Multi-feature concatenation and multi-classifier stacking: An interpretable and generalizable machine learning method for MDD discrimination with rsfMRI

Yunsong Luo, Wenyu Chen, Ling Zhan, Jiang Qiu, Tao Jia

Abstract: Highlights•A new MDD discrimination method MFMC is proposed.•MFMC is tested on REST-meta-MDD including over 2400 subjects.•MFMC outperforms existing methods with significant improvements.•The good generalizability of MFMC is verified.•MFMC identifies 13 features related with 9 brain regions important for MDD.