Ensemble Learning for Early‐Response Prediction of Antidepressant Treatment in Major Depressive Disorder

• Published in: Journal of magnetic resonance imaging Vol. 52; no. 1; pp. 161 - 171
• Main Authors: Pei, Cong, Sun, Yurong, Zhu, Jinlong, Wang, Xinyi, Zhang, Yujie, Zhang, Shuqiang, Yao, Zhijian, Lu, Qing
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.07.2020; Wiley Subscription Services, Inc
• Subjects: Algorithms; antidepressant response; Antidepressants; Antidepressive Agents - therapeutic use; Biomarkers; Brain; Clinical trials; Depressive Disorder, Major - diagnostic imaging; Depressive Disorder, Major - drug therapy; Field strength; genetics; Humans; Image processing; Information processing; Integration; Learning algorithms; Machine Learning; Magnetic resonance imaging; major depressive disorder; Medical imaging; Mental depression; Model accuracy; Modelling; Neuroimaging; Performance evaluation; prediction; Prediction models; Prospective Studies; resting‐state fMRI; Sensitivity; Statistical analysis; Statistical tests; Support Vector Machine; Support vector machines; antidepressant response; prediction; genetics; major depressive disorder; machine learning; resting-state fMRI

Background In order to reduce unsuccessful treatment trials for depression, neuroimaging and genetic information can be considered as biomarkers. Together with machine‐learning methods, prediction models have proved to be valuable for baseline prediction. Purpose To propose an ensemble learning mode...