{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T01:34:11Z","timestamp":1792892051557,"version":"4.5.0"},"reference-count":31,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T00:00:00Z","timestamp":1772064000000},"content-version":"unspecified","delay-in-days":56,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20341 and 82470394"],"award-info":[{"award-number":["U21A20341 and 82470394"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Open Heart"],"accepted":{"date-parts":[[2026,2,5]]},"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Patients with heart failure (HF) frequently suffer from undetected declines in cardiorespiratory fitness (CRF), which significantly increases their risk of poor outcomes. However, current clinical practice lacks effective tools for early CRF risk stratification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We conducted an artificial intelligence (AI)-driven unsupervised clustering analysis based on 15 multimodal clinical variables\u2014including metabolic, inflammatory and body composition indicators\u2014in 505 patients with HF. The associations between clustering-derived phenotypes and CRF impairment (maximal oxygen uptake (VO\n                      <jats:sub>2<\/jats:sub>\n                      max) \u226420\u2009mL\/kg\/min) were evaluated using multivariable logistic regression and five supervised machine learning models. SHapley Additive exPlanations analysis was applied for model interpretability. External validation was performed in an independent cohort of 201 patients.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Three distinct phenotypes were identified: balanced, inflammatory-sarcopenic and metabolically dysregulated. Compared with the balanced phenotype, both non-balanced phenotypes showed significantly higher odds of impaired VO\n                      <jats:sub>\u2082<\/jats:sub>\n                      max. In the derivation cohort test set, random forest (area under the curve (AUC)=0.75; 95%\u2009CI 0.62 to 0.87) and XGBoost (AUC=0.74; 95%\u2009CI 0.62 to 0.87) demonstrated the best discriminative performance. In the external validation cohort, the highest discrimination was observed for Naive Bayes (AUC=0.75; 95%\u2009CI 0.67 to 0.83), followed by random forest (AUC=0.74; 95%\u2009CI 0.58 to 0.91).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>By integrating multimodal clinical data with AI-driven clustering and machine learning, this study identified novel CRF risk phenotypes in patients with HF and established a highly interpretable and generalisable risk stratification model. These findings offer a valuable framework for early functional assessment and pave the way for precision rehabilitation strategies in HF management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/openhrt-2025-003530","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:35:21Z","timestamp":1772116521000},"page":"e003530","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":5,"title":["Artificial intelligence-based clustering to identify functional risk phenotypes in heart failure"],"prefix":"10.1136","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2731-1832","authenticated-orcid":false,"given":"Xunhan","family":"Qiu","sequence":"first","affiliation":[{"name":"Department of Cardiology, Shanghai Jiao Tong University School of Medicine Affiliated Renji Hospital, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Shanghai Jiao Tong University School of Medicine Affiliated Renji Hospital, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Nursing, Shanghai Jiao Tong University School of Medicine Affiliated Renji Hospital, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Shanghai Jiao Tong University School of Medicine Affiliated Renji Hospital, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Pu","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Shanghai Jiao Tong University School of Medicine Affiliated Renji Hospital, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,2,26]]},"reference":[{"key":"2026022606351427000_13.1.e003530.1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.121.318172"},{"key":"2026022606351427000_13.1.e003530.2","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1038\/s41572-020-0151-7","article-title":"Acute heart failure","volume":"6","author":"Arrigo","year":"2020","journal-title":"Nat Rev Dis Primers"},{"key":"2026022606351427000_13.1.e003530.3","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1016\/j.cardfail.2021.02.007","article-title":"Patterns of Change in Individual Domains of the Kansas City Cardiomyopathy Questionnaire With a Palliative Care Intervention for Patients With Advanced Heart Failure: Insights from PAL-HF","volume":"27","author":"Wan","year":"2021","journal-title":"J Card Fail"},{"key":"2026022606351427000_13.1.e003530.4","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.122.027852","article-title":"Burden, Trends, and Inequalities of Heart Failure Globally, 1990 to 2019: A Secondary Analysis Based on the Global Burden of Disease 2019 Study","volume":"12","author":"Yan","year":"2023","journal-title":"J Am Heart Assoc"},{"key":"2026022606351427000_13.1.e003530.5","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.119.315889"},{"key":"2026022606351427000_13.1.e003530.6","doi-asserted-by":"publisher","DOI":"10.1016\/S0735-1097(19)32815-3"},{"key":"2026022606351427000_13.1.e003530.7","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCHEARTFAILURE.114.001615"},{"key":"2026022606351427000_13.1.e003530.8","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.83.3.778"},{"key":"2026022606351427000_13.1.e003530.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ahj.2003.07.014"},{"key":"2026022606351427000_13.1.e003530.10","doi-asserted-by":"publisher","DOI":"10.1136\/svn-2017-000101"},{"key":"2026022606351427000_13.1.e003530.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102444"},{"key":"2026022606351427000_13.1.e003530.12","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehab649"},{"key":"2026022606351427000_13.1.e003530.13","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-42657-2","article-title":"Cluster analysis driven by unsupervised latent feature learning of medications to identify novel pharmacophenotypes of critically ill patients","volume":"13","author":"Sikora","year":"2023","journal-title":"Sci Rep"},{"key":"2026022606351427000_13.1.e003530.14","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbz170"},{"key":"2026022606351427000_13.1.e003530.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103364"},{"key":"2026022606351427000_13.1.e003530.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2023.115265"},{"key":"2026022606351427000_13.1.e003530.17","doi-asserted-by":"publisher","DOI":"10.1002\/ejhf.1621"},{"key":"2026022606351427000_13.1.e003530.18","doi-asserted-by":"crossref","first-page":"45","DOI":"10.2459\/JCM.0000000000001116","article-title":"Phenotypic clustering of heart failure with preserved ejection fraction reveals different rates of hospitalization","volume":"22","author":"Casebeer","year":"2021","journal-title":"J Cardiovasc Med (Hagerstown)"},{"key":"2026022606351427000_13.1.e003530.19","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1038\/s41569-025-01165-8","article-title":"Immunometabolism in heart failure","volume":"22","author":"Andreadou","year":"2025","journal-title":"Nat Rev Cardiol"},{"key":"2026022606351427000_13.1.e003530.20","first-page":"2235","article-title":"Molecular mechanisms of skeletal muscle remodeling in heart failure","volume":"600","author":"Cruz-Topete","year":"2022","journal-title":"J Physiol"},{"key":"2026022606351427000_13.1.e003530.21","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-021-27634-5","article-title":"Skeletal muscle derived Musclin protects the heart during pathological overload","volume":"13","author":"Szaroszyk","year":"2022","journal-title":"Nat Commun"},{"key":"2026022606351427000_13.1.e003530.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cardiores.2006.08.018"},{"key":"2026022606351427000_13.1.e003530.23","doi-asserted-by":"crossref","unstructured":"Guazzi M , Adams V , Conraads V , et al . Clinical recommendations for cardiopulmonary exercise testing data assessment in specific patient populations: a scientific statement from the European Association for Cardiovascular Prevention. 2012;126:2261\u201374. doi:10.1161\/CIR.0b013e31826fb946","DOI":"10.1161\/CIR.0b013e31826fb946"},{"key":"2026022606351427000_13.1.e003530.24","doi-asserted-by":"publisher","DOI":"10.1016\/0002-9149(85)90792-1"},{"key":"2026022606351427000_13.1.e003530.25","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehz158"},{"key":"2026022606351427000_13.1.e003530.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jchf.2017.09.009"},{"key":"2026022606351427000_13.1.e003530.27","doi-asserted-by":"publisher","DOI":"10.3945\/jn.116.230912"},{"key":"2026022606351427000_13.1.e003530.28","doi-asserted-by":"crossref","DOI":"10.3390\/ijms252413480","article-title":"Irisin: A Multifaceted Hormone Bridging Exercise and Disease Pathophysiology","volume":"25","author":"Paoletti","year":"2024","journal-title":"Int J Mol Sci"},{"key":"2026022606351427000_13.1.e003530.29","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.117.029617"},{"key":"2026022606351427000_13.1.e003530.30","doi-asserted-by":"crossref","DOI":"10.1186\/s12933-023-02089-8","article-title":"Association between the triglyceride-glucose index and impaired cardiovascular fitness in non-diabetic young population","volume":"23","author":"Guo","year":"2024","journal-title":"Cardiovasc Diabetol"},{"key":"2026022606351427000_13.1.e003530.31","doi-asserted-by":"publisher","DOI":"10.1097\/00041433-200306000-00008"}],"container-title":["Open Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/openhrt-2025-003530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:35:24Z","timestamp":1772116524000},"score":1,"resource":{"primary":{"URL":"https:\/\/openheart.bmj.com\/lookup\/doi\/10.1136\/openhrt-2025-003530"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,2,26]]},"published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1136\/openhrt-2025-003530"],"URL":"https:\/\/doi.org\/10.1136\/openhrt-2025-003530","relation":{},"ISSN":["2053-3624"],"issn-type":[{"value":"2053-3624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}