Phenomapping Heart Failure with Preserved Ejection Fraction Using Machine Learning Cluster Analysis: Prognostic and Therapeutic Implications

Elena Galli (1, 2) , Corentin Bourg (1, 2) , Wojciech Kosmala (3) , Emmanuel Oger (4) , Erwan Donal (1, 2)

1 LTSI - Laboratoire Traitement du Signal et de l'Image
2 Centre Hospitalier Universitaire de Rennes [CHU Rennes] = Rennes University Hospital [Ponchaillou]
3 Medical University of Warsaw - Poland
4 REPERES - Recherche en Pharmaco-épidémiologie et Recours aux Soins

Heart failure with preserved ejection fraction (HFpEF) is characterized by a high rate of hospitalization and mortality (up to 84% at 5 years), which are similar to those observed for heart failure with reduced ejection fraction (HFrEF). These epidemiologic data claim for the development of specific and innovative therapies to reduce the burden of morbidity and mortality associated with this disease. Compared with HFrEF, which is due to a primary myocardial damage (eg ischemia, cardiomyopathies, toxicity), a heterogeneous etiologic background characterizes HFpEF. The authors discuss these phenotypes and specificities for defining therapeutic strategies that could be proposed according to phenotypes.

Mots clés: Heart failure with preserved ejection fraction; Machine learning; Phenomapping; Precision medicine; Prognosis; Targeted treatment

Domaines: Ingénierie biomédicale

Elena Galli, Corentin Bourg, Wojciech Kosmala, Emmanuel Oger, Erwan Donal. Phenomapping Heart Failure with Preserved Ejection Fraction Using Machine Learning Cluster Analysis: Prognostic and Therapeutic Implications. Heart Failure Clinics, 2021, 17 (3), pp.499-518. ⟨10.1016/j.hfc.2021.02.010⟩. ⟨hal-03246464⟩