Table 2.

Performance of the classifiers with respect to area under receiver operating characteristic curve, accuracy, sensitivity, specificity, F1-score, and false discovery rate on test sets with randomly picked 100 common variants.^a

Model	Area under receiver operating characteristic curve	Accuracy	Sensitivity	Specificity	F1-score	False discovery rate
DeepAutism	0.670	0.689	0.685	0.697	0.755	0.145
Naive Bayes	0.556	0.454	0.717	0.432	0.166	0.906
Random forest	0.701	0.629	0.612	0.855	0.754	0.018
Logistic regression	0.571	0.583	0.598	0.489	0.704	0.143
Support vector machine	0.672	0.679	0.633	0.571	0.696	0.139
Deep neural network	0.656	0.677	0.681	0.702	0.733	0.143

^aItalicized data show the best performance; the performance of all models became worse on all the metrics with randomly selected common variants.