deep forest	0.9784	0.8966	0.9965	0.9465
Decision tree	0.9820	0.9508	0.9890	0.9699
Multilayer perception	0.8222	0.7814	0.9862	0.9693
Support vector machine	0.6166	0.5265	0.6992	0.5851

**Table 2.** A Comparison of Performance Measures of Six Different ML Algorithm Feature Selections (Top Eight Ranked Variables)
Classifier	Accuracy	Sensitivity	Specificity	AUC
ML: machine learning; AUC: area under the receiver operating characteristic curve.
Logistic regression	0.8351	0.7566	0.9839	0.8124
Random forest	0.9876	0.9374	0.9932	0.9769
Deep forest	0.9773	0.8962	0.9875	0.9510
Decision tree	0.9818	0.9493	0.9901	0.9710
Multilayer perception	0.8263	0.7798	0.9861	0.9634
Support vector machine	0.7052	0.6891	0.7134	0.6971