Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients

Abstract

BackgroundWhereas heart failure (HF) is a complex clinical syndrome, conventional approaches to its management have treated it as a singular disease, leading to inadequate patient care and inefficient clinical trials. We hypothesized that applying advanced analytics to a large cohort of HF patients would improve prognostication of outcomes, identify distinct patient phenotypes, and detect heterogeneity in treatment response.Methods and ResultsThe Swedish Heart Failure Registry is a nationwide registry collecting detailed demographic, clinical, laboratory, and medication data and linked to databases with outcome information. We applied random forest modeling to identify predictors of 1‐year survival. Cluster analysis was performed and validated using serial bootstrapping. Association between clusters and survival was assessed with Cox proportional hazards modeling and interaction testing was performed to assess for heterogeneity in response to HF pharmacotherapy across propensity‐matched clusters. Our study included 44 886 HF patients enrolled in the Swedish Heart Failure Registry between 2000 and 2012. Random forest modeling demonstrated excellent calibration and discrimination for survival (C‐statistic=0.83) whereas left ventricular ejection fraction did not (C‐statistic=0.52): there were no meaningful differences per strata of left ventricular ejection fraction (1‐year survival: 80%, 81%, 83%, and 84%). Cluster analysis using the 8 highest predictive variables identified 4 clinically relevant subgroups of HF with marked differences in 1‐year survival. There were significant interactions between propensity‐matched clusters (across age, sex, and left ventricular ejection fraction and the following medications: diuretics, angiotensin‐converting enzyme inhibitors, β‐blockers, and nitrates, P<0.001, all).ConclusionsMachine learning algorithms accurately predicted outcomes in a large data set of HF patients. Cluster analysis identified 4 distinct phenotypes that differed significantly in outcomes and in response to therapeutics. Use of these novel analytic approaches has the potential to enhance effectiveness of current therapies and transform future HF clinical trials.

DIY AI, deep learning network development for automated image classification in a point‐of‐care ultrasound quality assurance program

“…In medicine, imaging analysis is among the most prominent and exciting AI applications. This technology is being driven largely by industry rather than by frontline clinicians 16,17 . Given this, the vast majority of deep learning activity by corporations are focused on radiology AI use and POCUS uses have been largely overlooked 18…”

Identifying Phenogroups in Patients with Subclinical Diastolic Dysfunction Using Unsupervised Statistical Learning

“…Other investigators have used machine learning or cluster analysis to identify subgroups of patients with distinct phenotypes that differ in their risk profiles and survival outcomes (7)(8)(9)(10)(11). These researchers have studied heterogeneous populations of patients with primary HTN and the absence of HF (9), HFpEF alone (7,8), and mixed populations of HFrEF and HFpEF combined (10,11). However, to our knowledge, ours is the first study to use hierarchical clustering to identify subgroups of patients with subclinical diastolic dysfunction.…”

Identifying Phenogroups in Patients with Subclinical Diastolic Dysfunction Using Unsupervised Statistical Learning

“…Other investigators have used machine learning or cluster analysis to identify subgroups of patients with distinct phenotypes that differ in their risk profiles and survival outcomes (7-11). These researchers have studied heterogeneous populations of patients with primary HTN and the absence of HF (9), HFpEF alone (7,8), and mixed populations of HFrEF and HFpEF combined (10,11). However, to our knowledge, ours is the first study to use hierarchical clustering to identify subgroups of patients with subclinical diastolic dysfunction.…”

“…Due to the complexity of the data and heterogeneity of patients in medicine, intuitively identifying groups with similar phenotypes can be difficult and therefore the ability to identify these groups using machine learning methods may allow for more targeted diagnostics, therapeutic strategies and prognostication. For example, unsupervised machine learning has been previously used in research to divide large heterogeneous populations of patients into smaller unique phenogroups, including patients with HFpEF (7,8), patients with primary hypertension (HTN) without heart failure (9), and mixed patient groups with HFrEF and HFpEF combined (10,11).…”