Search

Highlights from the article: Machine learning classification of first-onset drug-naïve MDD using structural MRI We wanted to know whether it is possible to reliably train a predictive classification with a high accuracy even in the first-onset drug-naïve adolescent MDD just using structural MRI without using any other clinical data. A total of six classification models were used to build the adolescent MDD classification model: treebased bagging, random forest, multi-layered feedforward neural network, adaptive boosting, gradient boosting machine, and support vector machine.