METHODS: We first tested ten traditional machine learning algorithms, and then the three-best performing algorithms (three types of SVM) were used in the rest of the study. To improve the performance of these algorithms, a data preprocessing with normalization was carried out. Moreover, a genetic algorithm and particle swarm optimization, coupled with stratified 10-fold cross-validation, were used twice: for optimization of classifier parameters and for parallel selection of features.
RESULTS: The presented approach enhanced the performance of all traditional machine learning algorithms used in this study. We also introduced a new optimization technique called N2Genetic optimizer (a new genetic training). Our experiments demonstrated that N2Genetic-nuSVM provided the accuracy of 93.08% and F1-score of 91.51% when predicting CAD outcomes among the patients included in a well-known Z-Alizadeh Sani dataset. These results are competitive and comparable to the best results in the field.
CONCLUSIONS: We showed that machine-learning techniques optimized by the proposed approach, can lead to highly accurate models intended for both clinical and research use.
METHODS: We conducted a retrospective case review of pilots diagnosed with CAD at the Institute of Aviation Medicine (IAM), Royal Malaysian Air Force (RMAF) in October 2020.
RESULTS: Thirteen cases of CAD were included in the review. Ten pilots were diagnosed after developing acute coronary syndrome; the remaining three pilots were diagnosed during a routine medical examination via an exercise stress test. Twelve pilots required a revascularization procedure. A total of 11 pilots (84.6%) were recertified for flying duties, while another two were disqualified. The duration to recertification for these 11 pilots was between three months and one year.
CONCLUSIONS: The risk assessment was initiated with initial risk-stratification using population-appropriate risk calculator combined with the 4 × 4 aeromedical risk matrix. The reassessment of return to flying after coronary artery disease must be carried out no sooner than six months after the event. Pilots must be hemodynamically stable with no evidence of significant inducible ischemic left and a minimum 50% of ventricular ejection fraction (LVEF). A follow-up is recommended at the initial six months after recertification and then annually with a routine noninvasive cardiac assessment.