Identification of Salient Brain Regions for Anxiety Disorders Using Nonlinear EEG Feature Analysis DOI Creative Commons
Tetiana Biloborodova, Inna Skarga-Bandurova, Maryna Derkach

et al.

Studies in health technology and informatics, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 22, 2024

In this paper, we present a novel approach for identifying salient brain regions and interpreting the ability of nonlinear EEG features to discriminate between anxiety disorders healthy controls. The proposed method involves integration advanced preprocessing artefact correction, feature extraction using conditional permutation entropy, interpretable machine learning identify relevant electrodes. extracted show statistically significant differences classes, demonstrating high discriminative ability. was confirmed with T-tests (p = 1.05e-10) Mann-Whitney U tests 2.65e-11), robust statistical significance. Classification results support these findings guide identification electrodes, enhancing interpretability features. This highlights potential critical disorder diagnosis, paving way more targeted interventions improved clinical outcomes.

Language: Английский

Intricate mechanism of anxiety disorder, recognizing the potential role of gut microbiota and therapeutic interventions DOI
Sudarshan Singh Lakhawat, Paulina Mech, Akhilesh Kumar

et al.

Metabolic Brain Disease, Journal Year: 2024, Volume and Issue: 40(1)

Published: Dec. 13, 2024

Language: Английский

Citations

1
Clinics to Algorithms Using Science and Technology DOI
Amit Pimpalkar, Nisarg Gandhewar, Nilesh Shelke

et al.

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 158 - 187

Published: Feb. 14, 2024

The chapter addresses the persistent concerns surrounding detecting and early intervention of anxiety mood disorders. These mental health conditions have become increasingly prevalent, affecting individuals across various ages socio-economic backgrounds. However, despite growing awareness their impact, challenges persist in timely diagnosis, leading to delayed treatment aggravated conditions. By examining continuum from clinical settings algorithmic analyses, strives elucidate how intelligent solutions, fueled by datasets, artificial intelligence (AI), machine learning (ML), deep (DL), can enhance accuracy, efficiency, accessibility diagnosis. chapter's primary concern revolves around leveraging power science technology revolutionize diagnostic landscape. It aims unravel transformative potential transitioning conventional assessments data-driven algorithms.

Language: Английский

Citations

0
A QR Code for the Brain: A dynamical systems framework for computing neurophysiological biomarkers DOI
William J. Bosl, Michelle Bosquet Enlow, Charles A. Nelson

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 18, 2024

Abstract Neural circuits are often considered the bridge connecting genetic causes and behavior. Whereas prenatal neural believed to be derived from a combination of intrinsic activity, postnatal largely influenced by exogenous activity experience. A dynamical neuroelectric field maintained is proposed as fundamental information processing substrate cognitive function. Time series measurements can collected scalp sensors used mathematically quantify essential features constructing digital twin system phase space. The multiscale nonlinear values that result organized into tensor data structures, which latent extracted using factorization. These mapped behavioral constructs derive biomarkers. This computational framework provides robust method for incorporating neurodynamical measures neuropsychiatric biomarker discovery.

Language: Английский

Citations

0
Identification of Salient Brain Regions for Anxiety Disorders Using Nonlinear EEG Feature Analysis DOI Creative Commons
Tetiana Biloborodova, Inna Skarga-Bandurova, Maryna Derkach

et al.

Studies in health technology and informatics, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 22, 2024

In this paper, we present a novel approach for identifying salient brain regions and interpreting the ability of nonlinear EEG features to discriminate between anxiety disorders healthy controls. The proposed method involves integration advanced preprocessing artefact correction, feature extraction using conditional permutation entropy, interpretable machine learning identify relevant electrodes. extracted show statistically significant differences classes, demonstrating high discriminative ability. was confirmed with T-tests (p = 1.05e-10) Mann-Whitney U tests 2.65e-11), robust statistical significance. Classification results support these findings guide identification electrodes, enhancing interpretability features. This highlights potential critical disorder diagnosis, paving way more targeted interventions improved clinical outcomes.

Language: Английский

Citations

0