EEG Microstate-Based Classification in Adolescents with Depression and Non-Suicidal Self-Injury
Poster No:
448
Submission Type:
Abstract Submission
Authors:
Young Wook Song1, Se-Hoon Shim2, Ji Sun Kim2, Sungkean Kim1
Institutions:
1Department of Applied Artificial Intelligence, Hanyang University, Ansan, Gyeonggi-do, Republic of Korea, 2Department of Psychiatry, Soonchunhyang University, Cheonan, Chungcheongnam-do, Republic of Korea
First Author:
Young Wook Song
Department of Applied Artificial Intelligence, Hanyang University
Ansan, Gyeonggi-do, Republic of Korea
Department of Applied Artificial Intelligence, Hanyang University
Ansan, Gyeonggi-do, Republic of Korea
Co-Author(s):
Se-Hoon Shim
Department of Psychiatry, Soonchunhyang University
Cheonan, Chungcheongnam-do, Republic of Korea
Department of Psychiatry, Soonchunhyang University
Cheonan, Chungcheongnam-do, Republic of Korea
Ji Sun Kim
Department of Psychiatry, Soonchunhyang University
Cheonan, Chungcheongnam-do, Republic of Korea
Department of Psychiatry, Soonchunhyang University
Cheonan, Chungcheongnam-do, Republic of Korea
Sungkean Kim
Department of Applied Artificial Intelligence, Hanyang University
Ansan, Gyeonggi-do, Republic of Korea
Department of Applied Artificial Intelligence, Hanyang University
Ansan, Gyeonggi-do, Republic of Korea
Introduction:
Non-suicidal self-injury (NSSI) is a prevalent and concerning behavior among adolescents, particularly those diagnosed with Major Depressive Disorder (MDD). The identification of neural correlates associated with NSSI in this population is crucial for early detection and intervention. Electroencephalography (EEG) microstate analysis, which offers insights into brain dynamics with high temporal resolution, presents a promising approach for exploring these neural patterns. This study investigated the distinct EEG microstate patterns in adolescents with MDD and NSSI and evaluated the potential of machine learning techniques in distinguishing these patterns.
Methods:
The 134 participants including 44 depressed adolescents with NSSI, 41 depressed adolescents without NSSI, and 49 healthy controls (HCs) were enrolled and recorded EEG. For the microstate analysis, four representative topographic maps were extracted among groups and five microstate parameters were derived: global explained variance, duration, occurrence, coverage, and transition probabilities. We compared the obtained microstate parameters with the results of psychological assessments. Finally, Machine learning algorithms were employed to classify the EEG data, aiming to identify patterns specific to the adolescent MDD with or without NSSI group from HCs.
·Overview of EEG microstate analysis
Results:
As for GEV, duration, occurrence, and coverage, microstate B had a significantly higher value in the HCs compared to the adolescent MDD with or without NSSI. The adolescent MDD with NSSI showed significantly lower TP value from class D to B compared to the adolescent MDD without NSSI and HCs. Microstate B and C related parameters showed significant correlation with psychological assessment in adolescent MDD with NSSI group. For classification among groups, the best classification performances showed 77.42 % accuracy between adolescent MDD with NSSI and HCs, 71.11 % accuracy between adolescent MDD without NSSI and HCs, and 63.53 % accuracy between adolescent MDD without NSSI and adolescent MDD with NSSI.
·Microstate template maps obtained from HC, MDD without NSSI, MDD with NSSI, and grand mean among three groups
Conclusions:
This study underscores the utility of EEG microstate analysis combined with machine learning techniques in identifying biomarkers associated with NSSI in adolescents with MDD. These findings contribute to the understanding of the neural mechanisms underlying NSSI and offer a potential pathway for developing predictive tools for early intervention in this vulnerable population.
Disorders of the Nervous System:
Psychiatric (eg. Depression, Anxiety, Schizophrenia) 1
Modeling and Analysis Methods:
Classification and Predictive Modeling
EEG/MEG Modeling and Analysis 2
Novel Imaging Acquisition Methods:
EEG
Keywords:
Electroencephaolography (EEG)
Machine Learning
Psychiatric Disorders
Other - Non-Suicidal Self-Injury
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
Provide references using APA citation style.
Khanna, A., Pascual-Leone, A., Michel, C. M., & Farzan, F. (2015). Microstates in resting-state EEG: current status and future directions. Neuroscience & Biobehavioral Reviews, 49, 105-113.