Improving risk prediction in heart failure using machine learning

Abstract

Background Predicting mortality is important in patients with heart failure (HF). However, current strategies for predicting risk are only modestly successful, likely because they are derived from statistical analysis methods that fail to capture prognostic information in large data sets containing multi‐dimensional interactions. Methods and results We used a machine learning algorithm to capture correlations between patient characteristics and mortality. A model was built by training a boosted decision tree algorithm to relate a subset of the patient data with a very high or very low mortality risk in a cohort of 5822 hospitalized and ambulatory patients with HF. From this model we derived a risk score that accurately discriminated between low and high‐risk of death by identifying eight variables (diastolic blood pressure, creatinine, blood urea nitrogen, haemoglobin, white blood cell count, platelets, albumin, and red blood cell distribution width). This risk score had an area under the curve (AUC) of 0.88 and was predictive across the full spectrum of risk. External validation in two separate HF populations gave AUCs of 0.84 and 0.81, which were superior to those obtained with two available risk scores in these same populations. Conclusions Using machine learning and readily available variables, we generated and validated a mortality risk score in patients with HF that was more accurate than other risk scores to which it was compared. These results support the use of this machine learning approach for the evaluation of patients with HF and in other settings where predicting risk has been challenging.

Big Data Approaches in Heart Failure Research

“…Predicting the outcomes of HF patients, especially within subgroups, is a major area within big data studies using EHR data or other data relevant to clinical care [108]. Adler et al were able to divide HF patients into those at high and low risk of death based on clinical variables, and their classifier had a better predictive power than any of the individual classifier components, and better than other comparison markers including NT-proBNP [109]. Ahmad et al divided a group of HF patients into four clusters which differed in age, sex, clinical measures, and comorbid conditions, before building a classifier to predict survival.…”

January 2020 at a glance: translational medicine, predictors of outcome and treatments

“…Machine learning may be used to identify patients responding to HF therapies such as cardiac resynchronization. 18 Adler et al 19 used a machine-learning algorithm based on eight easy variables to predict mortality in HF patients. Also Segar et al 20 used machine-learning analysis to identify three phenotypes of HFpEF with different clinical characteristics and outcomes.…”

“…Machine learning may be used to identify patients responding to HF therapies such as cardiac resynchronization . Adler et al . used a machine‐learning algorithm based on eight easy variables to predict mortality in HF patients.…”

Machine learning to predict mortality after rehabilitation among patients with severe stroke

“…Correlation between covariates, nonlinearity of the association between continuous covariates and risk for the outcome of interest, and potential complex interactions among covariates represent common analytic challenges in regression modelling 20 , 21 . In comparison with statistical models, machine-learning (ML) methods have the advantages of using a larger number of predictors, requiring fewer assumptions, using an agnostic approach instead of a priori hypotheses, incorporating “multi-dimensional correlations that contain prognostic information”, and producing a “more flexible relationship among the predictor variables (alone or in combination) and the outcome” 20 , 22 – 24 . As observed by Deo 24 , “there may be features that are useful in combinations but not on their own”.…”