Background: Despite cardiac rehabilitation (CR) being shown to improve health outcomes among patients with heart disease, its use has been suboptimal. In response, the Million Hearts Cardiac Rehabilitation Collaborative developed a road map to improve CR use, including increasing participation rates to ≥70% by 2022. This observational study provides current estimates to measure progress and identifies the populations and regions most at risk for CR service underutilization. Methods and Results: We identified Medicare fee-for-service beneficiaries who were CR eligible in 2016, and assessed CR participation (≥1 CR session attended), timely initiation (participation within 21 days of event), and completion (≥36 sessions attended) through 2017. Measures were assessed overall, by beneficiary characteristics and geography, and by primary CR-qualifying event type (acute myocardial infarction hospitalization; coronary artery bypass surgery; heart valve repair/replacement; percutaneous coronary intervention; or heart/heart-lung transplant). Among 366 103 CR-eligible beneficiaries, 89 327 (24.4%) participated in CR, of whom 24.3% initiated within 21 days and 26.9% completed CR. Eligibility was highest in the East South Central Census Division (14.8 per 1000). Participation decreased with increasing age, was lower among women (18.9%) compared with men (28.6%; adjusted prevalence ratio: 0.91 [95% CI, 0.90–0.93]) was lower among Hispanics (13.2%) and non-Hispanic blacks (13.6%) compared with non-Hispanic whites (25.8%; adjusted prevalence ratio: 0.63 [0.61–0.66] and 0.70 [0.67–0.72], respectively), and varied by hospital referral region and Census Division (range: 18.6% [East South Central] to 39.1% [West North Central]) and by qualifying event type (range: 7.1% [acute myocardial infarction without procedure] to 55.3% [coronary artery bypass surgery only]). Timely initiation varied by geography and qualifying event type; completion varied by geography. Conclusions: Only 1 in 4 CR-eligible Medicare beneficiaries participated in CR and marked disparities were observed. Reinforcement of current effective strategies and development of new strategies will be critical to address the noted disparities and achieve the 70% participation goal.

Machine learning is becoming a popular and important approach in the field of medical research. In this study, we investigate the relative performance of various machine learning methods such as Decision Tree, Naïve Bayes, Logistic Regression, Logistic Model Tree and Random Forests for predicting incident diabetes using medical records of cardiorespiratory fitness. In addition, we apply different techniques to uncover potential predictors of diabetes. This FIT project study used data of 32,555 patients who are free of any known coronary artery disease or heart failure who underwent clinician-referred exercise treadmill stress testing at Henry Ford Health Systems between 1991 and 2009 and had a complete 5-year follow-up. At the completion of the fifth year, 5,099 of those patients have developed diabetes. The dataset contained 62 attributes classified into four categories: demographic characteristics, disease history, medication use history, and stress test vital signs. We developed an Ensembling-based predictive model using 13 attributes that were selected based on their clinical importance, Multiple Linear Regression, and Information Gain Ranking methods. The negative effect of the imbalance class of the constructed model was handled by Synthetic Minority Oversampling Technique (SMOTE). The overall performance of the predictive model classifier was improved by the Ensemble machine learning approach using the Vote method with three Decision Trees (Naïve Bayes Tree, Random Forest, and Logistic Model Tree) and achieved high accuracy of prediction (AUC = 0.92). The study shows the potential of ensembling and SMOTE approaches for predicting incident diabetes using cardiorespiratory fitness data.

This study evaluates and compares the performance of different machine learning techniques on predicting the individuals at risk of developing hypertension, and who are likely to benefit most from interventions, using the cardiorespiratory fitness data. The dataset of this study contains information of 23,095 patients who underwent clinician- referred exercise treadmill stress testing at Henry Ford Health Systems between 1991 and 2009 and had a complete 10-year follow-up. The variables of the dataset include information on vital signs, diagnosis and clinical laboratory measurements. Six machine learning techniques were investigated: LogitBoost (LB), Bayesian Network classifier (BN), Locally Weighted Naive Bayes (LWB), Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Tree Forest (RTF). Using different validation methods, the RTF model has shown the best performance (AUC = 0.93) and outperformed all other machine learning techniques examined in this study. The results have also shown that it is critical to carefully explore and evaluate the performance of the machine learning models using various model evaluation methods as the prediction accuracy can significantly differ.

BackgroundPrior studies have demonstrated that cardiorespiratory fitness (CRF) is a strong marker of cardiovascular health. Machine learning (ML) can enhance the prediction of outcomes through classification techniques that classify the data into predetermined categories. The aim of this study is to present an evaluation and comparison of how machine learning techniques can be applied on medical records of cardiorespiratory fitness and how the various techniques differ in terms of capabilities of predicting medical outcomes (e.g. mortality).MethodsWe use data of 34,212 patients free of known coronary artery disease or heart failure who underwent clinician-referred exercise treadmill stress testing at Henry Ford Health Systems Between 1991 and 2009 and had a complete 10-year follow-up. Seven machine learning classification techniques were evaluated: Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Networks (ANN), Naïve Bayesian Classifier (BC), Bayesian Network (BN), K-Nearest Neighbor (KNN) and Random Forest (RF). In order to handle the imbalanced dataset used, the Synthetic Minority Over-Sampling Technique (SMOTE) is used.ResultsTwo set of experiments have been conducted with and without the SMOTE sampling technique. On average over different evaluation metrics, SVM Classifier has shown the lowest performance while other models like BN, BC and DT performed better. The RF classifier has shown the best performance (AUC = 0.97) among all models trained using the SMOTE sampling.ConclusionsThe results show that various ML techniques can significantly vary in terms of its performance for the different evaluation metrics. It is also not necessarily that the more complex the ML model, the more prediction accuracy can be achieved. The prediction performance of all models trained with SMOTE is much better than the performance of models trained without SMOTE. The study shows the potential of machine learning methods for predicting all-cause mortality using cardiorespiratory fitness data.

The enrollment (28.6%), engagement (mean number of visits = 25), and program completion rates (27.6%) remain low among Medicare beneficiaries in the United States, indicating that many patients did not fully benefit from a class I guideline-recommended therapy. Additional research and successful enrollment and engagement initiatives are needed, especially among identified populations.