A Review on Machine Learning Models for Breathing Pattern Analysis of Soldiers DOI

P. Kaleeswari,

R. Ramalakshmi,

Arunprasath Thiyagarajan

et al.

Published: Dec. 14, 2023

Since 2001, the U.S. military has sent 2.7 million people to support missions in Afghanistan and Asia. The experience of land-based employees is increased by exposure additional inhalational exposures particulate matter from a variety sources. For purpose preventing significant loss nation individual soldier, post-traumatic stress disorder (PTSD) must be identified. Breathing pattern analysis key method for detecting PTSD, various studies have used machine learning techniques this purpose. This survey examines multiple ML models determine soldiers' breathing patterns distinct works. overview discusses several strategies over past few decades conducting extensive research. Military personnel' are analyzed using datasets, statistical factors, methodologies. effectiveness algorithms compared qualitative as well quantitative approaches. potential future study areas with major challenges discussed reach conclusion.

Language: Английский

The Functional Aspects of Resting EEG Microstates: A Systematic Review DOI
Povilas Tarailis, Thomas Koenig, Christoph M. Michel

et al.

Brain Topography, Journal Year: 2023, Volume and Issue: 37(2), P. 181 - 217

Published: May 10, 2023

Language: Английский

Citations

121
Test–retest reliability of resting‐state EEG in young and older adults DOI Creative Commons
Tzvetan Popov, Marius Tröndle, Zofia Baranczuk‐Turska

et al.

Psychophysiology, Journal Year: 2023, Volume and Issue: 60(7)

Published: March 9, 2023

Abstract The quantification of resting‐state electroencephalography (EEG) is associated with a variety measures. These include power estimates at different frequencies, microstate analysis, and frequency‐resolved source connectivity analyses. Resting‐state EEG metrics have been widely used to delineate the manifestation cognition identify psychophysiological indicators age‐related cognitive decline. reliability utilized prerequisite for establishing robust brain–behavior relationships clinically relevant To date, however, test–retest examination measures derived from resting human EEG, comparing between young older participants, within same adequately powered dataset, lacking. present registered report examined in sample 95 (age range: 20–35 years) 93 60–80 participants. A good‐to‐excellent was confirmed both age groups on scalp levels as well individual alpha peak frequency. Partial confirmation observed hypotheses stating microstates connectivity. Equal were scalp‐level partially so source‐level In total, five out nine postulated empirically supported most commonly reported metrics.

Language: Английский

Citations

36
EEG Microstates in Mood and Anxiety Disorders: A Meta-analysis DOI Creative Commons

Alina Chivu,

Simona A. Pascal, Alena Damborská

et al.

Brain Topography, Journal Year: 2023, Volume and Issue: unknown

Published: Aug. 24, 2023

Abstract To reduce the psycho-social burden increasing attention has focused on brain abnormalities in most prevalent and highly co-occurring neuropsychiatric disorders, such as mood anxiety. However, high inter-study variability these patients results inconsistent contradictory alterations fast temporal dynamics of large-scale networks measured by EEG microstates. Thus, this meta-analysis, we aim to investigate consistency changes better understand possible common neuro-dynamical mechanisms disorders. In systematic search, twelve studies investigating microstate participants with anxiety disorders individuals subclinical depression were included adding up 787 participants. The suggest that microstates consistently discriminate impairments from general population states. Specifically, found a small significant effect size for B compared healthy controls, larger sizes increased presence unmedicated comorbidity. subgroup meta-analysis ten disorder studies, D showed decreased presence. When only two significantly A medium E (one study). more are needed elucidate whether findings diagnostic-specific markers. Results discussed relation functional meaning contribution an explanatory mechanism overlapping symptomatology

Language: Английский

Citations

14
Automated Detection of Neurological and Mental Health Disorders Using EEG Signals and Artificial Intelligence: A Systematic Review DOI Creative Commons
Hakan Uyanık, Abdulkadir Sengur, Massimo Salvi

et al.

Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 1, 2025

ABSTRACT Mental and neurological disorders significantly impact global health. This systematic review examines the use of artificial intelligence (AI) techniques to automatically detect these conditions using electroencephalography (EEG) signals. Guided by Preferred Reporting Items for Systematic Reviews Meta‐Analysis (PRISMA), we reviewed 74 carefully selected studies published between 2013 August 2024 that used machine learning (ML), deep (DL), or both two methods mental health EEG The most common prevalent disorder types were sourced from major databases, including Scopus, Web Science, Science Direct, PubMed, IEEE Xplore. Epilepsy, depression, Alzheimer's disease are studied meet our evaluation criteria, 32, 12, 10 identified on topics, respectively. Conversely, number meeting criteria regarding stress, schizophrenia, Parkinson's disease, autism spectrum was relatively more average: 6, 4, 3, diseases least met one study each seizure, stroke, anxiety diseases, examining epilepsy together. Support Vector Machines (SVM) widely in ML methods, while Convolutional Neural Networks (CNNs) dominated DL approaches. generally outperformed traditional ML, as they yielded higher performance huge data. We observed complex decision process during feature extraction signals ML‐based models impacted results, DL‐based handled this efficiently. AI‐based analysis shows promise automated detection conditions. Future research should focus multi‐disease studies, standardizing datasets, improving model interpretability, developing clinical support systems assist diagnosis treatment disorders.

Language: Английский

Citations

0
The Role of Testosterone in Modulating Positive and Negative Empathy in Social Interactions DOI

Shiwei Zhuo,

Yinhua Zhang,

Chennan Lin

et al.

Neuropharmacology, Journal Year: 2025, Volume and Issue: unknown, P. 110465 - 110465

Published: April 1, 2025

Language: Английский

Citations

0
Systematic review of machine learning in PTSD studies for automated diagnosis evaluation DOI Creative Commons
Yuqi Wu, Kaining Mao, Liz Dennett

et al.

npj Mental Health Research, Journal Year: 2023, Volume and Issue: 2(1)

Published: Sept. 27, 2023

Abstract Post-traumatic stress disorder (PTSD) is frequently underdiagnosed due to its clinical and biological heterogeneity. Worldwide, many people face barriers accessing accurate timely diagnoses. Machine learning (ML) techniques have been utilized for early assessments outcome prediction address these challenges. This paper aims conduct a systematic review investigate if ML promising approach PTSD diagnosis. In this review, statistical methods were employed synthesize the outcomes of included research provide guidance on critical considerations task implementation. These (a) selection most appropriate model available dataset, (b) identification optimal features based chosen diagnostic method, (c) determination sample size distribution data, (d) implementation suitable validation tools assess performance selected models. We screened 3186 studies 41 articles eligibility criteria in final synthesis. Here we report that analysis highlights potential artificial intelligence (AI) However, implementing AI-based systems real settings requires addressing several limitations, including regulation, ethical considerations, protection patient privacy.

Language: Английский

Citations

8
Machine learning-based identification of a psychotherapy-predictive electroencephalographic signature in PTSD DOI
Yu Zhang, Sharon Naparstek,

Joseph R. Gordon

et al.

Nature Mental Health, Journal Year: 2023, Volume and Issue: 1(4), P. 284 - 294

Published: April 18, 2023

Language: Английский

Citations

7
Altered EEG Patterns in Individuals with Disorganized Attachment: An EEG Microstates Study DOI
Giuseppe Alessio Carbone, Christoph M. Michel, Benedetto Farina

et al.

Brain Topography, Journal Year: 2024, Volume and Issue: 37(3), P. 420 - 431

Published: Feb. 28, 2024

Language: Английский

Citations

2
A biomarker of brain arousal mediates the intergenerational link between maternal and child post-traumatic stress disorder DOI Creative Commons
Marie‐Pierre Deiber,

Virginie C. Pointet Perizzolo,

Dominik A. Moser

et al.

Journal of Psychiatric Research, Journal Year: 2024, Volume and Issue: 177, P. 305 - 313

Published: July 23, 2024

This study examined whether there is a biological basis in the child's resting brain activity for intergenerational link between maternal interpersonal violence-related posttraumatic stress disorder (IPV-PTSD) and child subclinical symptoms. We used high-density EEG recordings to investigate sample of 57 children, 34 from mothers with IPV-PTSD, 23 without PTSD. These children were part prospective, longitudinal focusing on offspring reporting how severity mother's IPV-PTSD can impact her emotional regulation risk developing mental illness. However, we had not yet looked into potential biomarkers during state that might mediate and/or moderate effects health, particular The alpha band spectral power as well aperiodic exponent spectrum (PLE; power-law exponent) mediators While was no difference two groups, PLE significantly reduced compared control indicating cortical hyper-arousal. Interestingly, negatively correlated suggesting an interaction. interpretation reinforced by negative correlation PTSD Finally, causal analyses using structural equation modelling indicated mediated relationship Our observations suggest has neurobehavioral development through abnormal marker arousal (i.e. PLE). findings are potentially relevant psychotherapy research more effective psycho-neurobehavioral therapies neurofeedback) among affected individuals.

Language: Английский

Citations

1
Resting-state EEG functional connectivity predicts post-traumatic stress disorder subtypes in veterans DOI Creative Commons
Qianliang Li,

Maya Coulson Theodorsen,

Ivana Konvalinka

et al.

Journal of Neural Engineering, Journal Year: 2022, Volume and Issue: 19(6), P. 066005 - 066005

Published: Oct. 17, 2022

Objective. Post-traumatic stress disorder (PTSD) is highly heterogeneous, and identification of quantifiable biomarkers that could pave the way for targeted treatment remains a challenge. Most previous electroencephalography (EEG) studies on PTSD have been limited to specific handpicked features, their findings variable inconsistent. Therefore, disentangle role promising EEG biomarkers, we developed machine learning framework investigate wide range commonly used in order identify which features or combinations are capable characterizing potential subtypes.Approach. We recorded 5 min eyes-closed eyes-open resting-state from 202 combat-exposed veterans (53% with probable 47% controls). Multiple spectral, temporal, connectivity were computed logistic regression, random forest, support vector machines feature selection methods employed classify PTSD. To obtain robust results, performed repeated two-layer cross-validation test an entirely unseen set.Main results. Our classifiers obtained balanced accuracy up 62.9% predicting patients. In addition, identified two subtypes within PTSD: one where patterns similar those controls, another characterized by increased global functional connectivity. classifier 79.4% when classifying this subtype clear improvement compared whole group. Interestingly, alpha dorsal ventral attention network was particularly important prediction, these connections positively correlated arousal symptom scores, central cluster PTSD.Significance. Taken together, novel presented here demonstrates how unsupervised subtyping can delineate heterogeneity improve prediction PTSD, may better biomarkers.

Language: Английский

Citations

7