Comparison of machine learning techniques to predict all-cause mortality using fitness data: The Henry Ford exercIse testing (FIT) project

Keyphrases

• All-cause Mortality 100%
• Exercise Test 100%
• Machine Learning Techniques 100%
• Henry Ford 100%
• Oversampling Technique 100%
• Fitness Data 100%
• Synthetic Minority 100%
• Cardiorespiratory Fitness 60%
• Decision Tree 40%
• Bayesian Network 40%
• Evaluation Metrics 40%
• Bayesian Classifier 40%
• Health Systems 20%
• Coronary Artery Disease 20%
• Artificial Neural Network 20%
• Medical Records 20%
• Outcome Prediction 20%
• Heart Failure 20%
• Classification Methods 20%
• Support Vector Machine 20%
• Machine Learning 20%
• Sampling Methods 20%
• 10-year Follow-up 20%
• Prediction Accuracy 20%
• Background Prior 20%
• Performance Prediction 20%
• Random Forest 20%
• Cardiovascular Health 20%
• Medical Outcomes 20%
• Treadmill Test 20%
• Low Performance 20%
• K-nearest 20%
• Bayesian Decision Analysis 20%
• Machine Learning Classification 20%
• Nave Bayesian 20%
• Machine Learning Models 20%
• Imbalanced Data 20%
• Data Use 20%
• Model Evaluation 20%
• Random Forest Classifier 20%
• Support Vector Classifier 20%
• Tree Support 20%

Computer Science

• Sampling Technique 100%
• Machine Learning Technique 100%
• Support Vector Machine 33%
• Classification Technique 33%
• Evaluation Metric 33%
• Bayesian Classifier 33%
• Bayesian Networks 33%
• Machine Learning 33%
• Learning System 33%
• Decision Tree 33%
• Random Forest Classifier 16%
• Random Decision Forest 16%
• Neural Network 16%
• Medical Record 16%
• Prediction Accuracy 16%
• Prediction Performance 16%
• Cardiovascular Health 16%
• Bayesian Decision 16%
• Lower Performance 16%
• Machine Learning Model 16%