{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T22:33:17Z","timestamp":1791671597837,"version":"4.3.4"},"reference-count":35,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"8","content-domain":{"domain":["www.ahajournals.org"],"crossmark-restriction":true},"short-container-title":["JAHA"],"published-print":{"date-parts":[[2018,4,17]]},"abstract":"<jats:sec xml:lang=\"en\">\n            <jats:title>Background<\/jats:title>\n            <jats:p xml:lang=\"en\">\n              Whereas heart failure (\n              <jats:styled-content style=\"fixed-case\">HF<\/jats:styled-content>\n              ) is a complex clinical syndrome, conventional approaches to its management have treated it as a singular disease, leading to inadequate patient care and inefficient clinical trials. We hypothesized that applying advanced analytics to a large cohort of\n              <jats:styled-content style=\"fixed-case\">HF<\/jats:styled-content>\n              patients would improve prognostication of outcomes, identify distinct patient phenotypes, and detect heterogeneity in treatment response.\n            <\/jats:p>\n          <\/jats:sec>\n          <jats:sec xml:lang=\"en\">\n            <jats:title>Methods and Results<\/jats:title>\n            <jats:p xml:lang=\"en\">\n              The Swedish Heart Failure Registry is a nationwide registry collecting detailed demographic, clinical, laboratory, and medication data and linked to databases with outcome information. We applied random forest modeling to identify predictors of 1\u2010year survival. Cluster analysis was performed and validated using serial bootstrapping. Association between clusters and survival was assessed with Cox proportional hazards modeling and interaction testing was performed to assess for heterogeneity in response to\n              <jats:styled-content style=\"fixed-case\">HF<\/jats:styled-content>\n              pharmacotherapy across propensity\u2010matched clusters. Our study included 44\u00a0886\n              <jats:styled-content style=\"fixed-case\">HF<\/jats:styled-content>\n              patients enrolled in the Swedish Heart Failure Registry between 2000 and 2012. Random forest modeling demonstrated excellent calibration and discrimination for survival (C\u2010statistic=0.83) whereas left ventricular ejection fraction did not (C\u2010statistic=0.52): there were no meaningful differences per strata of left ventricular ejection fraction (1\u2010year survival: 80%, 81%, 83%, and 84%). Cluster analysis using the 8 highest predictive variables identified 4 clinically relevant subgroups of\n              <jats:styled-content style=\"fixed-case\">HF<\/jats:styled-content>\n              with marked differences in 1\u2010year survival. There were significant interactions between propensity\u2010matched clusters (across age, sex, and left ventricular ejection fraction and the following medications: diuretics, angiotensin\u2010converting enzyme inhibitors, \u03b2\u2010blockers, and nitrates,\n              <jats:italic>P<\/jats:italic>\n              &lt;0.001, all).\n            <\/jats:p>\n          <\/jats:sec>\n          <jats:sec xml:lang=\"en\">\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p xml:lang=\"en\">\n              Machine learning algorithms accurately predicted outcomes in a large data set of\n              <jats:styled-content style=\"fixed-case\">HF<\/jats:styled-content>\n              patients. Cluster analysis identified 4 distinct phenotypes that differed significantly in outcomes and in response to therapeutics. Use of these novel analytic approaches has the potential to enhance effectiveness of current therapies and transform future\n              <jats:styled-content style=\"fixed-case\">HF<\/jats:styled-content>\n              clinical trials.\n            <\/jats:p>\n          <\/jats:sec>","DOI":"10.1161\/jaha.117.008081","type":"journal-article","created":{"date-parts":[[2018,4,12]],"date-time":"2018-04-12T09:55:13Z","timestamp":1523526913000},"update-policy":"https:\/\/doi.org\/10.1161\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":223,"title":["Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients"],"prefix":"10.1161","volume":"7","author":[{"given":"Tariq","family":"Ahmad","sequence":"first","affiliation":[{"name":"Section\u00a0of Cardiovascular Medicine and Center for Outcomes Research, Yale University School of Medicine New Haven, CT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars H.","family":"Lund","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Karolinska Institutet Department of Medicine and Karolinska University Hospital, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pooja","family":"Rao","sequence":"additional","affiliation":[{"name":"Qure.ai, Mumbai, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohit","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Qure.ai, Mumbai, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prashant","family":"Warier","sequence":"additional","affiliation":[{"name":"Qure.ai, Mumbai, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Vaccaro","sequence":"additional","affiliation":[{"name":"Section\u00a0of Cardiovascular Medicine and Center for Outcomes Research, Yale University School of Medicine New Haven, CT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ulf","family":"Dahlstr\u00f6m","sequence":"additional","affiliation":[{"name":"Department of Medicine and Health Sciences, Link\u00f6ping University, Link\u00f6ping, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher M.","family":"O'Connor","sequence":"additional","affiliation":[{"name":"Duke Clinical Research Institute, Duke University, Durham, NC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G. Michael","family":"Felker","sequence":"additional","affiliation":[{"name":"Duke Clinical Research Institute, Duke University, Durham, NC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nihar R.","family":"Desai","sequence":"additional","affiliation":[{"name":"Section\u00a0of Cardiovascular Medicine and Center for Outcomes Research, Yale University School of Medicine New Haven, CT"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(14)61889-4"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.116.025795"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa052256"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehw128"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCHEARTFAILURE.109.893222"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jchf.2017.06.013"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jchf.2017.08.012"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2016.05.011"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jchf.2016.06.004"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1606181"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.18421"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2014.07.979"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.114.010637"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2012.452"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurjhf\/hfp175"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2012.14785"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2014.15241"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2016.3956"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0174944"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2164-6-35"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-213"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1111\/ejhf.32"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.105.584102"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2016.5036"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2014.0053"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2012.02.009"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/nrd2219"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.111.089243"},{"key":"e_1_3_3_31_2","doi-asserted-by":"crossref","first-page":"ix","DOI":"10.1016\/j.hfc.2014.02.001","article-title":"Comorbid conditions in heart failure: an unhappy marriage","volume":"10","author":"Mehra MR","year":"2014","unstructured":"Mehra MR, Butler J. Comorbid conditions in heart failure: an unhappy marriage. Heart Fail Clin. 2014;10:ix.","journal-title":"Heart Fail Clin"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2017.04.014"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehx511"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0b013e31824f2173"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2017.8462"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2012.14795"}],"container-title":["Journal of the American Heart Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ahajournals.org\/doi\/full\/10.1161\/JAHA.117.008081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T11:20:58Z","timestamp":1715599258000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ahajournals.org\/doi\/10.1161\/JAHA.117.008081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,17]]},"references-count":35,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2018,4,17]]}},"alternative-id":["10.1161\/JAHA.117.008081"],"URL":"https:\/\/doi.org\/10.1161\/jaha.117.008081","relation":{},"ISSN":["2047-9980"],"issn-type":[{"value":"2047-9980","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4,17]]},"assertion":[{"value":"2017-11-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-03-13","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-04-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e008081"}}