Table 3 The performance of the prediction models based on different classifications using a test dataset with 95% CI.

From: Factors of acute respiratory infection among under-five children across sub-Saharan African countries using machine learning approaches

Algorithms

Sensitivity (95% CI)

Specificity (95% CI)

AUC (95% CI)

Accuracy (95% CI)

GLM

0.64 (0.63, 0.66)

0.67 (0.64, 0.69)

0.72 (0.70, 0.73)

0.65 (0.64, 0.67)

Ridge

0.89 (0.88, 0.90)

0.36 (0.34, 0.39)

0.71 (0.70, 0.73)

0.71 (0.70, 0.73)

Lasso

0.89 (0.88, 0.90)

0.37 (0.34, 0.39)

0.72 (70, 0.73)

0.71 (0.69, 0.72)

elastic-net

0.89 (0.88, 0.90)

0.36 (0.34, 0.39)

0.72 (0.70, 0.73)

0.70 (0.69, 0.72)

ANN

0.64 (0.63, 0.66)

0.71 (0.68, 0.73)

0.74 (0.73, 0.75)

0.67 (0.65, 0.68)

KNN

0.84 (0.83, 0.86)

0.43 (0.40, 0.45)

0.71 (70, 0.73)

0.70 (0.69, 0.72)

NB

0.59 (0.57, 0.61)

0.72 (0.69, 0.74)

0.70 (0.68, 0.71)

0.63 (0.61, 0.65)

Bagged tree

0.80 (0.78, 0.81)

0.53 (0.50, 0.56)

0.74 (0.72, 0.75)

0.71 (0.69, 0.72)

RF

0.81 (0.80, 0.83)

0.55 (0.52, 0.58)

0.77 (0.75, 0.78)

0.72 (0.71, 0.73)

Boosting

0.82 (0.81, 0.84)

0.53 (0.50, 0.55)

0.76 (0.74, 0.77)

0.72 (0.71, 0.74)

DT

0.86 (0.85, 0.88)

0.40 (0.37, 0.73)

0.68 (66, 0.70)

0.71 (0.69, 0.72)

  1. GLM generalized linear model, ANN artificial neural network, KNN K nearest neighbor, NB Naïve Bayes, RF Random Forest, DT decision tree, AUC area under curve, CI confidence interval.
  2. The selected machine learning algorithm in bold.
Back to article page