Machine-Learning-Based Prediction of Exercise Intolerance of Patients With Heart Failure Using Pragmatic Submaximal Exercise Parameters
Authors:
Open Access
- 10 April 2025
- journal article
- research article
- Published by Japanese Circulation Society in Circulation Reports
- Vol. 7 (4) , 257-266
Abstract
Background: Low peak oxygen uptake (V̇O2), especially ≤14 mL/min/kg, is a strong indicator of poor prognosis in patients with heart failure (HF). However, measuring this parameter is sometimes difficult if the maximal workload is not reached. This study developed a predictive classification model for low peak V̇O2in HF patients using machine learning (ML).Methods and Results: We retrospectively analyzed the data for 343 patients with chronic HF and left ventricular ejection fraction <50% who underwent a symptom-limited cardiopulmonary exercise test and extracted 33 variables from their laboratory, echocardiographic, and exercise data up to the submaximal workload. The dataset was randomly divided into training and testing datasets in a 4 : 1 ratio. ML methods, including an exhaustive search for predictor selection, were used, and a support vector machine algorithm was applied for model optimization. We identified 5 important predictors: age, B-type natriuretic peptide, left ventricular end-diastolic diameter, V̇O2at rest, and V̇O2at respiratory exchange ratio of 1.00. Using these 5 predictors, an optimized predictive model was validated on the testing dataset, yielding an accuracy of 85%, F1 score of 0.81, and area under the receiver operating curve of 0.94 (95% confidence interval: 0.89–1.00).Conclusions: Using readily available parameters, ML methods can enable accurate prediction of low peak V̇O2in patients with HF.Keywords
This publication has 30 references indexed in Scilit:
- $ {V}_{\text{O}_{2}}$ @RER1.0: A Novel Submaximal Cardiopulmonary Exercise IndexPediatric Cardiology, 2009
- Left atrial size may predict exercise capacity and cardiovascular events in patients with heart failure.2008
- Maximal lactate steady state determination with a single incremental test exerciseEuropean Journal of Applied Physiology, 2005
- Complementary roles of simple variables, NYHA and N-BNP, in indicating aerobic capacity and severity of heart failureInternational Journal of Cardiology, 2005
- Contribution of peak respiratory exchange ratio to peak VO2 prognostic reliability in patients with chronic heart failure and severely reduced exercise capacityAmerican Heart Journal, 2003
- Exercise Anaerobic Threshold and Ventilatory Efficiency Identify Heart Failure Patients for High Risk of Early DeathCirculation, 2002
- Exercise Capacity and Mortality among Men Referred for Exercise TestingNew England Journal of Medicine, 2002
- Attenuation of Compensation of Endogenous Cardiac Natriuretic Peptide System in Chronic Heart FailureCirculation, 1997
- Value of peak exercise oxygen consumption for optimal timing of cardiac transplantation in ambulatory patients with heart failure.Circulation, 1991
- The ability of a submaximal exercise test to predict maximal exercise capacity in patients with heart failureEuropean Heart Journal, 1985