Phenogrouping heart failure with preserved or mildly reduced ejection fraction using electronic health record data.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Additional Information
    • Source:
      Publisher: BioMed Central Country of Publication: England NLM ID: 100968539 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2261 (Electronic) Linking ISSN: 14712261 NLM ISO Abbreviation: BMC Cardiovasc Disord Subsets: MEDLINE
    • Publication Information:
      Original Publication: London : BioMed Central, [2001-
    • Subject Terms:
    • Abstract:
      Background: Heart failure (HF) with preserved or mildly reduced ejection fraction includes a heterogenous group of patients. Reclassification into distinct phenogroups to enable targeted interventions is a priority. This study aimed to identify distinct phenogroups, and compare phenogroup characteristics and outcomes, from electronic health record data.
      Methods: 2,187 patients admitted to five UK hospitals with a diagnosis of HF and a left ventricular ejection fraction ≥ 40% were identified from the NIHR Health Informatics Collaborative database. Partition-based, model-based, and density-based machine learning clustering techniques were applied. Cox Proportional Hazards and Fine-Gray competing risks models were used to compare outcomes (all-cause mortality and hospitalisation for HF) across phenogroups.
      Results: Three phenogroups were identified: (1) Younger, predominantly female patients with high prevalence of cardiometabolic and coronary disease; (2) More frail patients, with higher rates of lung disease and atrial fibrillation; (3) Patients characterised by systemic inflammation and high rates of diabetes and renal dysfunction. Survival profiles were distinct, with an increasing risk of all-cause mortality from phenogroups 1 to 3 (p < 0.001). Phenogroup membership significantly improved survival prediction compared to conventional factors. Phenogroups were not predictive of hospitalisation for HF.
      Conclusions: Applying unsupervised machine learning to routinely collected electronic health record data identified phenogroups with distinct clinical characteristics and unique survival profiles.
      (© 2024. The Author(s).)
    • References:
      Card Fail Rev. 2017 Apr;3(1):7-11. (PMID: 28785469)
      J Am Coll Cardiol. 2022 Jun 7;79(22):2219-2232. (PMID: 35654493)
      Circulation. 2015 Jan 20;131(3):269-79. (PMID: 25398313)
      Lancet. 2020 Aug 29;396(10251):623-634. (PMID: 32861307)
      Eur J Heart Fail. 2015 Sep;17(9):925-35. (PMID: 26250359)
      BMJ. 2019 Nov 20;367:l6055. (PMID: 31748235)
      Heart. 2020 Mar;106(5):342-349. (PMID: 31911501)
      BMJ Health Care Inform. 2020 Nov;27(3):. (PMID: 33214194)
      N Engl J Med. 2022 Sep 22;387(12):1089-1098. (PMID: 36027570)
      J Am Coll Cardiol. 2020 Mar 24;75(11):1281-1295. (PMID: 32192654)
      J Am Coll Cardiol. 2017 Oct 24;70(17):2186-2200. (PMID: 29050567)
      Eur J Heart Fail. 2016 Jun;18(6):716-26. (PMID: 27126231)
      Circ Heart Fail. 2020 Aug;13(8):e006414. (PMID: 32809874)
      Bioinformatics. 2012 Jan 1;28(1):112-8. (PMID: 22039212)
      Eur J Heart Fail. 2021 Jun;23(6):983-991. (PMID: 33651430)
      JACC Heart Fail. 2020 Mar;8(3):172-184. (PMID: 31926856)
      N Engl J Med. 2021 Oct 14;385(16):1451-1461. (PMID: 34449189)
      Eur Heart J. 2021 Sep 21;42(36):3599-3726. (PMID: 34447992)
      Eur J Heart Fail. 2020 Jan;22(1):148-158. (PMID: 31637815)
      J Am Heart Assoc. 2020 Apr 7;9(7):e013684. (PMID: 32212911)
      J Am Coll Cardiol. 2013 Jul 23;62(4):263-71. (PMID: 23684677)
      Lancet. 2018 Feb 10;391(10120):572-580. (PMID: 29174292)
    • Grant Information:
      AI_AWARD01864 National Institute for Health and Care Research; NIHR301338 National Institute for Health and Care Research; Horizon Europe Guarantee for DataTools4Heart UK Research and Innovation; AA/18/6/24223 United Kingdom BHF_ British Heart Foundation; FS/CRA/22/23036 United Kingdom BHF_ British Heart Foundation; AA/18/4/34221 United Kingdom BHF_ British Heart Foundation; RE/18/4/34215 BHF Imperial Centre for Research Excellence
    • Contributed Indexing:
      Keywords: Electronic health records; Heart failure with preserved or mildly reduced ejection fraction; Machine learning
    • Publication Date:
      Date Created: 20240705 Date Completed: 20240705 Latest Revision: 20241113
    • Publication Date:
      20241114
    • Accession Number:
      PMC11229019
    • Accession Number:
      10.1186/s12872-024-03987-9
    • Accession Number:
      38969974