Estimation of gender by using decision tree, a machine learning algorithm, with patellar measurements obtained from MDCT images

Aim: The present study aimed to analyze whether gender could be determined with the decision tree (DT) method, a machine learning algorithm, based on patellar multidetector computed tomography (MDCT) image measurements. Material and Methods: was conducted 219 male 131 female MDCT images. anteroposterior (Ap), craniocaudal (Cc), transverse (Trv) length volume (Vol), adjusted orthogonal plane by radiologist, were calculated. In measurements, initially linear discriminant outliers detected clear data for prediction. Accuracy (Acc), Sensitivity (Sen), Specificity (Spe), F1-Score (F1) Matthew’s Correlation Coefficient (Mcc) criteria taken as performance DT. Results: It that Ap, Trv, Cc, Vol values higher when compared there significant difference between these (pAp, = 0.000). Using above-mentioned it calculated prediction rate individuals 98.2% individuals, 98.4%. Conclusion: DT analysis patella morphometry provided simple, adequate highly accurate approach estimation. Furthermore, would provide an advantage researchers in using only branching cut-off structure without need use computer.