Skip to main content

Table 3 Performance of five-category classification model for bed net use in validation dataset

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

Net use behaviour

Observations

Sensitivity

Specificity

AUC (95% CI)

Sleep/no activity

233

0.991

0.981

0.993 (0.984–1.000)

Net folded down

45

0.733

0.989

0.985 (0.973–0.996)

Net folded up

35

0.800

0.989

0.994 (0.989–0.999)

Enter net

94

0.681

0.917

0.930 (0.908–0.952)

Exit net

95

0.632

0.909

0.906 (0.872–0.940)

Overall accuracy

416/502 (82.9%)

   
  1. AUC area under the curve, CI confidence interval
Back to article page

Malaria Journal

ISSN: 1475-2875

Contact us