Background: Identifying skeletal remains has been and will remain a challenge for forensic experts and forensic anthropologists, especially in disasters with multiple victims or skeletal remains in an advanced stage of decomposition. This study examined the performance of two machine learning (ML) algorithms in predicting the person’s sex based only on the morphometry of L1–L5 lumbar vertebrae collected recently from Romanian individuals. The purpose of the present study was to assess whether by using the machine learning (ML) techniques one can obtain a reliable prediction of sex in forensic identification based only on the parameters obtained from the metric analysis of the lumbar spine. Method: This paper built and tuned predictive models with two of the most popular techniques for classification, RF (random forest) and XGB (xgboost). Both series of models used cross-validation and a grid search to find the best combination of hyper-parameters. The best models were selected based on the ROC_AUC (area under curve) metric. Results: The L1–L5 lumbar vertebrae exhibit sexual dimorphism and can be used as predictors in sex prediction. Out of the eight significant predictors for sex, six were found to be particularly important for the RF model, while only three were determined to be important by the XGB model. Conclusions: Even if the data set was small (149 observations), both RF and XGB techniques reliably predicted a person’s sex based only on the L1–L5 measurements. This can prove valuable, especially when only skeletal remains are available. With minor adjustments, the presented ML setup can be transformed into an interactive web service, freely accessible to forensic anthropologists, in which, after entering the L1–L5 measurements of a body/cadaver, they can predict the person’s sex.

Introduction: Forensic identification practice requires a multitude of methods for positive identification, among which the facial reconstruction occupies a high place. For this to be done in the best way possible, it is mandatory that each population have their own database regarding soft tissue thickness. Objective: The present research is focused on creating such a database for the Romanian adult population and on exploring the statistical distribution and correlation of craniometric landmarks, overall, and in groups defined according to sex and weight categories. This might provide support in estimating the values of missing landmarks or other variables (e.g., age, sex) for unidentified bodies. Methods: Twelve craniometric landmarks were measured on 100 cadavers less than 24 h after death. Results and discussions: Of the 12 anatomical landmarks, only one appears to manifest statistically significant differences between sexes, and seven landmarks appear to vary significantly among the weight categories. Additionally, some evidence of interpopulation differences in the average soft tissue thicknesses were observed by the comparison of these data with similar studies from Caucasian groups with different geographic origin. Additionally, correlations between facial landmarks were examined, overall and between sexes.

Identifying skeletal remains has been and will remain a challenge for forensic doctors and forensic anthropologists, especially in disasters with multiple victims or skeletal remains in an advanced stage of decomposition. This study proposes a machine learning method to determine gender starting from morphometric analysis of L1-L5 lumbar vertebrae in a modern Romanian population. The purpose of the present study was to observe whether by using the ML method there is a good predictability of gender in forensic identification based on parameters obtained from the metric analysis of the lumbar spine specific to the Romanian population. This paper offers two models of ML, RF and XGB, each with its own characteristics, and presenting different performance, random forest having the best. For both, we used two metrics (accuracy and roc_auc), the latter being the most used to highlight model performance. The L1-L5 lumbar vertebrae exhibit sexual dimorphism and can be used in gender estimation. Machine learning is more accurate in determining gender than discriminatory function analysis.