Skip to main content

Table 3 Performance of different machine learning algorithms in the classification of mild COPD and moderate + severe COPD

From: Multi-channel lung sounds intelligent diagnosis of chronic obstructive pulmonary disease

Model Accuracy Sensitivity Specificity AUC F1-Score Kappa
SVM 89.13 87.72 91.01 96.27 89.13 78.66
(87.49–91.05) (85.12–90.48) (89.64–92.54) (95.56–96.98) (87.29–91.03) (74.99–82.09)
Bayes 84.97 82.61 87.34 93.29 84.65 69.94
(83.48–86.47) (80.94–84.29) (85.32–89.37) (92.11–94.46) (83.04–86.26) (68.33–70.16)
Decision Tree 69.25 66.32 72.24 67.88 68.39 38.52
(68.33–70.16) (62.63–70.01) (67.24–77.23) (64.69–71.06) (67.02–69.76) (36.60–40.46)
DBN 71.74 70.08 73.53 77.75 71.27 43.52
(66.42–77.06) (62.99–77.16) (63.54–83.52) (73.52–81.98) (65.92–76.62) (32.90–54.14)