Table 10.

Automated detection of CAP.

Author (Year) [Reference]	Database	Data Preprocessing	Model	Results
Mariani et al. (2012) [107]	Parma Sleep Disorders Center	Hjorth activity; EEG variance	Discriminant classifier	Accuracy = 84.9%
Chindhade et al. (2018) [105]	CAP Sleep Database	Differential moving average	Logistic regression	AUROC = 0.512; Accuracy = 58%
Hui et al.(2021) [106]	CAP Sleep Database	-	CNN	Sensitivity = 80.29%; Accuracy = 74.43%
Mendona et al.(2021) [108]	CAP Sleep Database	Lowpass filter	LSTM	Accuracy = 81.3%; Sensitivity = 73.7%; Specificity = 81.7%