Resting-State EEG Signal for Major Depressive Disorder Detection: A Systematic Validation on a Large and Diverse Dataset
Authors:
- Chien-Te WuCWChien-Te Wu
- Hao-Chuan HuangHHHao-Chuan Huang
- Shiuan HuangSHShiuan Huang
- I-Ming ChenICI-Ming Chen
- Shih-Cheng LiaoSLShih-Cheng Liao
- Chih-Ken ChenCCChih-Ken Chen
- Chemin LinCLChemin Lin
- Shwu-Hua LeeSLShwu-Hua Lee
- Mu-Hong ChenMCMu-Hong Chen
- Chia-Fen TsaiCTChia-Fen Tsai
- Chang-Hsin WengCWChang-Hsin Weng
- Li-Wei KoLKLi-Wei Ko
Open Access
- 6 December 2021
- journal article
- research article
- Published by MDPI AG in Biosensors
- Vol. 11 (12) , 499
Abstract
Major depressive disorder (MDD) is a global healthcare issue and one of the leading causes of disability. Machine learning combined with non-invasive electroencephalography (EEG) has recently been shown to have the potential to diagnose MDD. However, most of these studies analyzed small samples of participants recruited from a single source, raising serious concerns about the generalizability of these results in clinical practice. Thus, it has become critical to re-evaluate the efficacy of various common EEG features for MDD detection across large and diverse datasets. To address this issue, we collected resting-state EEG data from 400 participants across four medical centers and tested classification performance of four common EEG features: band power (BP), coherence, Higuchi’s fractal dimension, and Katz’s fractal dimension. Then, a sequential backward selection (SBS) method was used to determine the optimal subset. To overcome the large data variability due to an increased data size and multi-site EEG recordings, we introduced the conformal kernel (CK) transformation to further improve the MDD as compared with the healthy control (HC) classification performance of support vector machine (SVM). The results show that (1) coherence features account for 98% of the optimal feature subset; (2) the CK-SVM outperforms other classifiers such as K-nearest neighbors (K-NN), linear discriminant analysis (LDA), and SVM; (3) the combination of the optimal feature subset and CK-SVM achieves a high five-fold cross-validation accuracy of 91.07% on the training set (140 MDD and 140 HC) and 84.16% on the independent test set (60 MDD and 60 HC). The current results suggest that the coherence-based connectivity is a more reliable feature for achieving high and generalizable MDD detection performance in real-life clinical practice.Keywords
This publication has 67 references indexed in Scilit:
- Spectral Asymmetry and Higuchi’s Fractal Dimension Measures of Depression ElectroencephalogramComputational and Mathematical Methods in Medicine, 2013
- Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signalComputer Methods and Programs in Biomedicine, 2013
- Major depressive disorder: new clinical, neurobiological, and treatment perspectivesThe Lancet, 2012
- Altered Cerebellar-Cerebral Functional Connectivity in Geriatric DepressionPLOS ONE, 2011
- Resting-state functional MRI in depression unmasks increased connectivity between networks via the dorsal nexusProceedings of the National Academy of Sciences, 2010
- Major Depressive DisorderNew England Journal of Medicine, 2008
- The PHQ-9Journal of General Internal Medicine, 2001
- The Mini International Neuropsychiatric Interview (MINI). A short diagnostic structured interview: reliability and validity according to the CIDIEuropean Psychiatry, 1997
- Floating search methods in feature selectionPattern Recognition Letters, 1994
- The Hospital Anxiety and Depression ScaleActa Psychiatrica Scandinavica, 1983