Journal
ACS CHEMICAL NEUROSCIENCE
Volume 12, Issue 15, Pages 2878-2886Publisher
AMER CHEMICAL SOC
DOI: 10.1021/acschemneuro.1c00256
Keywords
Major depressive disorder; resting-state functional connectivity; multiple-center; machine learning; classification; eXtreme Gradient Boosting
Funding
- National Key Research and Development Plan of China [2016YFC1306700]
- National Natural Science Key Foundation of China [81830040]
- Science and Technology Program of Guangdong [2018B030334001]
- Program of Excellent Talents in Medical Science of Jiangsu Province [JCRCA2016006]
- National Natural Science Foundation of China [81801680]
Ask authors/readers for more resources
Diagnosis of major depressive disorder using resting-state functional connectivity data faces challenges such as high dimensionality and individual differences. A machine learning model based on XGBoost showed optimal performance in distinguishing MDD patients from normal controls at an individual level, with identified features primarily distributed within specific brain networks. The model also accurately predicted the severity of depression symptoms in patients.
Diagnosis of major depressive disorder (MDD) using resting-state functional connectivity (rs-FC) data faces many challenges, such as the high dimensionality, small samples, and individual difference. To assess the clinical value of rs-FC in MDD and identify the potential rs-FC machine learning (ML) model for the individualized diagnosis of MDD, based on the rs-FC data, a progressive three-step ML analysis was performed, including six different ML algorithms and two dimension reduction methods, to investigate the classification performance of ML model in a multicentral, large sample dataset [1021 MDD patients and 1100 normal controls (NCs)]. Furthermore, the linear least-squares fitted regression model was used to assess the relationships between rs-FC features and the severity of clinical symptoms in MDD patients. Among used ML methods, the rs-FC model constructed by the eXtreme Gradient Boosting (XGBoost) method showed the optimal classification performance for distinguishing MDD patients from NCs at the individual level (accuracy = 0.728, sensitivity = 0.720, specificity = 0.739, area under the curve = 0.831). Meanwhile, identified rs-FCs by the XGBoost model were primarily distributed within and between the default mode network, limbic network, and visual network. More importantly, the 17 item individual Hamilton Depression Scale scores of MDD patients can be accurately predicted using rs-FC features identified by the XGBoost model (adjusted R-2 = 0.180, root mean squared error = 0.946). The XGBoost model using rs-FCs showed the optimal classification performance between MDD patients and HCs, with the good generalization and neuroscientifical interpretability.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available