A Comparison among Different Machine Learning Pretest Approaches to Predict Stress-Induced Ischemia at PET/CT Myocardial Perfusion Imaging

Abstract

Traditional approach for predicting coronary artery disease (CAD) is based on demographic data, symptoms such as chest pain and dyspnea, and comorbidity related to cardiovascular diseases. Usually, these variables are analyzed by logistic regression to quantifying their relationship with the outcome; nevertheless, their predictive value is limited. In the present study, we aimed to investigate the value of different machine learning (ML) techniques for the evaluation of suspected CAD; having as gold standard, the presence of stress-induced ischemia by 82Rb positron emission tomography/computed tomography (PET/CT) myocardial perfusion imaging (MPI) ML was chosen on their clinical use and on the fact that they are representative of different classes of algorithms, such as deterministic (Support vector machine and Naïve Bayes), adaptive (ADA and AdaBoost), and decision tree (Random Forest, rpart, and XGBoost). The study population included 2503 consecutive patients, who underwent MPI for suspected CAD. To testing ML performances, data were split randomly into two parts: training/test (80%) and validation (20%). For training/test, we applied a 5-fold cross-validation, repeated 2 times. With this subset, we performed the tuning of free parameters for each algorithm. For all metrics, the best performance in training/test was observed for AdaBoost. The Naïve Bayes ML resulted to be more efficient in validation approach. The logistic and rpart algorithms showed similar metric values for the training/test and validation approaches. These results are encouraging and indicate that the ML algorithms can improve the evaluation of pretest probability of stress-induced myocardial ischemia.

Cardiovascular risk factors and development of nomograms in an Italian cohort of patients with suspected coronary artery disease undergoing SPECT or PET stress myocardial perfusion imaging

“…Lastly, studies on cardiovascular risk factors are also performed using machine learning algorithms. In particular, support vector machines, neural networks, naïve Bayesian, boosting, and other procedures are used for clinical evaluations of cardiovascular patients (24)(25)(26). In light of these considerations, the study of risk factors with large cohorts, comparing models, and using machine learning algorithms are desirable for advancing cardiology diagnostics and therapeutics.…”

Detecting obstructive coronary artery disease with machine learning: rest-only gated single photon emission computed tomography myocardial perfusion imaging combined with coronary artery calcium score and cardiovascular risk factors

“…XGBoost, a scalable end-to-end tree boosting technique, uses a weighted quantile sketch for approximate tree learning and a sparse-aware algorithm for sparse data (38). The Logistic algorithm used in this study is a part of generalized linear models (17). This classifier is widely used in clinical statistical analysis for dichotomous and multicategory outcome variables.…”

“…Artificial intelligence (AI) is a growing and powerful technology in healthcare. In recent years, the application of AI in nuclear cardiology has become increasingly extensive (12)(13)(14)(15)(16)(17). An interpretable algorithm based on deep learning was used to diagnose obstructive CAD in stress or stress/ rest MPI (15,18).…”

Age-Specific Cardiovascular Risk Factors for Major Adverse Cardiac Events in Patients Undergoing Myocardial Perfusion Imaging

“…Studies on cardiovascular risk stratification are also performed by artificial intelligence, in particular using machine learning algorithms. Several approaches such as support vector machines, naïve Bayesian, neural networks, boosting, and other procedures are used for clinical evaluations of cardiovascular patients [ 37 , 38 , 39 ].…”