Multiband EEG signature decoded using machine learning for predicting rTMS treatment response in major depression DOI Creative Commons

Alexander Arteaga,

Xiaoyu Tong, Kanhao Zhao

и другие.

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Сен. 24, 2024

Abstract Major depressive disorder (MDD) is a global health challenge with high prevalence. Further, many diagnosed MDD are treatment resistant to traditional antidepressants. Repetitive transcranial magnetic stimulation (rTMS) offers promise as an alternative solution, but identifying objective biomarkers for predicting response remains underexplored. Electroencephalographic (EEG) recordings cost-effective neuroimaging approach, EEG analysis methods often do not consider patient-specific variations and fail capture complex neuronal dynamics. To address this, we propose data-driven approach combining iterated masking empirical mode decomposition (itEMD) sparse Bayesian learning (SBL). Our results demonstrated significant prediction of rTMS outcomes using this (Protocol 1: r=0.40, p<0.01; Protocol 2: r=0.26, p<0.05). From the decomposition, obtained three key oscillations: IMF-Alpha, IMF-Beta, remaining residue. We also identified spatial patterns associated two protocols: 1 (10Hz left DLPFC), important areas include frontal parietal regions, while 2 (1Hz right frontal, regions crucial. Additionally, our exploratory found few correlations between oscillation specific predictive features personality measures. This study highlights potential machine learning-driven personalized prediction, offering pathway improved patient outcomes.

Язык: Английский

Multiband EEG signature decoded using machine learning for predicting rTMS treatment response in major depression DOI Creative Commons

Alexander Arteaga,

Xiaoyu Tong, Kanhao Zhao

и другие.

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Сен. 24, 2024

Abstract Major depressive disorder (MDD) is a global health challenge with high prevalence. Further, many diagnosed MDD are treatment resistant to traditional antidepressants. Repetitive transcranial magnetic stimulation (rTMS) offers promise as an alternative solution, but identifying objective biomarkers for predicting response remains underexplored. Electroencephalographic (EEG) recordings cost-effective neuroimaging approach, EEG analysis methods often do not consider patient-specific variations and fail capture complex neuronal dynamics. To address this, we propose data-driven approach combining iterated masking empirical mode decomposition (itEMD) sparse Bayesian learning (SBL). Our results demonstrated significant prediction of rTMS outcomes using this (Protocol 1: r=0.40, p<0.01; Protocol 2: r=0.26, p<0.05). From the decomposition, obtained three key oscillations: IMF-Alpha, IMF-Beta, remaining residue. We also identified spatial patterns associated two protocols: 1 (10Hz left DLPFC), important areas include frontal parietal regions, while 2 (1Hz right frontal, regions crucial. Additionally, our exploratory found few correlations between oscillation specific predictive features personality measures. This study highlights potential machine learning-driven personalized prediction, offering pathway improved patient outcomes.

Язык: Английский

Процитировано

0