{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T21:14:27Z","timestamp":1788815667240,"version":"build-2803163510"},"reference-count":57,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Artificial intelligence (AI) models have been increasingly explored for predicting treatment response to cognitive behavioral therapy (CBT) in patients with anxiety disorders. Identifying potential responders in advance may help inform treatment planning and support clinical decision-making. Although a growing number of studies have applied AI techniques in this context, reported performance estimates vary across studies, and the overall predictive accuracy has not been comprehensively quantified.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This systematic review and meta-analysis aims to quantify the overall performance of AI models in predicting treatment response following CBT for anxiety disorders and to examine how data sources, algorithmic approaches, and diagnostic subtypes influence predictive performance.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A systematic literature search was conducted in PubMed, Embase, Web of Science, Cochrane Library, and PsycINFO up to August 2025. We included studies that validated AI models for predicting CBT treatment response (remission or response) in patients diagnosed with an anxiety disorder. The risk of bias was assessed using the PROBAST+AI (Prediction Model Risk of Bias Assessment Tool for Artificial Intelligence) tool. Predictive performance metrics, including sensitivity, specificity, accuracy, and area under the curve (AUC), were extracted and pooled. Pooled estimates for sensitivity, specificity, and diagnostic accuracy were derived using the Restricted Maximum Likelihood estimator, with CIs adjusted via the Hartung-Knapp-Sidik-Jonkman method. Prediction intervals were calculated and reported alongside these pooled estimates to illustrate the expected distribution of effects in real-world settings.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Eleven studies were included in the meta-analysis. The pooled sensitivity of AI-based models for predicting treatment response was 0.73 (95% CI 0.58\u20100.85;\n I<\/jats:italic>\n \u00b2=82.8%), and the pooled specificity was 0.75 (95% CI 0.59\u20100.89;\n I<\/jats:italic>\n \u00b2=96.7%). The overall pooled accuracy was 0.74 (95% CI 0.62\u20100.84;\n I<\/jats:italic>\n \u00b2=94.6%). The summary AUC was 0.81 (95% CI 0.78\u20100.85), indicating moderate discriminative performance. Subgroup analyses showed that models incorporating multimodal data achieved superior predictive performance, with a pooled sensitivity of 0.84 and an accuracy of 0.82. In addition, predictive performance was the highest in patients with social anxiety disorder compared with other anxiety disorder subtypes.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This meta-analysis quantitatively synthesized AI performance in predicting CBT response for anxiety disorders, moving beyond narrative reviews to provide pooled evidence. In contrast to existing reviews that encompass broader diagnostic groups, our focused approach establishes a precise benchmark for this clinical domain, highlighting the current moderate overall performance. Furthermore, we extend beyond previous work by demonstrating the superior predictive utility of multimodal data, identifying social anxiety disorder as the most predictable subtype, and systematically evaluating the impact of data modalities and algorithm types. Future efforts should prioritize robustly validated multimodal models, laying essential groundwork for the potential development of AI-assisted tools to personalize treatment planning in anxiety disorders.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/86079","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T06:55:06Z","timestamp":1771916106000},"page":"e86079-e86079","source":"Crossref","is-referenced-by-count":1,"title":["Artificial Intelligence for Predicting Treatment Response in Patients With Anxiety Disorders After Cognitive Behavioral Therapy: Systematic Review and Meta-Analysis"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2833-670X","authenticated-orcid":false,"given":"Jiawen","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8928-1369","authenticated-orcid":false,"given":"Junhui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2813-0590","authenticated-orcid":false,"given":"Zhaobin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8836-9042","authenticated-orcid":false,"given":"Mohamad Ibrani Shahrimin Bin","family":"Adam Assim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-023-04581-7","article-title":"Prevalence and economic burden of depression and anxiety symptoms among Singaporean adults: results from a 2022 web panel","volume":"23","author":"Chodavadia","journal-title":"BMC Psychiatry"},{"issue":"8","key":"R2","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1007\/s10198-025-01764-9","article-title":"Psychological distress and productivity loss: a longitudinal analysis of Australian working adults","volume":"26","author":"Keramat","journal-title":"Eur J Health Econ"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-023-05306-6","article-title":"A meta-analysis on the efficacy of low-intensity cognitive behavioural therapy for generalised anxiety disorder","volume":"24","author":"Powell","journal-title":"BMC Psychiatry"},{"issue":"3","key":"R4","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1001\/jamapsychiatry.2023.3971","article-title":"Psychotherapies for generalized anxiety disorder in adults: a systematic review and network meta-analysis of randomized clinical trials","volume":"81","author":"Papola","journal-title":"JAMA Psychiatry"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-025-07012-x","article-title":"Clinical, genetic, and sociodemographic predictors of symptom severity after internet-delivered cognitive behavioural therapy for depression and anxiety","volume":"25","author":"Kravchenko","journal-title":"BMC Psychiatry"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00677-8","article-title":"A systematic review of digital and face-to-face cognitive behavioral therapy for depression","volume":"5","author":"Kambeitz-Ilankovic","journal-title":"NPJ Digit Med"},{"issue":"3","key":"R7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0313351","article-title":"Predicting treatment response to cognitive behavior therapy in social anxiety disorder on the basis of demographics, psychiatric history, and scales: a machine learning approach","volume":"20","author":"Bukhari","journal-title":"PLoS ONE"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.1186\/s40359-024-01688-8","article-title":"Psychometric properties of the GAD-7 (General Anxiety Disorder-7): a cross-sectional study of the Peruvian general population","volume":"12","author":"Villarreal-Zegarra","journal-title":"BMC Psychol"},{"issue":"5","key":"R9","doi-asserted-by":"publisher","DOI":"10.1192\/bjo.2025.10055","article-title":"Hamilton Rating Scale for Anxiety: exploring validity with robust measures of classical theory parameters and a rating scale model in university students","volume":"11","author":"Manzar","journal-title":"BJPsych Open"},{"issue":"5","key":"R10","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1089\/cap.2021.0111","article-title":"A characterization of the Clinical Global Impression Scale thresholds in the treatment of adolescent depression across multiple rating scales","volume":"32","author":"Zhang","journal-title":"J Child Adolesc Psychopharmacol"},{"issue":"2","key":"R11","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s11126-023-10022-1","article-title":"Evaluating the use of online self-report questionnaires as clinically valid mental health monitoring tools in the clinical whitespace","volume":"94","author":"Arrow","journal-title":"Psychiatr Q"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-025-06754-y","article-title":"Poor performance of PHQ-9 and GAD-7 in screening clinical depression and anxiety among a large sample of Chinese children and adolescents","volume":"25","author":"Wang","journal-title":"BMC Psychiatry"},{"issue":"12","key":"R13","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1111\/jcpp.14009","article-title":"Patterns of sub-optimal change following CBT for childhood anxiety","volume":"65","author":"Bertie","journal-title":"J Child Psychol Psychiatry"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2024.1504190","article-title":"Machine learning prediction of anxiety symptoms in social anxiety disorder: utilizing multimodal data from virtual reality sessions","volume":"15","author":"Park","journal-title":"Front Psychiatry"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.2196\/46781","article-title":"Effects of an artificial intelligence platform for behavioral interventions on depression and anxiety symptoms: randomized clinical trial","volume":"25","author":"Sadeh-Sharvit","journal-title":"J Med Internet Res"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.2196\/60435","article-title":"Generative AI-enabled therapy support tool for improved clinical outcomes and patient engagement in group therapy: real-world observational study","volume":"27","author":"Habicht","journal-title":"J Med Internet Res"},{"issue":"11","key":"R17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0272685","article-title":"Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety","volume":"18","author":"Prasad","journal-title":"PLoS ONE"},{"issue":"120639","key":"R18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2024.120639","article-title":"Lack of evidence for predictive utility from resting state fMRI data for individual exposure-based cognitive behavioral therapy outcomes: a machine learning study in two large multi-site samples in anxiety disorders","volume":"295","author":"Hilbert","journal-title":"Neuroimage"},{"issue":"10","key":"R19","doi-asserted-by":"publisher","first-page":"4928","DOI":"10.1038\/s41380-025-03155-1","article-title":"Clinical features and genetic mechanisms of anxiety, fear, and avoidance: a comprehensive review of five anxiety disorders","volume":"30","author":"Ohi","journal-title":"Mol Psychiatry"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1016\/j.janxdis.2025.102978","article-title":"Development of a machine learning-based multivariable prediction model for the naturalistic course of generalized anxiety disorder","volume":"110","author":"Basterfield","journal-title":"J Anxiety Disord"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291724003295","article-title":"Artificial intelligence in mental health care: a systematic review of diagnosis, monitoring, and intervention applications","volume":"55","author":"Cruz-Gonzalez","journal-title":"Psychol Med"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m2632","article-title":"Preferred reporting items for systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): explanation, elaboration, and checklist","volume":"370","author":"Salameh","journal-title":"BMJ"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-020-01542-z","article-title":"PRISMA-S: an extension to the PRISMA Statement for Reporting Literature Searches in Systematic Reviews","volume":"10","author":"Rethlefsen","journal-title":"Syst Rev"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2024-082505","article-title":"PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","journal-title":"BMJ"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-25","article-title":"The Hartung-Knapp-Sidik-Jonkman method for random effects meta-analysis is straightforward and considerably outperforms the standard DerSimonian-Laird method","volume":"14","author":"IntHout","journal-title":"BMC Med Res Methodol"},{"issue":"4","key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imr.2023.101014","article-title":"How to understand and report heterogeneity in a meta-analysis: the difference between I-squared and prediction intervals","volume":"12","author":"Borenstein","journal-title":"Integr Med Res"},{"issue":"5","key":"R27","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1038\/npp.2013.328","article-title":"Single-subject anxiety treatment outcome prediction using functional neuroimaging","volume":"39","author":"Ball","journal-title":"Neuropsychopharmacology"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291724002654","article-title":"Predicting remission following CBT for childhood anxiety disorders: a machine learning approach","volume":"17","author":"Bertie","journal-title":"Psychol Med"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2019.10.027","article-title":"Neuroimaging, genetic, clinical, and demographic predictors of treatment response in patients with social anxiety disorder","volume":"261","author":"Frick","journal-title":"J Affect Disord"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1001\/jamapsychiatry.2014.1741","article-title":"Predicting treatment response to cognitive behavioral therapy in panic disorder with agoraphobia by integrating local neural information","volume":"72","author":"Hahn","journal-title":"JAMA Psychiatry"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-024-00626-4","article-title":"Methodological choices and clinical usefulness for machine learning predictions of outcome in Internet-based cognitive behavioural therapy","volume":"4","author":"Hentati Isacsson","journal-title":"Commun Med (Lond)"},{"issue":"3","key":"R32","doi-asserted-by":"publisher","DOI":"10.1038\/tp.2015.22","article-title":"Predicting long-term outcome of Internet-delivered cognitive behavior therapy for social anxiety disorder using fMRI and support vector machine learning","volume":"5","author":"M\u00e5nsson","journal-title":"Transl Psychiatry"},{"key":"R33","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2017.00099","article-title":"Support vector machine analysis of functional magnetic resonance imaging of interoception does not reliably predict individual outcomes of cognitive behavioral therapy in panic disorder with agoraphobia","volume":"8","author":"Sundermann","journal-title":"Front Psychiatry"},{"issue":"5","key":"R34","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1038\/mp.2015.109","article-title":"Brain connectomics predict response to treatment in social anxiety disorder","volume":"21","author":"Whitfield-Gabrieli","journal-title":"Mol Psychiatry"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpr.2022.102193","article-title":"Can we predict who will benefit from cognitive-behavioural therapy? A systematic review and meta-analysis of machine learning studies","volume":"97","author":"Vieira","journal-title":"Clin Psychol Rev"},{"issue":"2","key":"R36","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1111\/bjc.12452","article-title":"Predicting treatment response using machine learning: a registered report","volume":"63","author":"Jankowsky","journal-title":"Br J Clin Psychol"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1177\/20552076211060659","article-title":"Predicting therapy outcome in a digital mental health intervention for depression and anxiety: a machine learning approach","volume":"7","author":"Hornstein","journal-title":"Digit Health"},{"issue":"2","key":"R38","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1002\/wps.20882","article-title":"The promise of machine learning in predicting treatment outcomes in psychiatry","volume":"20","author":"Chekroud","journal-title":"World Psychiatry"},{"issue":"3","key":"R39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009926","article-title":"The ability to classify patients based on gene-expression data varies by algorithm and performance metric","volume":"18","author":"Piccolo","journal-title":"PLoS Comput Biol"},{"key":"R40","doi-asserted-by":"publisher","DOI":"10.2196\/59505","article-title":"Multimodal large language models in health care: applications, challenges, and future outlook","volume":"26","author":"AlSaad","journal-title":"J Med Internet Res"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.e813","article-title":"Impact of single centre status on estimates of intervention effects in trials with continuous outcomes: meta-epidemiological study","volume":"344","author":"Bafeta","journal-title":"BMJ"},{"issue":"7","key":"R42","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD015456","article-title":"Hospital Anxiety and Depression Scale Anxiety subscale (HADS-A) for detecting anxiety disorders in adults","volume":"7","author":"Fomenko","journal-title":"Cochrane Database Syst Rev"},{"issue":"2","key":"R43","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1002\/wps.21088","article-title":"Therapist-supported Internet-based cognitive behaviour therapy yields similar effects as face-to-face therapy for psychiatric and somatic disorders: an updated systematic review and meta-analysis","volume":"22","author":"Hedman-Lagerl\u00f6f","journal-title":"World Psychiatry"},{"issue":"1","key":"R44","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-20655-6","article-title":"Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning","volume":"12","author":"Abrol","journal-title":"Nat Commun"},{"issue":"1","key":"R45","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-16615-3","article-title":"Prediction performance and fairness heterogeneity in cardiovascular risk models","volume":"12","author":"Kartoun","journal-title":"Sci Rep"},{"issue":"15","key":"R46","doi-asserted-by":"publisher","first-page":"3533","DOI":"10.1002\/sim.8981","article-title":"Developing more generalizable prediction models from pooled studies and large clustered data sets","volume":"40","author":"de Jong","journal-title":"Stat Med"},{"issue":"4","key":"R47","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3001627","article-title":"Population heterogeneity in clinical cohorts affects the predictive accuracy of brain imaging","volume":"20","author":"Benkarim","journal-title":"PLoS Biol"},{"issue":"2","key":"R48","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1111\/biom.13434","article-title":"Pursuing sources of heterogeneity in modeling clustered population","volume":"78","author":"Li","journal-title":"Biometrics"},{"issue":"1","key":"R49","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-023-04698-z","article-title":"Revolutionizing healthcare: the role of artificial intelligence in clinical practice","volume":"23","author":"Alowais","journal-title":"BMC Med Educ"},{"key":"R50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpbup.2024.100148","article-title":"Artificial intelligence for clinical prediction: exploring key domains and essential functions","volume":"5","author":"Khalifa","journal-title":"Computer Methods and Programs in Biomedicine Update"},{"issue":"8","key":"R51","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.1017\/S0033291723003537","article-title":"Select or adjust? How information from early treatment stages boosts the prediction of non-response in internet-based depression treatment","volume":"54","author":"Hammelrath","journal-title":"Psychol Med"},{"issue":"11","key":"R52","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1056\/NEJMp1714229","article-title":"Implementing machine learning in health care - addressing ethical challenges","volume":"378","author":"Char","journal-title":"N Engl J Med"},{"issue":"23s","key":"R53","doi-asserted-by":"publisher","first-page":"826","DOI":"10.64252\/mev1b885","article-title":"Advances in evidence-based interventions for depression and anxiety: implications for mental health nursing practice","volume":"11","author":"Tendolkar","journal-title":"Int J Environ Sci"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.2196\/75866","article-title":"AI-Supported Shared Decision-Making (AI-SDM): conceptual framework","volume":"4","author":"As\u2019ad","journal-title":"JMIR AI"},{"issue":"1","key":"R55","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3390\/info16010011","article-title":"An exploratory investigation of chatbot applications in anxiety management: a focus on personalized interventions","volume":"16","author":"Manole","journal-title":"Information"},{"key":"R56","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1435895","article-title":"A review on the efficacy of artificial intelligence for managing anxiety disorders","volume":"7","author":"Das","journal-title":"Front Artif Intell"},{"issue":"3","key":"R57","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240982","article-title":"Navigating the AI landscape in medical imaging: a critical analysis of technologies, implementation, and implications","volume":"315","author":"Sosna","journal-title":"Radiology"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e86079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:14:07Z","timestamp":1782839647000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e86079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":57,"URL":"https:\/\/doi.org\/10.2196\/86079","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"article-number":"v28i1e86079"}}