Identifying Phenogroups in patients with subclinical diastolic dysfunction using unsupervised statistical learning

Abstract

Background: Subclinical diastolic dysfunction is a precursor for developing heart failure with preserved ejection fraction (HFpEF); yet not all patients progress to HFpEF. Our objective was to evaluate clinical and echocardiographic variables to identify patients who develop HFpEF. Methods: Clinical, laboratory, and echocardiographic data were retrospectively collected for 81 patients without HF and 81 matched patients with HFpEF at the time of first documentation of subclinical diastolic dysfunction. Densitybased clustering or hierarchical clustering to group patients was based on 65 total variables including 19 categorical and 46 numerical variables. Logistic regression analysis was conducted on the entire study population as well as each individual cluster to identify independent predictors of HFpEF. Results: Unsupervised clustering identified 3 subgroups which differed in gender composition, severity of cardiac hypertrophy and aortic stenosis, NT-proBNP, percentage of patients who progressed to HFpEF, and timing of disease progression from diastolic dysfunction to HFpEF to death. Clusters that had higher percentages of women had progressively milder cardiac hypertrophy, less severe aortic stenosis, lower NT-proBNP, were diagnosed at an older age with HFpEF, and survived to an older age. Independent predictors of HFpEF for the entire cohort included diabetes, chronic kidney disease, atrial fibrillation, and diuretic use, with additional predictive variables found for each cluster. Conclusions: Cluster analysis can identify phenotypically distinct subgroups of patients with diastolic dysfunction. Clusters differ in HFpEF and mortality outcome. In addition, the variables that correlate with and predict HFpEF outcome differ among clusters.

Evaluating the adverse outcome of subtypes of heart failure with preserved ejection fraction defined by machine learning: a systematic review focused on defining high risk phenogroups

“…Sabbah et al did not attempt to identify a new HFpEF clinical classification but rather to use ML analytic techniques to determine whether unique inflammation patterns exist in HFpEF and are associated with clinical severity or profibrotic state (Sabbah et al, 2020[ 99 ]). One study enrolled patients with echocardiographic evidence of diastolic dysfunction and evaluated whether they did or did not progress to have clinical evidence of heart failure (HFpEF) (Kaptein et al, 2020[ 53 ]). One study focused on comparing different ML models rather than trying to identify phenogroups (Angraal et al, 2020[ 4 ]).…”

Heart Failure with Preserved Ejection Fraction: a Pharmacotherapeutic Update

“…Due to the complexity of the data and heterogeneity of patients, the identification of distinct clinical phenotypes using machine learning may allow for more targeted diagnostics and personalized therapeutic options [ 119 ]. Cohen et al identified three distinct phenogroups that displayed differences in circulating biomarkers, cardiac/arterial characteristics, and prognosis among TOPCAT trial participants [ 120 ].…”

Decision Support Systems in HF based on Deep Learning Technologies

“…The DL approach showed higher AUC than the 2016 American Society of Echocardiography guideline-based left ventricular grades [60] for predicting elevated left ventricular filling pressure (0.883 vs. 0.676). Kaptein et al [61] proposed an unsupervised learning approach to identify subgroups of patients with asymptomatic diastolic dysfunction, where three subgroups were identified. Similarly, in [62], a model-based clustering on clinical and echocardiogram variables in 320 HFpEF patients was applied, from which six phenogroups were derived.…”