Predictive Modeling for Autism Spectrum Disorder: Leveraging Machine Learning Algorithms to Assess Likelihood from Multifactorial Features DOI
Praveen Kumar,

Rahul Dwedi,

Mohd Izhab Alam

et al.

Published: Nov. 23, 2023

This work proposed predictive modeling approach for Autism Spectrum Disorder (ASD) assessment, employing machine learning algorithms to analyze multifactorial features. Utilizing a diverse dataset that includes demographic, behavioral, and clinical information, our models aim predict the likelihood of ASD. The chosen evaluation metric is Area Under Receiver Operating Characteristic Curve (AUC-ROC Score), ensuring robust model performance assessment. Through rigorous experimentation, we demonstrate effectiveness methodology in accurately identifying individuals at risk research contributes advancing early detection methods enhancing understanding intricate interplay features influencing ASD, laying groundwork more informed diagnostic strategies.

Language: Английский

Digital Companionship or Psychological Risk? The Role of AI Characters in Shaping Youth Mental Health DOI
Ritesh Bhat, Suhas Kowshik,

S. Suresh

et al.

Asian Journal of Psychiatry, Journal Year: 2025, Volume and Issue: 104, P. 104356 - 104356

Published: Jan. 1, 2025

Language: Английский

Citations

1
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

1
Digital and AI-Enhanced Cognitive Behavioral Therapy for Insomnia: Neurocognitive Mechanisms and Clinical Outcomes DOI Open Access
Evgenia Gkintoni, Stephanos P. Vassilopoulos, Γεώργιος Νικολάου

et al.

Journal of Clinical Medicine, Journal Year: 2025, Volume and Issue: 14(7), P. 2265 - 2265

Published: March 26, 2025

Background/Objectives: This systematic review explores the integration of digital and AI-enhanced cognitive behavioral therapy (CBT) for insomnia, focusing on underlying neurocognitive mechanisms associated clinical outcomes. Insomnia significantly impairs functioning, overall health, quality life. Although traditional CBT has demonstrated efficacy, its scalability ability to deliver individualized care remain limited. Emerging AI-driven interventions-including chatbots, mobile applications, web-based platforms-present innovative avenues delivering more accessible personalized insomnia treatments. Methods: Following PRISMA guidelines, this synthesized findings from 78 studies published between 2004 2024. A search was conducted across PubMed, Scopus, Web Science, PsycINFO. Studies were included based predefined criteria prioritizing randomized controlled trials (RCTs) high-quality empirical research that evaluated AI-augmented interventions targeting sleep disorders, particularly insomnia. Results: The suggest improves parameters, patient adherence, satisfaction, personalization in alignment with individual profiles. Moreover, these technologies address critical limitations conventional CBT, notably those related access scalability. AI-based tools appear especially promising optimizing treatment delivery adapting cognitive-behavioral patterns. Conclusions: While demonstrates strong potential advancing through broader accessibility, several challenges persist. These include uncertainties surrounding long-term practical implementation barriers, ethical considerations. Future large-scale longitudinal is necessary confirm sustained benefits AI-powered

Language: Английский

Citations

1
Individualized prediction models in ADHD: a systematic review and meta-regression DOI Creative Commons
Gonzalo Salazar de Pablo,

Raquel Iniesta,

Alessio Bellato

et al.

Molecular Psychiatry, Journal Year: 2024, Volume and Issue: 29(12), P. 3865 - 3873

Published: May 23, 2024

Abstract There have been increasing efforts to develop prediction models supporting personalised detection, prediction, or treatment of ADHD. We overviewed the current status science in ADHD by: (1) systematically reviewing and appraising available models; (2) quantitatively assessing factors impacting performance published models. did a PRISMA/CHARMS/TRIPOD-compliant systematic review (PROSPERO: CRD42023387502), searching, until 20/12/2023, studies reporting internally and/or externally validated diagnostic/prognostic/treatment-response Using meta-regressions, we explored impact affecting area under curve (AUC) assessed study risk bias with Prediction Model Risk Bias Assessment Tool (PROBAST). From 7764 identified records, 100 were included (88% diagnostic, 5% prognostic, 7% treatment-response). Of these, 96% validated, respectively. None was implemented clinical practice. Only 8% deemed at low bias; 67% considered high bias. Clinical, neuroimaging, cognitive predictors used 35%, 31%, 27% studies, The increased those including, compared not (β = 6.54, p 0.007). Type validation, age range, type model, number predictors, quality, other alter AUC. Several developed support diagnosis However, predict outcomes response limited, none is ready for implementation into use which may be combined seems improve A new generation research should address these gaps by conducting replicable, models, followed research.

Language: Английский

Citations

7
Maximum and Minimum Activity in Inpatient Adolescents with Bipolar Disorders: Daily-Variability Classification of Actigraphy Pattern with Artificial Intelligence DOI Creative Commons
Farzan Vahedifard, Boris Birmaher, Satish Iyengar

et al.

Psychiatry Research Communications, Journal Year: 2025, Volume and Issue: unknown, P. 100212 - 100212

Published: April 1, 2025

Language: Английский

Citations

0
Longitudinal Prediction of Mental Health Outcomes in Vulnerable Youth using Machine Learning DOI
Esmeralda Ruiz Pujadas, Covadonga M. Díaz‐Caneja, Dejan Stevanović

et al.

Published: May 13, 2025

Abstract Mental illnesses affect almost 15% of the world's population, with half cases emerging before age 14. Improved methods for predicting progression mental distress among adolescents, particularly in vulnerable populations, are needed. This study utilized traditional machine learning techniques to predict health status at 17. We assessed correlates outcomes a sample 632 adolescents general (i.e., total difficulties score 17 or higher) 11, who participated UK Millennium Cohort Study. was best predicted using Balanced Random Forest model (AUC 0.75). Explainability enabled identification several critical factors, such as school environment, emotional distress, sleep patterns, patience, and social network ages 11 14, which were able differentiate participants poor good Individuals experiencing persistent between most likely suffer from unhappiness academic struggles. Our results point potentially modifiable factors associated high risk. These could pave way improved early intervention preventive strategies young people during adolescence.

Language: Английский

Citations

0
The Dynamic Interplay Between Puberty and Structural Brain Development as a Predictor of Mental Health Difficulties in Adolescence: A Systematic Review DOI

Svenja Kretzer,

Andrew J. Lawrence, Rebecca Pollard

et al.

Biological Psychiatry, Journal Year: 2024, Volume and Issue: 96(7), P. 585 - 603

Published: June 24, 2024

Language: Английский

Citations

2
Machine learning for anxiety and depression profiling and risk assessment in the aftermath of an emergency DOI Creative Commons

Guillermo Villanueva Benito,

Ximena Goldberg, Nicolai Brachowicz

et al.

Artificial Intelligence in Medicine, Journal Year: 2024, Volume and Issue: 157, P. 102991 - 102991

Published: Sept. 30, 2024

Language: Английский

Citations

2
Prediction of Junior High School Students’ Problematic Internet Use: The Comparison of Neural Network Models and Linear Mixed Models in Longitudinal Study DOI Creative Commons
Mei Tian,

Qiulian Xing,

Xiao Wang

et al.

Psychology Research and Behavior Management, Journal Year: 2024, Volume and Issue: Volume 17, P. 1191 - 1203

Published: March 1, 2024

Purpose: With the rise of big data, deep learning neural networks have garnered attention from psychology researchers due to their ability process vast amounts data and achieve superior model fitting.We aim explore predictive accuracy network models linear mixed in tracking when subjective variables are predominant field psychology.We separately analyzed both conduct a comparative study further investigate.Simultaneously, we utilized examine influencing factors problematic internet usage its temporal changes, attempting provide insights for early interventions use.Patients Methods: This compared longitudinal junior high school students using ascertain efficacy these two methods processing psychological data. Results:The exhibited significantly smaller errors model.Furthermore, outcomes revealed that, analyzing single time point, influences seventh grade better predicted Problematic Internet Use ninth grade.And multiple points, sixth, seventh, eighth grades more accurately grade. Conclusion:Neural surpass precision predicting data.Furthermore, lower accurate predictions higher grades.The highest prediction is attained through utilization points.

Language: Английский

Citations

1
The Power Threat Meaning Framework: a qualitative study of depression in adolescents and young adults DOI Creative Commons
Erik Ekbäck, Lina Rådmark, Jenny Molin

et al.

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

Published: May 1, 2024

Introduction Depression constitutes one of our largest global health concerns and current treatment strategies lack convincing evidence effectiveness in youth. We suggest that this is partly due to inherent limitations the present diagnostic paradigm may group fundamentally different conditions together without sufficient consideration etiology, developmental aspects, or context. Alternatives complement system are available yet understudied. The Power Threat Meaning Framework (PTMF) option, developed for explanatory practical purposes. While based on scientific evidence, empirical research framework itself still lacking. This qualitative study was performed explore experiences adolescents young adults with depression from perspective PTMF. Methods conducted semi-structured interviews 11 Swedish individuals aged 15– 22 years, mainly female, currently enrolled a clinical trial major depressive disorder. Interviews were transcribed verbatim analyzed analysis informed by Results A complex multitude adversities preceding onset described, rich variety effects, interpretations, reactions. In total, 17 themes identified four dimensions PTMF, highlighting power Not all participants able formulate coherent narratives. Discussion PTMF provides understanding complexities, common themes, lived depression. be essential development new interventions increased precision young.

Language: Английский

Citations

1