Table 3 Evaluation metrics and 95% confidence interval (CI) of the ML classifiers using selected features (Peak current changes, age, urine pH).

From: Machine learning approach using electrochemical immunosensor data for precise classification of Opisthorchis viverrini infection

Model

Accuracy (%) (95% CI)

F1 Score (95% CI)

Recall (95% CI)

Specificity (95% CI)

AUC (95% CI)

Cross-validation scores (%) (95% CI)

Decision tree

90.65 (0.89–0.91)

0.91 (0.90–0.92)

0.96 (0.90–0.98)

0.83 (0.80–0.86)

0.86 (0.83–0.88)

88.21 (0.87–0.89)

k-nearest neighbors

84.11 (0.83–0.88)

0.84 (0.74–0.93)

0.86 (0.84–0.88)

0.81 (0.78–0.86)

0.87 (0.85–0.90)

83.95 (0.79–0.86)

AdaBoost

90.65 (0.89–0.91)

0.90 (0.88–0.92)

0.94 (0.92–0.96)

0.86 (0.84–0.89)

0.88 (0.84–0.92)

85.60 (0.85–0.89)

Naïve Bayes

82.24 (0.79–0.86)

0.82 (0.81–0.84)

0.89 (0.88–0.93)

0.71 (0.69–0.74)

0.83 (0.81–0.86)

82.31 (0.79–0.86)

Random forest

85.98 (0.80–0.89)

0.85 (0.80–0.88)

0.87 (0.84–0.90)

0.85 (0.81–0.89)

0.90 (0.87–0.93)

86.08 (0.82–0.90)

Neural network

89.72 (0.84–0.93)

0.89 (0.86–0.91)

0.89 (0.87–0.90)

0.91 (0.88–0.94)

0.84 (0.82–0.85)

87.50 (0.86–0.89)

Back to article page