Identification of novel pheno-groups in heart failure with preserved ejection fraction using machine learning

Åsa K. Hedman*, Camilla Hage, Anil Sharma, Mary Julia Brosnan, Leonard Buckbinder, Li Ming Gan, Sanjiv J. Shah, Cecilia M. Linde, Erwan Donal, Jean Claude Daubert, Anders Mälarstig, Daniel Ziemek, Lars Lund

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

19 Scopus citations


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.

Original languageEnglish (US)
Article number315481
StateAccepted/In press - Jan 1 2019


  • ECG/electrocardiogram
  • Heart failure with preserved ejection fraction

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine

Fingerprint Dive into the research topics of 'Identification of novel pheno-groups in heart failure with preserved ejection fraction using machine learning'. Together they form a unique fingerprint.

Cite this