Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comparative Study
. 2024 Jul 5;24(1):343.
doi: 10.1186/s12872-024-03987-9.

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

Fardad Soltani  1   2 , David A Jenkins  3 , Amit Kaura  4 , Joshua Bradley  1   2 , Nicholas Black  1   2 , John P Farrant  1   2 , Simon G Williams  2 , Abdulrahim Mulla  4   5 , Benjamin Glampson  4   5 , Jim Davies  6 , Dimitri Papadimitriou  4   5 , Kerrie Woods  6 , Anoop D Shah  7 , Mark R Thursz  4 , Bryan Williams  7 , Folkert W Asselbergs  7 , Erik K Mayer  4   5 , Christopher Herbert  8 , Stuart Grant  9 , Nick Curzen  10 , Iain Squire  11 , Thomas Johnson  12 , Kevin O'Gallagher  13 , Ajay M Shah  13 , Divaka Perera  14 , Rajesh Kharbanda  6 , Riyaz S Patel  7 , Keith M Channon  6 , Richard Lee  15 , Niels Peek  3   9   16 , Jamil Mayet  4 , Christopher A Miller  17   18   19   20
Affiliations
Comparative Study

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

Fardad Soltani et al. BMC Cardiovasc Disord. .

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.

Keywords: Electronic health records; Heart failure with preserved or mildly reduced ejection fraction; Machine learning.

PubMed Disclaimer

Conflict of interest statement

CAM has participated on advisory boards/consulted for AstraZeneca, Boehringer Ingelheim and Lilly Alliance, Novartis and PureTech Health, serves as an advisor for HAYA Therapeutics, has received speaker fees from AstraZeneca, Boehringer Ingelheim and Novo Nordisk, conference attendance support from AstraZeneca, and research support from Amicus Therapeutics, AstraZeneca, Guerbet Laboratories Limited, Roche and Univar Solutions B.V.

Figures

Fig. 1
Fig. 1
STROBE diagram. EF indicates ejection fraction; HIC, Health Informatics Collaborative; ICD-10, International Classification of Diseases 10th Revision; NIHR, National Institute for Health Research; STROBE, Strengthening the Reporting of Observational Studies in Epidemiology
Fig. 2
Fig. 2
Cluster plot illustrating the graphical representation of clusters from the k-means algorithm. Dimensions represent the principal components explaining the largest variation in data. Dimension 1 and Dimension 2 capture 9.1% and 7.8% of the variance, respectively. Each of the dots represent individual participants
Fig. 3
Fig. 3
Kaplan-Meier curves for all-cause mortality. Survival free of all-cause mortality stratified by phenogroup
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. McDonagh TA, Metra M, Adamo M, Gardner RS, Baumbach A, Böhm M, et al. 2021 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure: developed by the Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC) with the special contribution of the Heart Failure Association (HFA) of the ESC. Eur Heart J. 2021;42(36):3599–726. doi: 10.1093/eurheartj/ehab368. - DOI - PubMed
    1. Savarese G, Lund LH. Global Public Health Burden of Heart Failure. Cardiac Failure Review. 2017;3(1):7–11. 2017. - PMC - PubMed
    1. Conrad N, Judge A, Tran J, Mohseni H, Hedgecott D, Crespillo AP, et al. Temporal trends and patterns in heart failure incidence: a population-based study of 4 million individuals. Lancet. 2018;391(10120):572–80. doi: 10.1016/S0140-6736(17)32520-5. - DOI - PMC - PubMed
    1. Lewis GA, Schelbert EB, Williams SG, Cunnington C, Ahmed F, McDonagh TA, et al. Biological phenotypes of heart failure with preserved ejection fraction. J Am Coll Cardiol. 2017;70(17):2186–200. doi: 10.1016/j.jacc.2017.09.006. - DOI - PubMed
    1. Anker SD, Butler J, Filippatos G, Ferreira JP, Bocchi E, Böhm M, et al. Empagliflozin in Heart failure with a preserved ejection fraction. N Engl J Med. 2021;385(16):1451–61. doi: 10.1056/NEJMoa2107038. - DOI - PubMed

Publication types

MeSH terms