In forensic anthropology, ancestry estimation is essential in establishing the individual biological profile. The aim of this study is to present a new program--AncesTrees--developed for assessing ancestry based on metric analysis. AncesTrees relies on a machine learning ensemble algorithm, random forest, to classify the human skull. In the ensemble learning paradigm, several models are generated and co-jointly used to arrive at the final decision. The random forest algorithm creates ensembles of decision trees classifiers, a non-linear and non-parametric classification technique. The database used in AncesTrees is composed by 23 craniometric variables from 1,734 individuals, representative of six major ancestral groups and selected from the Howells' craniometric series. The program was tested in 128 adult crania from the following collections: the African slaves' skeletal collection of Valle da Gafaria; the Medical School Skull Collection and the Identified Skeletal Collection of 21st Century, both curated at the University of Coimbra. The first step of the test analysis was to perform ancestry estimation including all the ancestral groups of the database. The second stage of our test analysis was to conduct ancestry estimation including only the European and the African ancestral groups. In the first test analysis, 75% of the individuals of African ancestry and 79.2% of the individuals of European ancestry were correctly identified. The model involving only African and European ancestral groups had a better performance: 93.8% of all individuals were correctly classified. The obtained results show that AncesTrees can be a valuable tool in forensic anthropology.

The purpose of this study is to characterize and contextualize the new collection of This collection constitutes a fundamental tool for forensic anthropology research, including development and validation studies of skeletal aging and sexing methods that target elderly adults. Moreover, this collection can also be used in conjunction with the other reference collections housed in the University of Coimbra to investigate secular trends in skeletal development and aging, among others.

Biological sex estimation is one of the main parameters required in the construction of a biological profile of an unknown deceased person. In corpses in an advanced state of decomposition, skeletonized or severely mutilated, bone analysis may provide the only way to access biological sex. Although the hip bones are the most dimorphic and useful bones for sex estimation, they are often badly preserved and/or fragmented or may not even be present in some cases. For that reason, it is necessary to develop sex estimation methods based on bones less dimorphic. In this study, 13 dimensions of the second cervical vertebra were measured in order to quantify sex-related variation and to generate a simple predictive model based on logistic regression analysis. For logistic regression fitting, 190 individuals from the Coimbra Identified Skeletal Collection were used as a training sample. The resulting model was also evaluated in an independent test sample composed of 47 individuals from the Identified Skeletal Collection of the 21st Century (University of Coimbra). The developed logistic regression model correctly estimated known sex in 86.7 to 89.7 % of the cases. The second cervical vertebra demonstrated to be a useful alternative for sex estimation when other skeletal elements are not available or suitable for analysis. This method seems promising but more reliability studies are required for a more robust validation.

Age at death estimation in adult skeletons is hampered, among others, by the unremarkable correlation of bone estimators with chronological age, implementation of inappropriate statistical techniques, observer error, and skeletal incompleteness or destruction. Therefore, it is beneficial to consider alternative methods to assess age at death in adult skeletons. The decrease in bone mineral density with age was explored to generate a method to assess age at death in human remains. A connectionist computational approach, artificial neural networks, was employed to model femur densitometry data gathered in 100 female individuals from the Coimbra Identified Skeletal Collection. Bone mineral density declines consistently with age and the method performs appropriately, with mean absolute differences between known and predicted age ranging from 9.19 to 13.49 years. The proposed method-DXAGE-was implemented online to streamline age estimation. This preliminary study highlights the value of densitometry to assess age at death in human remains.

Sex estimation is extremely important in the analysis of human remains as many of the subsequent biological parameters are sex specific (e.g., age at death, stature, and ancestry). When dealing with incomplete or fragmented remains, metric analysis of the tarsal bones of the feet has proven valuable. In this study, the utility of 18 width, length, and height tarsal measurements were assessed for sex-related variation in a Portuguese sample. A total of 300 males and females from the Coimbra Identified Skeletal Collection were used to develop sex prediction models based on statistical and machine learning algorithm such as discriminant function analysis, logistic regression, classification trees, and artificial neural networks. All models were evaluated using 10-fold cross-validation and an independent test sample composed of 60 males and females from the Identified Skeletal Collection of the 21st Century. Results showed that tarsal bone sex-related variation can be easily captured with a high degree of repeatability. A simple tree-based multivariate algorithm involving measurements from the calcaneus, talus, first and third cuneiforms, and cuboid resulted in 88.3% correct sex estimation both on training and independent test sets. Traditional statistical classifiers such as the discriminant function analysis were outperformed by machine learning techniques. Results obtained show that machine learning algorithm are an important tool the forensic practitioners should consider when developing new standards for sex estimation.