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.
CASE PRESENTATION: Here, we present two cases of immunocompetent patients with long-standing, progressively enlarging parotid swelling. Postoperative histopathological examination of these patients revealed features of BLEC.
CONCLUSION: Wide surgical excision is the gold standard for treatment and recurrences is rare. These cases are of particular interest because of the rarity of BLEC in HIV-negative patients and highlight an important differential diagnosis of parotid swelling.