SexEst: An open access web application for metric skeletal sex estimation

Skeletal sex estimation is an essential step in any osteoarcheological study; hence, several metric and morphological methods have been developed for this purpose, employing different skeletal elements. This paper has a dual purpose: (1) test the performance of machine learning classification models using worldwide samples cranial postcranial measurements (2) present free web application implementation that exhibit highest accuracy so unknown skeletons can be straightforwardly estimated. Regarding first objective, Goldman database metrics William W. Howells craniometric database, were constructed prediction. The optimized with respect to their hyperparameters cross-validated reaching accuracies ranging from 80.8%–89.5% data 81.2%–87.7% data. offering rates correct (Extreme Gradient Boosting, Light Linear Discriminant Analysis) then selected construct open access source application, SexEst, predicting skeletons.