What does this research mean for the field?

Bipolar disorder patients exhibit higher EEG signal irregularity in frontal and central brain regions, and multiscale dispersion entropy (MDE) can distinguish them from healthy controls with 95% accuracy. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To assess the diagnostic utility of various basic and multiscale EEG entropy measures coupled with machine learning to distinguish individuals with bipolar disorder from healthy controls.

January 1, 2025IEEE AccessOpen Access

The best classification performance was achieved during the eyes-open condition for the multiscale dispersion entropy (MDE) measure, with an accuracy of 95%, specificity of 93.33%, and sensitivity of 96.66%.

View Full Paper

Ask AI

Bookmark

Why the study?

Accurate and timely diagnosis of bipolar disorder remains challenging, and EEG entropy measures offer a complementary nonlinear approach that is less explored than power spectral density changes.

Do EEG entropy measures combined with machine learning accurately distinguish individuals with bipolar disorder from healthy controls?

Population

60 individuals: 30 patients with bipolar disorder and 30 healthy control participants

Comparison

Patients with bipolar disorder vs healthy controls

Design

Case-control machine learning evaluation

Authors

HBHamed Bagheri SMSeied Rabi Mahdavi NENazila Eyvazzadeh

Discussion

Member takes

Overview

May support EEG-based bipolar disorder classification tools; hypothesis-generating from Level 4 case-control data and needs prospective validation.

Key Points

To assess the diagnostic utility of various basic and multiscale EEG entropy measures coupled with machine learning to distinguish individuals with bipolar disorder from healthy controls.
Recorded resting-state EEG under eyes-closed and eyes-open conditions in 60 participants (30 patients with bipolar disorder, mean age 37.33; 30 healthy controls, mean age 35.73).
Calculated five basic entropy measures and four multiscale entropy measures across five cortical brain regions.
Applied statistical analyses and machine learning algorithms to evaluate regional entropy differences and diagnostic classification performance.
Patients with bipolar disorder showed significantly higher signal irregularity across frontal and central brain regions, with dispersion entropy and fuzzy entropy exhibiting the most pronounced group differences.
Multiscale dispersion entropy in anterior brain regions at beta frequency scales achieved peak diagnostic performance during the eyes-open condition, yielding 95.0% accuracy, 96.66% sensitivity, and 93.33% specificity.

Structured PICO

Do EEG entropy measures combined with machine learning accurately distinguish individuals with bipolar disorder from healthy controls?

Population

60 individuals: 30 patients with Bipolar Disorder (15 females, mean age = 37.33, SD = 8.83) and 30 healthy control participants (13 females, mean age = 35.73, SD = 9.01)

Intervention

EEG entropy measures (approximate, sample, permutation, fuzzy, dispersion, and multiscale entropies) combined with machine learning

Comparator

Healthy controls

Outcome

Classification performance (accuracy, specificity, sensitivity) in distinguishing individuals with BD from healthy controlssurrogate

Multiscale dispersion entropy from resting-state EEG, particularly in the frontal brain region, shows high accuracy (95%) in distinguishing bipolar disorder patients from healthy controls.

Cite This Study

Bagheri et al. (2025) studied this question.

synapsesocial.com/papers/6a1be66a4ebd09f3dfa92f50 https://doi.org/10.1109/access.2025.3539323

View Full Paper

Ask AI

Bookmark

January 1, 2025IEEE AccessOpen Access

The best classification performance was achieved during the eyes-open condition for the multiscale dispersion entropy (MDE) measure, with an accuracy of 95%, specificity of 93.33%, and sensitivity of 96.66%.

View Full Paper

Ask AI

Bookmark

Why the study?

Accurate and timely diagnosis of bipolar disorder remains challenging, and EEG entropy measures offer a complementary nonlinear approach that is less explored than power spectral density changes.

Do EEG entropy measures combined with machine learning accurately distinguish individuals with bipolar disorder from healthy controls?

Population

60 individuals: 30 patients with bipolar disorder and 30 healthy control participants

Comparison

Patients with bipolar disorder vs healthy controls

Design

Case-control machine learning evaluation

Authors

HBHamed Bagheri SMSeied Rabi Mahdavi NENazila Eyvazzadeh

Discussion

Member takes

Overview

May support EEG-based bipolar disorder classification tools; hypothesis-generating from Level 4 case-control data and needs prospective validation.

Key Points

To assess the diagnostic utility of various basic and multiscale EEG entropy measures coupled with machine learning to distinguish individuals with bipolar disorder from healthy controls.
Recorded resting-state EEG under eyes-closed and eyes-open conditions in 60 participants (30 patients with bipolar disorder, mean age 37.33; 30 healthy controls, mean age 35.73).
Calculated five basic entropy measures and four multiscale entropy measures across five cortical brain regions.
Applied statistical analyses and machine learning algorithms to evaluate regional entropy differences and diagnostic classification performance.
Patients with bipolar disorder showed significantly higher signal irregularity across frontal and central brain regions, with dispersion entropy and fuzzy entropy exhibiting the most pronounced group differences.
Multiscale dispersion entropy in anterior brain regions at beta frequency scales achieved peak diagnostic performance during the eyes-open condition, yielding 95.0% accuracy, 96.66% sensitivity, and 93.33% specificity.

Structured PICO

Do EEG entropy measures combined with machine learning accurately distinguish individuals with bipolar disorder from healthy controls?

Population

60 individuals: 30 patients with Bipolar Disorder (15 females, mean age = 37.33, SD = 8.83) and 30 healthy control participants (13 females, mean age = 35.73, SD = 9.01)

Intervention

EEG entropy measures (approximate, sample, permutation, fuzzy, dispersion, and multiscale entropies) combined with machine learning

Comparator

Healthy controls

Outcome

Classification performance (accuracy, specificity, sensitivity) in distinguishing individuals with BD from healthy controlssurrogate

Multiscale dispersion entropy from resting-state EEG, particularly in the frontal brain region, shows high accuracy (95%) in distinguishing bipolar disorder patients from healthy controls.

Cite This Study

Bagheri et al. (2025) studied this question.

synapsesocial.com/papers/6a1be66a4ebd09f3dfa92f50 https://doi.org/10.1109/access.2025.3539323

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark