New random generalized linear model for sex determination based on cranial measurements

Lescure, Javier; Ardevines, Claudia; Becerra, Paula; Marrodán, María Dolores

doi:10.1007/s12520-020-01145-8

Cited by 5 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, considering that throughout human history there has been notable mobility, it may not always be optimum to use population‐specific models but instead adopt a broader reference sample (see, e.g., a similar approach adopted by Ruff et al, 2012, for European Holocene stature and body mass estimation). Indeed, it has been supported by other scholars as well that population‐specific sex prediction equations “are not as applicable in archeological contexts, in which the geographical or genetic origin of individuals is rarely known…In this kind of context, a method that is not temporally or geographically limited by the sample used to create it is preferable …” (Lescure et al, 2020, p. 4). We would like to urge authors to test the performance of SexEst in different collections and assess the necessity to employ population‐specific models.…”

Section: Discussionmentioning

confidence: 99%

“…This is the reason why we developed SexEst having in mind primarily osteoarcheological applications rather than forensic anthropological ones, where we cannot guarantee that these models meet the Daubert standard. Nonetheless, a recent study that developed sex prediction models using five variables from the Howells database and tested them on a documented modern American assemblage (Forensic Data Bank) achieved 86.26% precision in sex classification, which suggests that the Howells database has the potential to offer accurate sex predictions (Lescure et al, 2020). We believe that using sex prediction equations based on pre-industrial assemblages conveys an important advantage to osteoarcheologists, which outweighs the limitation that such equations are based on individuals with nondocumented sex.…”

Section: Web Applicationmentioning

confidence: 99%

See 1 more Smart Citation

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

Constantinou

Nikita

2022

Intl J of Osteoarchaeology

View full text Add to dashboard Cite

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 several machine learning classification models for skeletal sex estimation using worldwide samples of cranial and postcranial measurements and (2) present a free web application for the implementation of the models that exhibit the highest accuracy so that the sex of unknown skeletons can be straightforwardly estimated. Regarding the first objective, using the Goldman database of postcranial metrics and the William W. Howells craniometric database, machine learning classification models were constructed for sex prediction. The models were optimized with respect to their hyperparameters and cross‐validated reaching accuracies ranging from 80.8%–89.5% for the postcranial data and 81.2%–87.7% for the cranial data. The models offering the highest rates of correct sex classification (Extreme Gradient Boosting, Light Gradient Boosting, and Linear Discriminant Analysis) were then selected to construct an open access and open source web application, SexEst, for predicting the sex of unknown skeletons.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Web Applicationmentioning

confidence: 99%

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

Constantinou

Nikita

2022

Intl J of Osteoarchaeology

View full text Add to dashboard Cite

show abstract

“…Since the Goldman and Howells datasets consist mostly of pre-industrial individuals, their sex was skeletally estimated by Benjamin Auerbach and William Howells, respectively. While it is acknowledged that the absence of documented sex and the variability in levels of sexual dimorphism across populations pose limitations, studies using these collections have achieved high accuracy rates in sex estimation (e.g., Lescure et al, 2020). In addition, SexEst was developed for use primarily in archeological contexts, where the advantages of using pre-industrial assemblages for sex estimation compared with using modern forensic standards would be substantial due to issues related to secular change.…”

Section: Introductionmentioning

confidence: 99%

Testing the accuracy of the SexEst software for sex estimation in a modern Greek sample

Nikita,

Garoufi,

Valakos

et al. 2024

Intl J of Osteoarchaeology

View full text Add to dashboard Cite

Sex estimation from human skeletal remains is fundamental in osteoarcheology and forensic anthropology. The increasing availability of reference skeletal collections across the world has allowed the development of morphological and metric methods for skeletal sex estimation, some of which may be implemented in specialized computer software. The present study aims to evaluate the freely available SexEst software, which utilizes cranial and postcranial measurements, and different classification models for sex estimation, on a contemporary Greek population comprising of 227 (126 males and 101 females) adult individuals. After the calculation of intra‐observer error to assess the repeatability of the measurements, the proposed variables were tested for classification accuracy individually and in different combinations. Based on the results, the postcranial models outperformed the cranial ones in all cases and can be adequately applied on a Greek population sample. The light gradient boosting (LGB) algorithm yielded the highest correct classification rates when no missing values exist, while the linear discriminant analysis (LDA) models should only be used when dealing with missing data. The highest classification accuracy for a 0.65 posterior probability threshold was reached when utilizing a combination of postcranial variables (89.67%), while the lowest was achieved with the cranial measurement “Glabella‐occipital length” (45.00%). The same models yielded the highest and lowest accuracy for a 0.5 probability threshold, with values of 92.96% and 67.73%, respectively. Combining variables yielded higher accuracies in both skeletal regions, suggesting that the software would be more helpful in cases of intact skeletons. The loss of classification accuracy due to population specificity further corroborates the need to include different ancestries in sex estimation software.

show abstract