Integrating Genetic, Neuropsychological and Neuroimaging Data to Model Early-Onset Obsessive Compulsive Disorder Severity
Table 3
Summary of the performances estimates of the two developed machine-learning methods.
This table summarizes the performances estimates of the two machine-learning methods used in the present study (support vector machine [SVM] and naïve Bayes [NB]) developed with the training sample and validated with the validation sample. For each machine-learning method we show: (1) the estimates of the training step using the LOO procedure; and (2) the estimates obtained with the Validation Set subsample. P-values were obtained after 10.000 permutation cycles as described in the Material and Methods section (**p < 0.01; *p < 0.05).