Evaluation of an accelerometer-based monitor for detecting bed net use and human entry/exit using a machine learning algorithm

Table 1 Performance of three-category classification model for bed net use behaviours in validation dataset

Net use behaviour	Observations	Sensitivity	Specificity	AUC (95% CI)
Sleep/no activity	233	0.996	0.981	0.992 (0.983–1.000)
Net down/enter/exit^a	254	0.957	0.966	0.992 (0.985–0.998)
Net folded up	35	0.771	0.989	0.987 (0.975–0.998)
Overall accuracy	483/502 (96.2%)

AUC area under the curve, CI confidence interval
^aComprises activities that occur when net is in use: unfurling net and entering/exiting unfurled net

ISSN: 1475-2875