Performance of the Machine Learning Algorithm in Stature Estimation Using Scapula Measurements from Post-Mortem Computed Tomography in a Thai Male Population

Abstract

Objective: This study attempted to investigate the performance of stature prediction models from scapular dimensions based on post-mortem computed tomography (PMCT) using machine learning algorithms within the male population of Southern Thailand.Material and Methods: Linear Regression (LR), K-Nearest Neighbors (KNN), Random Forest tree (RF), and Support vector machine (SVM) algorithms were used to create the stature estimation model. Then its performance was compared by coefficient of determination (R2), mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE).Results: Machine learning is a valuable tool for estimating stature within this demographic. LR algorithm provided the best performance matrices, with the highest R2 being 0.316, and the lowest values for MAE, MSE, and RMSE being 4.379 cm, 29.530 cm, and 5.382 cm, respectively.Conclusion: The machine learning algorithm demonstrated valuable tools for estimation stature. However, it is essential to note that complex machine learning models do not always produce better performance measures than non-complex models.