Article Text

Download PDFPDF

Original research
Identification of novel pheno-groups in heart failure with preserved ejection fraction using machine learning
  1. Åsa K Hedman1,2,
  2. Camilla Hage3,4,
  3. Anil Sharma2,
  4. Mary Julia Brosnan5,
  5. Leonard Buckbinder5,
  6. Li-Ming Gan6,7,
  7. Sanjiv J Shah8,
  8. Cecilia M Linde3,4,
  9. Erwan Donal9,
  10. Jean-Claude Daubert10,
  11. Anders Mälarstig1,2,
  12. Daniel Ziemek11,
  13. Lars Lund3,4
  1. 1 Cardiovascular Medicine Unit, Department of Medicine Solna, Karolinska Institute, Stockholm, Sweden
  2. 2 Pfizer Global Research and Development, Stockholm, Sweden
  3. 3 Department of Medicine Solna, Unit of Cardiology, Karolinska Institute, Stockholm, Sweden
  4. 4 Heart and Vascular Theme, Karolinska University Hospital, Stockholm, Sweden
  5. 5 Pfizer Global Research and Development, Boston, Massachusetts, USA
  6. 6 Department of Cardiology and Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, Goteborgs Universitet, Goteborg, Sweden
  7. 7 Early Clinical Development, Early CVRM BioPharmaceuticals R&D, AstraZeneca FoU Goteborg, Goteborg, Sweden
  8. 8 Division of Cardiology, Department of Medicine, Feinberg School of Medicine, Northwestern University, Evanston, Illinois, USA
  9. 9 Cardiology and CIC-IT1414, CHU de Rennes LTSI, Universite Rennes, Rennes, France
  10. 10 Cardiology, University Hospital Rennes, Rennes, Bretagne, France
  11. 11 Pfizer Global Research and Development, Berlin, Germany
  1. Correspondence to Dr Åsa K Hedman, Department of Medicine Solna, Karolinska Institute, Stockholm, Sweden; asa.hedman{at}


Objective Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous syndrome. We aimed to derive HFpEF phenotype-based groups ('phenogroups') based on clinical and echocardiogram data using machine learning, and to compare clinical characteristics, proteomics and outcomes across the phenogroups.

Methods We applied model-based clustering to 32 echocardiogram and 11 clinical and laboratory variables collected in stable condition from 320 HFpEF outpatients in the Karolinska-Rennes cohort study (56% female, median 78 years (IQR: 71–83)). Baseline proteomics and the composite end point of all-cause mortality or heart failure (HF) hospitalisation were used in secondary analyses.

Results We identified six phenogroups, for which significant differences in the prevalence of concomitant atrial fibrillation (AF), anaemia and kidney disease were observed (p<0.05). Fifteen out of 86 plasma proteins differed between phenogroups (false discovery rate, FDR<0.05), including biomarkers of HF, AF and kidney function. The composite end point was significantly different between phenogroups (log-rank p<0.001), at short-term (100 days), mid-term (18 months) and longer-term follow-up (1000 days). Phenogroup 2 was older, with poorer diastolic and right ventricular function and higher burden of risk factors as AF (85%), hypertension (83%) and chronic obstructive pulmonary disease (30%). In this group a third experienced the primary outcome to 100 days, and two-thirds to 18 months (HR (95% CI) versus phenogroups 1, 3, 4, 5, 6: 1.5 (0.8–2.9); 5.7 (2.6–12.8); 2.9 (1.5–5.6); 2.7 (1.6–4.6); 2.1 (1.2–3.9)).

Conclusions Using machine learning we identified distinct HFpEF phenogroups with differential characteristics and outcomes, as well as differential levels of inflammatory and cardiovascular proteins.

  • heart failure with preserved ejection fraction
  • ECG/electrocardiogram

Statistics from


  • Twitter @twitganglion, @HFpEF

  • AM, DZ and LL contributed equally.

  • Contributors ÅKH, AM, DZ and LL conceived and designed the study. ÅKH performed statistical analyses and wrote the manuscript with contributions from LL, AM and DZ. AM, DZ and LL supervised the project. ED, J-CD, LL, CH, CML performed or supervised clinical data collection and phenotyping. L-MG provided proteomic profiling. SJS, MJB and LB provided technical and clinical contribution as well as discussion. All authors read, provided feedback and approved the final manuscript.

  • Funding This study was funded in part by grants 20120321 and 20150557 from the Swedish Heart-Lung Foundation, grants 2013-23897-104604-23 and 523-2014-2336 from the Swedish Research Council and 20140220 from Stockholm County council to LL; and from Medtronic to the French Heart Foundation. CML received funding from the Heart-Lung-foundation.

  • Competing interests ÅKH, AS, MJB, LB, AM and DZ are (or were during the duration of the study) employees of Pfizer. L-MG is an employee of Astra Zeneca.

  • Patient consent for publication Not required.

  • Ethics approval Approved by local ethics committees in Sweden and France; Karolinska Institute Sweden, Dnr: 2007/388- 31/2 Studietitel: KaRen Karolinska – Rennes forskningsstudie om hjärtsvikt med bevarad systolisk vänsterkammarfunktion.

  • Provenance and peer review Not commissioned; externally peer reviewed.

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Linked Articles