机器学习在健康成年人运动试验中预测最大心率的准确性研究

A Machine Learning Approach to Developing an Accurate Prediction of Maximal Heart Rate During Exercise Testing in Apparently Healthy Adults.

机构信息

University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia (Mr Cundrič and Dr Bosnić); Fisher Institute of Health and Well-Being and Clinical Exercise Physiology Laboratory, Ball State University, Muncie, Indiana (Drs Kaminsky and Peterman); VA Palo Alto Health Care System and Stanford University, Palo Alto, California (Dr Myers); Departments of Information Systems, Faculty of Organizational Sciences (Dr Markovic) and Physiology, Faculty of Pharmacy (Dr Popović), University of Belgrade, Belgrade, Serbia; Department of Physical Therapy, College of Applied Science, University of Illinois at Chicago (Dr Arena); Division of Cardiology, University Clinical Center of Serbia, Belgrade, Serbia (Dr Popović); and Department for Cardiovascular Diseases, Mayo Clinic, Rochester, Minnesota (Dr Popović).

出版信息

J Cardiopulm Rehabil Prev. 2023 Sep 1;43(5):377-383. doi: 10.1097/HCR.0000000000000786. Epub 2023 Mar 8.

DOI:10.1097/HCR.0000000000000786

PMID:36880964

Abstract

PURPOSE

Maximal heart rate (HR max ) continues to be an important measure of adequate effort during an exercise test. The aim of this study was to improve the accuracy of HR max prediction using a machine learning (ML) approach.

METHODS

We used a sample from the Fitness Registry of the Importance of Exercise National Database, which included 17 325 apparently healthy individuals (81% males) who performed a maximal cardiopulmonary exercise test. Two standard formulas for HR max prediction were tested: Formula1 = 220 - age (yr), root-mean-squared error (RMSE) 21.9, relative root-mean-squared error (RRMSE) 1.1; and Formula2 = 209.3 - 0.72 × age (yr), RMSE 22.7 and RRMSE 1.1. For ML model prediction, we used age, weight, height, resting HR, and systolic and diastolic blood pressure. The following ML algorithms to predict HR max were applied: lasso regression (LR), neural networks (NN), support vector machine (SVM) and random forests (RF). An evaluation was performed using cross-validation and by computing the RMSE and RRMSE, Pearson correlation, and Bland-Altman plots. The best predictive model was explained with Shapley Additive Explanations (SHAP).

RESULTS

The HR max for the cohort was 162 ± 20 bpm. All ML models improved HR max prediction and reduced RMSE and RRMSE compared with Formula1 (LR: 20.2%, NN: 20.4%, SVM: 22.2%, and RF: 24.7%). The predictions of all algorithms significantly correlated with HR max ( r = 0.49, 0.51, 0.54, 0.57, respectively; P < .001). Bland-Altman analysis demonstrated lower bias and 95% CI for all ML models in comparison with standard equations. The SHAP explanation showed a high impact of all selected variables.

CONCLUSIONS

Machine learning, particularly the RF model, improved prediction of HR max using readily available measures. This approach should be considered for clinical application to refine HR max prediction.

摘要

目的

最大心率（HR max ）仍然是运动测试中评估充分努力程度的重要指标。本研究旨在通过机器学习（ML）方法提高 HR max 预测的准确性。

方法

我们使用来自“重要运动全国数据库健身登记处”的样本，其中包括 17325 名看似健康的个体（81%为男性），他们进行了最大心肺运动测试。测试了两种用于 HR max 预测的标准公式：公式 1=220-年龄（岁），均方根误差（RMSE）为 21.9，相对均方根误差（RRMSE）为 1.1；公式 2=209.3-0.72×年龄（岁），RMSE 为 22.7，RRMSE 为 1.1。对于 ML 模型预测，我们使用年龄、体重、身高、静息心率以及收缩压和舒张压。应用以下 ML 算法预测 HR max：lasso 回归（LR）、神经网络（NN）、支持向量机（SVM）和随机森林（RF）。通过交叉验证评估并计算 RMSE 和 RRMSE、Pearson 相关系数和 Bland-Altman 图来评估模型。用 Shapley 加性解释（SHAP）解释最佳预测模型。

结果

队列的 HR max 为 162±20 bpm。所有 ML 模型均提高了 HR max 预测，并降低了 RMSE 和 RRMSE，与公式 1 相比（LR：20.2%，NN：20.4%，SVM：22.2%，RF：24.7%）。所有算法的预测均与 HR max 显著相关（r=0.49、0.51、0.54、0.57，分别；P<0.001）。Bland-Altman 分析表明，与标准方程相比，所有 ML 模型的偏差和 95%置信区间均较低。SHAP 解释表明，所有选定变量的影响都很大。