Noninvasive Prototype for Type 2 Diabetes Detection

Table 5

Accuracy of machines that presented the best performances.

Algorithm	Accuracy
RL with lbfgs	0.94
RL with Newton-cg	0.93
RL with liblinear	0.93
RL with sag	0.85
ANN [ 19 14 16]	0.88
KNN with neighbors = 1	0.85
KNN with neighbors = 2	0.88
KNN with neighbors = 3	0.82
KNN with neighbors = 4	0.82

19 neurons in the input layer, 14 neurons in the hidden layer, and 16 neurons in the output layer.