Development of machine learning models to predict RT-PCR results for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in patients with influenza-like symptoms using only basic clinical data

Table 6 Predictive results with variables selection using Semeion (^a) and WEKA (^b) Machine learning systems

Machine learning system	Sensitivity	Specificity	Overall accuracy	Balanced accuracy	Variance	PPV	AUROC
D_FF_Conic(4x12x12x12)^a	94.1	88.7	91.4	92.2	0.5	93.5	0.90
D_FF_Conic(6x12x12x12)^a	92.5	90.2	91.3	91.7	0.0	94.1	0.91
D_FF_Bp(24) ^a	89.2	93.0	91.1	90.6	1.0	95.6	0.93
D_FF_Bp(16x16x16x16)^a	93.2	88.7	91.0	91.7	1.0	93.4	0.92
D_FF_GNet(64)^a	90.7	90.2	90.5	90.6	1.0	94.0	0.90
D_FF_Sn(48)^a	91.7	88.9	90.3	90.6	1.0	93.2	0.92
D_FF_Bm(48)^a	91.6	88.9	90.2	90.6	1.0	93.2	0.91
D_FF_Conic(48)^a	91.6	88.7	90.2	90.6	0.0	93.3	0.92
D_FF_Bp(0)^a	89.1	90.3	89.7	89.6	2.1	93.8	0.91
MLP^b	81.0	84.8	82.9	82.3	3.1	89.8	0.90
RandomForest^b	86.6	65.3	75.9	78.7	1.6	80.6	0.86
NaiveBayes^b	85.8	64.5	75.1	78.1	4.2	81.0	0.83
RotationForest^b	88.3	60.8	74.6	78.1	0.0	79.1	0.85
Logistic^b	80.7	67.9	74.3	76.0	1.0	80.8	0.63
LogitBoost^b	81.0	61.2	71.1	73.4	1.6	77.6	0.81
J48^b	77.4	60.7	69.0	71. 4	0.5	77.0	0.57
SMO^b	96.8	27.9	62.4	70.3	9.9	61.5	0.65
kNN^b	75.9	36.5	56.2	60.9	2.6	66.6	0.56

Employed machine learning systems are listed in decreasing order of overall accuracy. The results are the average of two testing experiments with training-testing A-B and B-A sequence. A hundred cases were presented in subset A and ninety-nine cases in subset B. Overall accuracy Arithmetic average of sensitivity and specificity, Balanced accuracy Weighted average of sensitivity and specificity, PPV Positive Predictive Value, AUROC Area Under the Receiver Operator Curve. Sensitivity, Specificity, Overall accuracy, Balanced accuracy, Variance and PPV are all expressed as percentage.

ISSN: 1757-7241