Skip to main content

Table 1 Tenfold cross-validation results showing discrimination between P. falciparum-positive sera from P. falciparum-negative sera with P. falciparum-positive sera considered as positive category: scores (in %) obtained with four different classifying algorithms (SVM, PLS-DA, RF, and LightGBM)

From: MALDI-TOF mass spectrometry combined with machine learning algorithms to identify protein profiles related to malaria infection in human sera from Côte d’Ivoire

 

Accuracy

%

Sensitivity

%

Specificity

%

Error rate

%

PPV

%

NPV

%

F1-score

%

SVM

73.28

70.23

76.34

26.72

74.8

71.94

72.44

PLS-DA

74.81

74.05

75.57

25.19

75.19

74.44

74.62

RF

80.92

83.97

77.86

19.08

79.14

82.93

81.48

LightGBM

81.3

81.68

80.92

18.7

81.06

81.54

81.37

  1. PPV: positive predictive values; NPV: negative predictive values