BMC Medical Informatics and Decision Making

Table 3 Random forest model versus simple heuristic baseline model performances over three time periods, reported on the test set

From: Use of machine learning to identify patients at risk of sub-optimal adherence: study based on real-world data from 10,929 children using a connected auto-injector device

	3 months prediction		6 months prediction		9 months prediction
	Random forest	Baseline	Random forest	Baseline	Random forest	Baseline
Sensitivity	0.77	0.49	0.77	0.44	0.72	0.39
Specificity	0.81	0.96	0.81	0.97	0.80	0.97
F1-score	0.59	0.60	0.59	0.57	0.60	0.52

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com