Automatic screening for posttraumatic stress disorder in early adolescents following the Ya’an earthquake using text mining techniques DOI Creative Commons
Yuan Yu, Zhiyuan Liu, Wei Miao

et al.

Frontiers in Psychiatry, Journal Year: 2024, Volume and Issue: 15

Published: Dec. 11, 2024

Background Self-narratives about traumatic experiences and symptoms are informative for early identification of potential patients; however, their use in clinical screening is limited. This study aimed to develop an automated method that analyzes self-narratives adolescent earthquake survivors screen PTSD a timely effective manner. Methods An inquiry-based questionnaire consisting series open-ended questions trauma history psychological symptoms, was designed simulate the structured interviews based on DSM-5 diagnostic criteria, used collect from 430 who experienced Ya’an Sichuan Province, China. Meanwhile, participants completed Checklist (PCL-5). Text classification models were constructed using three supervised learning algorithms (BERT, SVM, KNN) identify corresponding behavioral indicators each sentence self-narratives. Results The prediction accuracy symptom-level reached 73.2%, 67.2% indicator classification, with BERT performing best. Conclusions These findings demonstrate combined text mining techniques provide promising approach automated, rapid, accurate screening. Moreover, by conducting screenings community school settings, this equips clinicians psychiatrists evidence associated indicators, improving effectiveness detection treatment planning.

Language: Английский

From Lab to Real-Life: A Three-Stage Validation of Wearable Technology for Stress Monitoring DOI Creative Commons
Basil A. Darwish, Shafiq Ul Rehman, Ibrahim Sadek

et al.

MethodsX, Journal Year: 2025, Volume and Issue: 14, P. 103205 - 103205

Published: Feb. 5, 2025

Stress negatively impacts health, contributing to hypertension, cardiovascular diseases, and immune dysfunction. While conventional diagnostic methods, such as self-reported questionnaires basic physiological measurements, often lack the objectivity precision needed for effective stress management, wearable devices present a promising avenue early detection management. This study conducts three-stage validation of technology monitoring, transitioning from controlled experimental data real-life scenarios. Using WESAD dataset, binary five-class classification models were developed, achieving maximum accuracies 99.78 %±0.15 % 99.61 %±0.32 %, respectively. Electrocardiogram (ECG), Electrodermal Activity (EDA), Respiration (RESP) identified reliable biomarkers. Validation was extended SWEET representing data, confirm generalizability practical applicability. Furthermore, commercially available wearables supporting these modalities reviewed, providing recommendations optimal configurations in dynamic, real-world conditions. These findings demonstrate potential multimodal bridge gap between studies applications, advancing systems personalized management strategies.•Stress methods validated using (WESAD) (SWEET) datasets.•Commercial technologies offering insights into their applicability monitoring.

Language: Английский

Citations

0
Assessment of PTSD in military personnel via machine learning based on physiological habituation in a virtual immersive environment DOI Creative Commons

Gauthier Pellegrin,

Nicolas Ricka,

Denis A. Fompeyrine

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 4, 2025

Posttraumatic stress disorder (PTSD) is a complex mental health condition triggered by exposure to traumatic events that leads physical problems and socioeconomic impairments. Although the symptomatology of PTSD makes diagnosis difficult, early identification intervention are crucial mitigate long-term effects provide appropriate treatment. In this study, we explored potential for physiological habituation stressful predict status. We used passive data collected from 21 active-duty United States military personnel veterans in an immersive virtual environment with high-stress combat-related conditions involving trigger such as explosions or flashbangs. our work, proposed quantitative measure can be quantitatively estimated through heart rate, galvanic skin response eye blinking. Using Gaussian process classifier, prove predictor status, measured via Checklist Military version (PCL-M). Our algorithm achieved accuracy 80.95% across cohort. These findings suggest passively may noninvasive objective method identify individuals PTSD. markers could improve both detection treatment

Language: Английский

Citations

0
The role of attachment styles in post-traumatic stress disorder and posttraumatic growth in the Shidu parents of China DOI Creative Commons
Zhilei Shang, Na Zhou,

Buhang Xu

et al.

SAGE Open Medicine, Journal Year: 2025, Volume and Issue: 13

Published: March 1, 2025

Background: The number of Shidu parents in China is significant and expected to continue increasing. psychological status deserves more attention. Objective: Our objective investigate the impact post-traumatic stress disorder attachment styles among on growth, with aim providing valuable insights for alleviating symptoms enhancing levels growth following trauma. Design: Demographic data, Revised Adult Attachment Scale, Posttraumatic Stress Disorder Checklist DSM-5, post traumatic inventory were used investigated 297 parents. Method: Two samples t -test was employed evaluate disparities scores based diverse styles. Pearson’s correlation analysis association between Post-traumatic DSM-5 scores, as well different scores. We performed multiple mediator analyses further confirm influence inventory. Results: (1) A total 35% people tested positive disorder; (2) 56.9% participants exhibited secure attachment, while 43.1% insecure attachment; (3) results unveiled a substantial negative scores; (4) evident relation dependence/closeness inventory, established anxiety Conclusion: study suggests that associated It might offer new into influencing through intervention.

Language: Английский

Citations

0
Artificial intelligence in psychiatry: A systematic review and meta-analysis of diagnostic and therapeutic efficacy DOI Creative Commons
Moustaq Karim Khan Rony, Dipak Chandra Das,

Most. Tahmina Khatun

et al.

Digital Health, Journal Year: 2025, Volume and Issue: 11

Published: March 1, 2025

Artificial Intelligence (AI) has demonstrated significant potential in transforming psychiatric care by enhancing diagnostic accuracy and therapeutic interventions. Psychiatry faces challenges like overlapping symptoms, subjective methods, personalized treatment requirements. AI, with its advanced data-processing capabilities, offers innovative solutions to these complexities. This study systematically reviewed meta-analyzed the existing literature evaluate AI's efficacy care, focusing on various disorders AI technologies. Adhering PRISMA guidelines, included a comprehensive search across multiple databases. Empirical studies investigating applications psychiatry, such as machine learning (ML), deep (DL), hybrid models, were selected based predefined inclusion criteria. The outcomes of interest efficacy. Statistical analysis employed fixed- random-effects subgroup sensitivity analyses exploring impact methodologies designs. A total 14 met criteria, representing diverse diagnosing treating disorders. pooled was 85% (95% CI: 80%-87%), ML models achieving highest accuracy, followed DL models. For efficacy, effect size 84% 82%-86%), excelling plans symptom tracking. Moderate heterogeneity observed, reflecting variability designs populations. risk bias assessment indicated high methodological rigor most studies, though algorithmic biases data quality remain. demonstrates robust capabilities offering data-driven approach mental healthcare. Future research should address ethical concerns, standardize methodologies, explore underrepresented populations maximize transformative health.

Language: Английский

Citations

0
Attention bias variability as a cognitive marker of PTSD: A comparison of eye-tracking and reaction time methodologies DOI

Tal Lev,

Chelsea Dyan Gober Dykan,

Amit Lazarov

et al.

Journal of Affective Disorders, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Current Status and Future Directions of Artificial Intelligence in Post-Traumatic Stress Disorder: A Literature Measurement Analysis DOI Creative Commons

Ruoyu Wan,

Ruohong Wan,

Qing Xie

et al.

Behavioral Sciences, Journal Year: 2024, Volume and Issue: 15(1), P. 27 - 27

Published: Dec. 30, 2024

This study aims to explore the current state of research and applicability artificial intelligence (AI) at various stages post-traumatic stress disorder (PTSD), including prevention, diagnosis, treatment, patient self-management, drug development. We conducted a bibliometric analysis using software tools such as Bibliometrix (version 4.1), VOSviewer 1.6.19), CiteSpace 6.3.R1) on relevant literature from Web Science Core Collection (WoSCC). The reveals significant increase in publications since 2017. Kerry J. Ressler has emerged most influential author field date. United States leads number publications, producing seven times more papers than Canada, second-ranked country, demonstrating substantial influence. Harvard University Veterans Health Administration are also key institutions this field. Journal Affective Disorders highest impact area. In recent years, keywords related functional connectivity, risk factors, algorithm development have gained prominence. holds immense potential, with AI poised revolutionize PTSD management through early symptom detection, personalized treatment plans, continuous monitoring. However, there numerous challenges, fully realizing AI's potential will require overcoming hurdles design, data integration, societal ethics. To promote extensive in-depth future research, it is crucial prioritize standardized protocols for implementation, foster interdisciplinary collaboration-especially between neuroscience-and address public concerns about role healthcare enhance its acceptance effectiveness.

Language: Английский

Citations

1
Evaluating the Potential of Wearable Technology in Early Stress Detection: A Multimodal Approach DOI
Basil A. Darwish, Nancy M. Salem,

Ghada Kareem

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: July 21, 2024

Abstract Stress can adversely impact health, leading to issues like high blood pressure, heart diseases, and a compromised immune system. Consequently, using wearable devices monitor stress is essential for prompt intervention effective management. This study investigates the efficacy of in early detection psychological stress, employing both binary five-class classification models. Significant correlations were observed between levels physiological signals, including Electrocardiogram (ECG), Electrodermal Activity (EDA), Respiration (RESP), establishing these modalities as reliable biomarkers detection. Utilizing publicly available Wearable Affect Detection (WESAD) dataset, we employed two ensemble methods, Majority Voting (MV) Weighted Averaging (WA), integrate achieving maximum accuracies 99.96% 99.59% classification. integration significantly enhances accuracy robustness Furthermore, ten different classifiers evaluated, hyperparameter optimization K-fold cross-validation ranging from 3-fold 10-fold applied. Both time-domain frequency-domain features examined separately. A review commercially supporting was also conducted, resulting recommendations optimal configurations practical applications. Our findings highlight potential multimodal advancing continuous monitoring with significant implications future research development improved systems.

Language: Английский

Citations

0
Evaluating the Potential of Wearable Technology in Early Stress Detection: A Multimodal Approach DOI Creative Commons
Basil A. Darwish, Nancy M. Salem,

Ghada Kareem

et al.

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

Published: Aug. 21, 2024

Abstract Stress can adversely impact health, leading to issues like high blood pressure, heart diseases, and a compromised immune system. Monitoring stress with wearable devices is crucial for timely intervention management. This study examines the efficacy of in early detection using binary five-class classification models. Significant correlations between levels physiological signals, including Electrocardiogram (ECG), Electrodermal Activity (EDA), Respiration (RESP), were found, validating these signals as reliable biomarkers. Utilizing WESAD dataset, we applied ensemble methods, Majority Voting (MV) Weighted Averaging (WA), achieving maximum accuracies 99.96% 99.59% classification. Ten classifiers evaluated, hyperparameter optimization 3 10 fold cross-validation applied. Time frequency domain features analyzed separately. We reviewed commercially available wearables supporting modalities provided recommendations optimal configurations practical applications. Our findings demonstrate potential multimodal continuous monitoring psychological stress, suggesting significant implications future research development improved systems.

Language: Английский

Citations

0
Predicting the Risk of Loneliness in Children and Adolescents: A Machine Learning Study DOI Creative Commons
Jilei Zhang,

Xinyi Feng,

Wenhe Wang

et al.

Behavioral Sciences, Journal Year: 2024, Volume and Issue: 14(10), P. 947 - 947

Published: Oct. 15, 2024

Loneliness is increasingly emerging as a significant public health problem in children and adolescents. Predicting loneliness finding its risk factors adolescents lacking necessary, would greatly help determine intervention actions.

Language: Английский

Citations

0
Machine learning-based identification and validation of immune-related biomarkers for early diagnosis and targeted therapy in diabetic retinopathy DOI

Yulin Tao,

Minqi Xiong,

Yingchuan Peng

et al.

Gene, Journal Year: 2024, Volume and Issue: 934, P. 149015 - 149015

Published: Oct. 18, 2024

Language: Английский

Citations

0