{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:15:29Z","timestamp":1774556129243,"version":"3.50.1"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate risk stratification in pulmonary hypertension (PH) is integral for optimizing therapeutic strategies and improving patient outcomes. Recent artificial intelligence (AI) models have demonstrated notable efficacy in risk stratification of PH, achieving area under the curve (AUC) values of 0.94 and 0.81 in internal and external validation cohorts, respectively. This meta-analysis aims to demonstrate the effectiveness of AI models in the risk stratification of PH by comparing their performance to conventional risk stratification methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A systematic search of five databases (PubMed, Embase, ScienceDirect, Scopus, and the Cochrane Library) was conducted from inception to March 2025. Statistical analysis was performed in R (version 2024.12.1\u202f+\u202f563) using 2\u202f\u00d7\u202f2 contingency data. Sensitivity, specificity, and diagnostic odds ratio (DOR) were pooled using a bivariate random-effects model (reitsma from the mada package), while the AUC was meta-analyzed using logit-transformed values via the metagen() function from the meta package.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Six studies were included in the final synthesis, comprising 14,095 patients: 4,481 in internal test datasets and 4,948 in external datasets. AI risk stratification models showed significant performance with a logit mean difference of 0.26 (95% CI 0.09\u20130.43;\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.31), having low heterogeneity (\n                      <jats:italic>I<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      \u202f=\u202f14.3%) as compared to conventional methods. Furthermore, pooled sensitivity and specificity were 0.77 (95% CI 0.74\u20130.79) and 0.72 (95% CI 0.70\u20130.75) in favor of AI methods, respectively. The heterogeneities for pooled sensitivity and specificity were 57.1% (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.04) and 91.8% (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.0001), underscoring high variability across all studies. Finally, DOR was substantially high, 8.53 (6.59\u201311.04) in favor of AI models with a high heterogeneity of 73.6% (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.002). Heterogeneity (I2) for pooled sensitivity went to 25.9% after excluding a major outlier, but it remained high for pooled specificity and DOR upon leave-one-out sensitivity analysis.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Artificial intelligence-based risk stratification demonstrates significantly higher diagnostic performance compared to conventional methods in pulmonary hypertension. The higher pooled AUC, sensitivity, specificity, and DOR highlight AI\u2019s potential to enhance predictive accuracy, guiding better treatment strategies. Nonetheless, more superior quality studies are needed to validate AI models for clinical integration.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1692829","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:58:11Z","timestamp":1763553491000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Comparative diagnostic accuracy of artificial intelligence-derived risk stratification versus conventional risk stratification methods in pulmonary hypertension patients: a systematic review and meta-analysis"],"prefix":"10.3389","volume":"8","author":[{"given":"Faizan","family":"Ahmed","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faseeh","family":"Haider","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Arham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allah","family":"Dad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kinza","family":"Bakht","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Moseeb Ali","family":"Hashim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pawe\u0142","family":"\u0141ajczak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatima Binte","family":"Athar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Adnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Usman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Najam","family":"Gohar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tehmasp","family":"Mirza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mushood","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Moshiyakhov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brett","family":"Sealove","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swapnil","family":"Patel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesus","family":"Almendral","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Bakr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasar","family":"Sattar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fawaz","family":"Alenezi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e12253","DOI":"10.1002\/pul2.12253","article-title":"Risk assessment in pulmonary arterial hypertension: a step towards clinical implementation based on the 2022 ESC\/ERS pulmonary hypertension guidelines","volume":"13","author":"Ahmed","year":"2023","journal-title":"Pulm Circ."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e46454","DOI":"10.7759\/cureus.46454","article-title":"A systematic review of the barriers to the implementation of artificial intelligence in healthcare","volume":"15","author":"Ahmed","year":"2023","journal-title":"Cureus."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3390\/medicina61010085","article-title":"A comprehensive review of artificial intelligence (AI) applications in pulmonary hypertension (PH)","volume":"61","author":"Attaripour Esfahani","year":"2025","journal-title":"Medicina"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.chest.2020.08.2069","article-title":"Development and validation of an abridged version of the REVEAL 2.0 risk score calculator, REVEAL lite 2, for use in patients with pulmonary arterial hypertension","volume":"159","author":"Benza","year":"2021","journal-title":"Chest"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"919224","DOI":"10.3389\/fcvm.2022.919224","article-title":"Explainable machine learning models for predicting 30-day readmission in pediatric pulmonary hypertension: a multicenter, retrospective study","volume":"9","author":"Duan","year":"2022","journal-title":"Front. Cardiovasc Med."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1422327","DOI":"10.3389\/fcvm.2024.1422327","article-title":"Assessing the precision of machine learning for diagnosing pulmonary arterial hypertension: a systematic review and meta-analysis of diagnostic accuracy studies","volume":"11","author":"Fadilah","year":"2024","journal-title":"Front. Cardiovasc Med."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"20210332","DOI":"10.1259\/bjr.20210332","article-title":"Diagnostic test accuracy of artificial intelligence analysis of cross-sectional imaging in pulmonary hypertension: a systematic literature review","volume":"94","author":"Hardacre","year":"2021","journal-title":"Br. J. Radiol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1186\/s12890-024-02891-4","article-title":"Artificial intelligence-based model for predicting pulmonary arterial hypertension on chest x-ray images","volume":"24","author":"Imai","year":"2024","journal-title":"BMC Pulm. Med."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2000008","DOI":"10.1183\/13993003.00008-2020","article-title":"Risk stratification in pulmonary arterial hypertension using Bayesian analysis","volume":"56","author":"Kanwar","year":"2020","journal-title":"Eur. Respir. J."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"00484","DOI":"10.1183\/23120541.00484-2022","article-title":"Computational platform for doctor-artificial intelligence cooperation in pulmonary arterial hypertension prognostication: a pilot study","volume":"9","author":"Kheyfets","year":"2023","journal-title":"ERJ Open Res."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1001\/jama.2017.19163","article-title":"Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement","volume":"319","author":"McInnes","year":"2018","journal-title":"JAMA"},{"key":"ref13","first-page":"107910","article-title":"Riociguat improves long-term outcomes and COMPERA 2.0 risk status in PAH","volume":"215","author":"McLaughlin","year":"2024","journal-title":"Respir. Med."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e0305949","DOI":"10.1371\/journal.pone.0305949","article-title":"A comprehensive overview of barriers and strategies for AI implementation in healthcare: mixed-method design","volume":"19","author":"Nair","year":"2024","journal-title":"PLoS One"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"2400","DOI":"10.3390\/jcm14072400","article-title":"Pulmonary hypertension: updates in diagnosis and management","volume":"14","author":"Oliveros","year":"2025","journal-title":"J. Clin. Med."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"00072","DOI":"10.1183\/23120541.00072-2023","article-title":"Residual risk identified in routine noninvasive follow-up assessments in pulmonary arterial hypertension","volume":"9","author":"Ostermann","year":"2023","journal-title":"ERJ Open Res."},{"key":"ref17","article-title":"CT-based AI model for lung fibrosis quantification predicts mortality in PAH","author":"Park","year":"2023","journal-title":"Radiology"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2301023","DOI":"10.1183\/13993003.01023-2023","article-title":"Performance of the ESC\/ERS 4-strata risk stratification model for pulmonary arterial hypertension with missing variables","volume":"62","author":"Pausch","year":"2023","journal-title":"The European respiratory journal"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"00592","DOI":"10.1183\/23120541.00592-2024","article-title":"Artificial intelligence-based echocardiography assessment to detect pulmonary hypertension","volume":"11","author":"Salehi","year":"2025","journal-title":"ERJ Open Res."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e2019007","DOI":"10.4178\/epih.e2019007","article-title":"Diagnostic test accuracy: application and practice using R software","volume":"41","author":"Shim","year":"2019","journal-title":"Epidemiol Health."},{"key":"ref20","first-page":"223","article-title":"Deep learning electrocardiogram model for detection of elevated pulmonary artery pressure","volume":"1","author":"Siontis","year":"2022","journal-title":"J Am Coll Cardiol AI."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e2245","DOI":"10.7717\/peerj-cs.2245","article-title":"Trade-off between training and testing ratio in machine learning for medical image processing","volume":"10","author":"Sivakumar","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1186\/s12890-023-02427-2","article-title":"The combination of supervised and unsupervised learning based risk stratification and phenotyping in pulmonary arterial hypertension\u2014a long-term retrospective multicenter trial","volume":"23","author":"Sonnweber","year":"2023","journal-title":"BMC Pulm. Med."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"4349","DOI":"10.3390\/jcm12134349","article-title":"Risk stratification in pulmonary arterial hypertension, update and perspectives","volume":"12","author":"Vraka","year":"2023","journal-title":"J. Clin. Med."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"Whiting","year":"2011","journal-title":"Ann. Intern. Med."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1967","DOI":"10.1109\/JBHI.2023.3247492","article-title":"Multi-task learning for pulmonary arterial hypertension prognosis prediction via memory drift and prior prompt learning on 3D chest CT","volume":"27","author":"Yang","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1692829\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:58:12Z","timestamp":1763553492000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1692829\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":25,"alternative-id":["10.3389\/frai.2025.1692829"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1692829","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,19]]},"article-number":"1692829"}}