{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T01:37:51Z","timestamp":1794620271327,"version":"4.9.1"},"reference-count":30,"publisher":"BMJ","issue":"8","funder":[{"name":"AMED under Grant","award":["JP22uk1024007"],"award-info":[{"award-number":["JP22uk1024007"]}]},{"name":"Japan Society for the Promotion of Science Kakenhi Grants","award":["21K12706"],"award-info":[{"award-number":["21K12706"]}]},{"name":"Japan Society for the Promotion of Science Kakenhi Grants","award":["23K07509"],"award-info":[{"award-number":["23K07509"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Heart"],"accepted":{"date-parts":[[2023,11,30]]},"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>The classification of pulmonary hypertension (PH) is crucial for determining the appropriate therapeutic strategy. We investigated whether machine learning (ML) algorithms may assist in echocardiographic PH prediction, where current guidelines recommend integrating several different parameters.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We obtained physical and echocardiographic data from 885 patients who underwent right heart catheterisation (RHC). Patients were classified into three groups: non-PH, precapillary PH and postcapillary PH, based on values obtained from RHC. Using 24 parameters, we created predictive models employing four different classifiers and selected the one with the highest area under the curve. We then calculated the macro-average classification accuracy for PH on the derivation cohort (n=720) and prospective validation data set (n=165), comparing the results with guideline-based echocardiographic assessment obtained from each cohort.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Logistic regression with elastic net regularisation had the highest classification accuracy, with areas under the curves of 0.789, 0.766 and 0.742 for normal, precapillary PH and postcapillary PH, respectively. The ML model demonstrated significantly better predictive accuracy than the guideline-based echocardiographic assessment in the derivation cohort (59.4% vs 51.6%, p&lt;0.01). In the independent validation data set, the ML model\u2019s accuracy was comparable to the guideline-based PH classification (59.4% vs 57.8%, p=0.638).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>This preliminary study suggests promising potential for our ML model in predicting echocardiographic PH. Further research and validation are needed to fully assess its clinical utility in PH diagnosis and treatment decision-making.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/heartjnl-2023-323320","type":"journal-article","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T04:05:37Z","timestamp":1706673937000},"page":"586-593","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":30,"title":["Echocardiographic artificial intelligence for pulmonary hypertension classification"],"prefix":"10.1136","volume":"110","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3379-9387","authenticated-orcid":false,"given":"Yukina","family":"Hirata","sequence":"first","affiliation":[{"name":"Ultrasound Examination center, Tokushima University Hospital, Tokushima, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takumasa","family":"Tsuji","sequence":"additional","affiliation":[{"name":"Department of Radiological Technology, Teikyo University, Itabashi-ku, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun'ichi","family":"Kotoku","sequence":"additional","affiliation":[{"name":"Department of Radiological Technology, Teikyo University, Itabashi-ku, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masataka","family":"Sata","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4909-754X","authenticated-orcid":false,"given":"Kenya","family":"Kusunose","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Nephrology, and Neurology, University of the Ryukyus, Uehara, Okinawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2024,1,30]]},"reference":[{"key":"2025100708160243000_110.8.586.1","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/s11897-016-0306-8","article-title":"Pulmonary hypertension in heart failure patients: pathophysiology and Prognostic implications","volume":"13","author":"Guazzi","year":"2016","journal-title":"Curr Heart Fail Rep"},{"key":"2025100708160243000_110.8.586.2","doi-asserted-by":"crossref","DOI":"10.1007\/s42979-021-00592-x","article-title":"Machine learning: Algorithms, real-world applications and research directions","volume":"2","author":"Sarker","year":"2021","journal-title":"SN Comput Sci"},{"key":"2025100708160243000_110.8.586.3","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-020-76359-w","article-title":"Deep learning to predict elevated pulmonary artery pressure in patients with suspected pulmonary hypertension using standard chest X Ray","volume":"10","author":"Kusunose","year":"2020","journal-title":"Sci Rep"},{"key":"2025100708160243000_110.8.586.4","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.jacasi.2022.02.008","article-title":"Artificial intelligence-enabled electrocardiogram improves the diagnosis and prediction of mortality in patients with pulmonary hypertension","volume":"2","author":"Liu","year":"2022","journal-title":"JACC Asia"},{"key":"2025100708160243000_110.8.586.5","doi-asserted-by":"crossref","DOI":"10.3389\/fcvm.2022.891703","article-title":"Deep learning for detection of exercise-induced pulmonary hypertension using chest X-ray images","volume":"9","author":"Kusunose","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"2025100708160243000_110.8.586.6","doi-asserted-by":"crossref","DOI":"10.3389\/fcvm.2021.711611","article-title":"Machine learning augmented echocardiography for diastolic function assessment","volume":"8","author":"Fletcher","year":"2021","journal-title":"Front Cardiovasc Med"},{"key":"2025100708160243000_110.8.586.7","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1016\/j.echo.2022.06.005","article-title":"A novel continuous left ventricular diastolic function score using machine learning","volume":"35","author":"Jiang","year":"2022","journal-title":"J Am Soc Echocardiogr"},{"key":"2025100708160243000_110.8.586.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2016.10.012"},{"key":"2025100708160243000_110.8.586.9","doi-asserted-by":"crossref","first-page":"2671","DOI":"10.1016\/j.jacc.2020.10.007","article-title":"Cardiopulmonary hemodynamics in pulmonary hypertension and heart failure: JACC review topic of the week","volume":"76","author":"Maron","year":"2020","journal-title":"J Am Coll Cardiol"},{"key":"2025100708160243000_110.8.586.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2014.10.003"},{"key":"2025100708160243000_110.8.586.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2016.01.011"},{"key":"2025100708160243000_110.8.586.12","doi-asserted-by":"crossref","unstructured":"Galie N , Humbert M , Vachiery JL , et al . n.d. ESC\/ERS guidelines for the diagnosis and treatment of pulmonary hypertension: the joint task force for the diagnosis and treatment of pulmonary hypertension of the European society of cardiology (ESC). Eur Heart J;37:67\u2013119. doi:10.1093\/eurheartj\/ehv317","DOI":"10.1093\/eurheartj\/ehv317"},{"key":"2025100708160243000_110.8.586.13","unstructured":"Chang CC , Lin CJ . LIBSVM: A library for support vector Machines[Internet]. n.d. Available: www.csie.ntu.edu.tw\/"},{"key":"2025100708160243000_110.8.586.14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324\/METRICS"},{"key":"2025100708160243000_110.8.586.15","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . Xgboost: A Scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Association for Computing Machinery, 2016:785\u201394 doi:10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2025100708160243000_110.8.586.16","first-page":"4766","article-title":"A unified approach to interpreting model predictions","volume":"22","author":"Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing System"},{"key":"2025100708160243000_110.8.586.17","article-title":"Validity of algorithm for estimating left sided filling pressures on echocardiography in a population referred for pulmonary arterial hypertension","volume":"7","author":"Leung","year":"2017","journal-title":"Pulm Circ"},{"key":"2025100708160243000_110.8.586.18","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.115.002530","article-title":"Diagnostic accuracy of tissue Doppler index E\/E' for evaluating left ventricular filling pressure and diastolic dysfunction\/heart failure with preserved ejection fraction: A systematic review and meta-analysis","volume":"5","author":"Sharifov","year":"2016","journal-title":"J Am Heart Assoc"},{"key":"2025100708160243000_110.8.586.19","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1002\/ejhf.1220","article-title":"Correlation with invasive left ventricular filling pressures and Prognostic relevance of the echocardiographic diastolic parameters used in the 2016 ESC heart failure guidelines and in the 2016 ASE\/EACVI recommendations: a systematic review in patients with heart failure with preserved ejection fraction","volume":"20","author":"Nauta","year":"2018","journal-title":"Eur J Heart Fail"},{"key":"2025100708160243000_110.8.586.20","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1002\/ehf2.13119","article-title":"Meta-analysis of echocardiographic Quantification of left ventricular filling pressure","volume":"8","author":"Jones","year":"2021","journal-title":"ESC Heart Fail"},{"key":"2025100708160243000_110.8.586.21","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.ahj.2017.03.022","article-title":"Reliability of updated left ventricular diastolic function recommendations in predicting elevated left ventricular filling pressure and prognosis","volume":"189","author":"Sato","year":"2017","journal-title":"Am Heart J"},{"key":"2025100708160243000_110.8.586.22","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-021-96721-w","article-title":"Explainable machine-learning predictions for complications after pediatric congenital heart surgery","volume":"11","author":"Zeng","year":"2021","journal-title":"Sci Rep"},{"key":"2025100708160243000_110.8.586.23","doi-asserted-by":"crossref","first-page":"104813","DOI":"10.1016\/j.compbiomed.2021.104813","article-title":"Interpretable prediction of 3-year all-cause mortality in patients with heart failure caused by coronary heart disease based on machine learning and SHAP","volume":"137","author":"Wang","year":"2021","journal-title":"Comput Biol Med"},{"key":"2025100708160243000_110.8.586.24","first-page":"813","article-title":"Understanding heart failure patients EHR clinical features via SHAP interpretation of tree-based machine learning model predictions","volume":"2021","author":"Lu","year":"2021","journal-title":"AMIA Annu Symp Proc"},{"key":"2025100708160243000_110.8.586.25","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1111\/jch.14200","article-title":"Detection of abnormal left ventricular geometry in patients without cardiovascular disease through machine learning","volume":"23","author":"Angelaki","year":"2021","journal-title":"J Clin Hypertens (Greenwich)"},{"key":"2025100708160243000_110.8.586.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2017.01.058"},{"key":"2025100708160243000_110.8.586.27","doi-asserted-by":"publisher","DOI":"10.1038\/ejcn.2009.35"},{"key":"2025100708160243000_110.8.586.28","doi-asserted-by":"crossref","first-page":"3402","DOI":"10.1093\/eurheartj\/ehac389","article-title":"Riociguat in pulmonary hypertension and heart failure with preserved ejection fraction: the haemoDYNAMIC trial","volume":"43","author":"Dachs","year":"2022","journal-title":"Eur Heart J"},{"key":"2025100708160243000_110.8.586.29","doi-asserted-by":"crossref","first-page":"2358","DOI":"10.1038\/s41591-023-02526-x","article-title":"Semaglutide in Hfpef across obesity class and by body weight reduction: a Prespecified analysis of the STEP-Hfpef trial","volume":"29","author":"Borlaug","year":"2023","journal-title":"Nat Med"},{"key":"2025100708160243000_110.8.586.30","doi-asserted-by":"crossref","first-page":"3618","DOI":"10.1093\/eurheartj\/ehac237","article-title":"ESC\/ERS guidelines for the diagnosis and treatment of pulmonary hypertension: developed by the task force for the diagnosis and treatment of pulmonary hypertension of the European society of cardiology (ESC) and the European respiratory society (ERS). endorsed by the International society for heart and lung transplantation (ISHLT)","volume":"43","author":"Humbert","year":"2022","journal-title":"Eur Heart J"}],"container-title":["Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/heartjnl-2023-323320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T15:37:43Z","timestamp":1759851463000},"score":1,"resource":{"primary":{"URL":"https:\/\/heart.bmj.com\/lookup\/doi\/10.1136\/heartjnl-2023-323320"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,30]]},"references-count":30,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,3,22]]},"published-print":{"date-parts":[[2024,4]]}},"alternative-id":["10.1136\/heartjnl-2023-323320"],"URL":"https:\/\/doi.org\/10.1136\/heartjnl-2023-323320","relation":{},"ISSN":["1355-6037","1468-201X"],"issn-type":[{"value":"1355-6037","type":"print"},{"value":"1468-201X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,30]]}}}