Print Close

Predictive regression model for depression severity using gender/age-reflected QEEG biomarkers.

Poster No:

497

Submission Type:

Abstract Submission

Authors:

Nam-Heon Kim¹^,2, Daekeun Kim¹, Seungwan Kang¹^,3

Institutions:

¹iMediSync Inc., Gangnam-gu, Seoul, Republic of Korea, ²Department of Neurosurgery, Osaka University School of Medicine, Osaka, Japan, ³National Standard Reference Data Center for Korean EEG, Seoul National University College of Nursing, Seoul, Korea, Republic of

First Author:

Nam-Heon Kim
iMediSync Inc.|Department of Neurosurgery, Osaka University School of Medicine
Gangnam-gu, Seoul, Republic of Korea|Osaka, Japan

Co-Author(s):

Daekeun Kim
iMediSync Inc.
Gangnam-gu, Seoul, Republic of Korea

Seungwan Kang
iMediSync Inc.|National Standard Reference Data Center for Korean EEG, Seoul National University College of Nursing
Gangnam-gu, Seoul, Republic of Korea|Seoul, Korea, Republic of

Introduction:

Depression is a prevalent mental disorder in modern society, causing significant suffering and, in severe cases, leading to suicide. Psychiatrists and psychologists typically diagnose depression through well-known assessments such as the Beck Depression Inventory (BDI) and the Hamilton Depression Rating Scale (HDRS), often combined with patient consultations. However, these traditional methods are time-consuming, prone to patient bias, and influenced by clinician subjectivity.
Meanwhile, numerous studies have suggested that QEEG can serve as a biomarker for depression. When applied with precision, QEEG offers a promising approach for depression screening that is cost-effective and highly accessible.

Methods:

Eye-closed, resting-state QEEG data were collected from 118 potential depression patients and 80 healthy controls (male = 44, female = 36, age = 48.66 ± 16.71 years, BDI = 0), with each recording lasting longer than 2 minutes after pre-processing. Among the 118 potential depression patients, 34 were clinically diagnosed with depression, while 84 scored above 10 on the PHQ-9 test.
19-channel EEG data were recorded following the international 10-20 system. Pre-processing involved bad epoch rejection and Independent Component Analysis (ICA) using iSyncBrain®. Spectrum power and the lateral asymmetry of alpha power in the frontal lobe were calculated. Additionally, Dominant Frequency (DF) and DF power were derived from the cleaned data, which underwent a band-pass filter (6.5 to 12 Hz), with peak points exceeding a defined threshold being selected. Each feature was then standardized to a z-score using the iSyncBrain gender- and age-normative database.
The differences in each QEEG feature between the depression and healthy groups were analyzed. Using these features, a regression model was developed to predict depression severity. A 5-fold cross-validation approach was applied, where 80% of the data were used for training, and testing was performed on the remaining 20% of the data not included in training.

Results:

Patients with depression Showed different QEEG patterns compared to healthy control. In specific, overall Alpha, Delta power increased, Frontal asymmetry enhanced, Beta power in Central and Parietal areas increased, and Occipital peak frequency slowed.
The regression model showed R-square of 0.4 and classification accuracy of 77%.

·QEEG difference between depression and healthy group expressed by topography in Delta, Theta, Alpha and Beta frequency bands

·Scatter plot showing the result of regression model for depression severity prediction

Conclusions:

Significant differences across various QEEG features between the depression group and the normal group were confirmed. Based on this, it was verified that a regression model could predict not only the presence of depression but also its severity with good accuracy.

Disorders of the Nervous System:

Psychiatric (eg. Depression, Anxiety, Schizophrenia) ¹

Modeling and Analysis Methods:

EEG/MEG Modeling and Analysis ²

Novel Imaging Acquisition Methods:

EEG

Keywords:

Data analysis

Electroencephaolography (EEG)

Psychiatric Disorders

Other - Depression

^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.

I accept

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:

I do not want to participate in the reproducibility challenge.

Please indicate below if your study was a "resting state" or "task-activation” study.

Resting state

Healthy subjects only or patients (note that patient studies may also involve healthy subjects):

Patients

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.

Yes

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.

Not applicable

Please indicate which methods were used in your research:

EEG/ERP

Provide references using APA citation style.

not applicable

UNESCO Institute of Statistics and World Bank Waiver Form

I attest that I currently live, work, or study in a country on the UNESCO Institute of Statistics and World Bank List of Low and Middle Income Countries list provided.