Heart failure with preserved ejection fraction phenogroup classification using machine learning

Abstract

Aims: Heart failure (HF) with preserved ejection fraction (HFpEF) is a complex syndrome with a poor prognosis. Phenotyping is required to identify subtype-dependent treatment strategies. Phenotypes of Japanese HFpEF patients are not fully elucidated, whose obesity is much less than Western patients. This study aimed to reveal model-based phenomapping using unsupervised machine learning (ML) for HFpEF in Japanese patients.

Methods and results: We studied 365 patients with HFpEF (left ventricular ejection fraction >50%) as a derivation cohort from the Nara Registry and Analyses for Heart Failure (NARA-HF), which registered patients with hospitalization by acute decompensated HF. We used unsupervised ML with a variational Bayesian-Gaussian mixture model (VBGMM) with common clinical variables. We also performed hierarchical clustering on the derivation cohort. We adopted 230 patients in the Japanese Heart Failure Syndrome with Preserved Ejection Fraction Registry as the validation cohort for VBGMM. The primary endpoint was defined as all-cause death and HF readmission within 5 years. Supervised ML was performed on the composite cohort of derivation and validation. The optimal number of clusters was three because of the probable distribution of VBGMM and the minimum Bayesian information criterion, and we stratified HFpEF into three phenogroups. Phenogroup 1 (n = 125) was older (mean age 78.9 ± 9.1 years) and predominantly male (57.6%), with the worst kidney function (mean estimated glomerular filtration rate 28.5 ± 9.7 mL/min/1.73 m² ) and a high incidence of atherosclerotic factor. Phenogroup 2 (n = 200) had older individuals (mean age 78.8 ± 9.7 years), the lowest body mass index (BMI; 22.78 ± 3.94), and the highest incidence of women (57.5%) and atrial fibrillation (56.5%). Phenogroup 3 (n = 40) was the youngest (mean age 63.5 ± 11.2) and predominantly male (63.5 ± 11.2), with the highest BMI (27.46 ± 5.85) and a high incidence of left ventricular hypertrophy. We characterized these three phenogroups as atherosclerosis and chronic kidney disease, atrial fibrillation, and younger and left ventricular hypertrophy groups, respectively. At the primary endpoint, Phenogroup 1 demonstrated the worst prognosis (Phenogroups 1-3: 72.0% vs. 58.5% vs. 45%, P = 0.0036). We also successfully classified a derivation cohort into three similar phenogroups using VBGMM. Hierarchical and supervised clustering successfully showed the reproducibility of the three phenogroups.

Conclusions: ML could successfully stratify Japanese HFpEF patients into three phenogroups (atherosclerosis and chronic kidney disease, atrial fibrillation, and younger and left ventricular hypertrophy groups).

Keywords: Heart failure with preserved ejection fraction; Machine learning; Unsupervised clustering.

Figure 1

Study flow. HFpEF, heart failure with preserved ejection fraction; JASPER, Japanese Heart Failure Syndrome with Preserved Ejection Fraction Registry; LVEF, left ventricular ejection fraction; NARA‐HF, Nara Registry and Analyses for Heart Failure.

Figure 2

Characteristics summary of the three phenogroups in the Nara Registry and Analyses for Heart Failure. AF, atrial fibrillation; BMI, body mass index; CKD, chronic kidney disease; DM, diabetes mellitus; HL, hyperlipidaemia; HR, heart rate; HT, hypertension; LV, left ventricle; LVH, left ventricular hypertrophy.

Figure 3

Kaplan–Meier survival curves of primary and secondary endpoints in the Nara Registry and Analyses for Heart Failure: (A) primary endpoint, (B) all‐cause death, (C) cardiovascular death, and (D) heart failure readmission. AF, atrial fibrillation; CKD, chronic kidney disease; LVH, left ventricular hypertrophy.

Figure 4

Heat mapping of clinical variables in derivation and validation studies. AF, atrial fibrillation; Alb, serum albumin; BMI, body mass index; BNP, brain natriuretic peptide; BUN, blood urea nitrogen; Cre, serum creatinine level; CRP, C‐reactive protein; DBP, diastolic blood pressure; DM, diabetes mellitus; eGFR, estimated glomerular filtration rate; Hb, haemoglobin; HL, hyperlipidaemia; HR, heart rate; HT, hypertension; IVST, interventricular septal thickness; JASPER, Japanese Heart Failure Syndrome with Preserved Ejection Fraction Registry; LVDd, left ventricular end‐diastolic diameter; LVDs, left ventricular end‐systolic diameter; Na, serum sodium level; NARA‐HF, Nara Registry and Analyses for Heart Failure; OMI, old myocardial infarction; PWT, posterior wall thickness; SBP, systolic blood pressure; TP, serum total protein.