Reassociation of Skeletal Remains Using Laser-Induced Breakdown Spectroscopy.

A major challenge in forensic anthropology and bioarcheology is the development of fast and effective methods for sorting commingled remains. This study assesses how portable laser-induced breakdown spectroscopy (LIBS) can be used to group skeletal remains based on their elemental profiles. LIBS spectra were acquired from the remains of 45 modern skeletons, with a total data set of 8388 profiles from 1284 bones. Spectral feature selection was conducted to reduce the spectral profiles to the peaks exhibiting the highest variation among individuals. Emission lines corresponding to 9 elements (Ca, P, C, K, Mg, Na, Al, Ba, and Sr) were found important for classification. Linear discriminant analysis (LDA) was concurrently used to classify each spectral profile. From the 45 individuals, each LIBS spectrum was successfully sorted to its corresponding skeleton with an average accuracy of 87%. These findings indicate that variation exists among the LIBS profiles of individuals' skeletal remains, highlighting the potential for portable LIBS technology to aid in the sorting of commingled remains.

Awareness of forensic anthropology in Switzerland: a survey among forensic practitioners, police, and prosecutors.

Forensic anthropology (FA) as a specialized discipline has been practised in multi-lingual Switzerland for over a decade. A variety of expertise regarding osteological assessments as well as facial image comparison (FIC) is provided by different centres. Nevertheless, information is lacking about the awareness of FA and its benefits for forensic investigations among forensic stakeholders. Therefore, a survey was sent to Swiss anthropologists (AN) and related professions (police officers, prosecutors, and forensic pathologists) to assess three main aspects: (1) the experience of working (biological/forensic) anthropologists within FA; (2) how FA is perceived by other professions within the legal system; and (3) identify gaps (if any) in understanding of FA with the aim to suggest avenues for improvement if necessary. The results show that awareness of FA varies by occupation and cantonal regions. In areas where close collaborations between forensic anthropologists (FAs) and other stakeholders have been formally established, be it with focus on osteological analyses or FIC, the awareness of FA competencies was superior to areas where this was not the case. An overwhelming majority of forensic actors expressed interest in continuing education related to the role of FA. These findings indicate that facilitation of communication and collaboration leads to improvement in the awareness of the competencies of FAs and their contribution to forensic investigations.

Demonstrating the empirical effect of population specificity of anthropological standards in a contemporary Australian population.

The ability to differentiate individuals based on their biological sex is essential for the creation of an accurate anthropological assessment; it is therefore crucial that the standards that facilitate this are likewise accurate. Given the relative paucity of population-specific anthropological standards formulated specifically for application in the contemporary Australian population, forensic anthropological assessments have historically relied on the application of established methods developed using population geographically and/or temporally disparate. The aim of the present paper is, therefore, to assess the accuracy and reliability of established cranial sex estimation methods, developed from geographically distinct populations, as applied to the contemporary Australian population. Comparison between the original stated accuracy and sex bias values (where applicable) and those achieved after application to the Australian population provides insight into the importance of having anthropological standards optimised for application in specific jurisdictions. The sample analysed comprised computed tomographic (CT) cranial scans of 771 (385 female and 386 male) individuals collected from five Australian states/territories. Cranial CT scans were visualised as three-dimensional volume-rendered reconstructions using OsiriX®. On each cranium, 76 cranial landmarks were acquired, and 36 linear inter-landmark measurements were calculated using MorphDB. A total of 35 predictive models taken from Giles and Elliot (1963), Iscan et al. (1995), Ogawa et al. (2013), Steyn and Iscan (1998) and Kranioti et al. (2008) were tested. Application to the Australian population resulted in an average decrease in accuracy of 21.2%, with an associated sex bias range between - 64.0 and 99.7% (average sex bias value of 29.6%), relative to the original studies. The present investigation has highlighted the inherent inaccuracies of applying models derived from geographically and/or temporally disparate populations. It is, therefore, imperative that statistical models developed from a population consistent with the decedent be used for the estimation of sex in forensic casework.

Transcending time: the forensic anthropological case study of three unidentified transgender women in Italy in the early 1990s.

In forensic anthropology, the estimation of skeletal sex results in a dichotomous outcome: male or female. This poses challenges when dealing with transgender individuals. Italy has the highest rate per capita of transgender murders, making their identification a compelling issue. This study presents three cases of unidentified skeletal remains of transgender women (MtF) that underwent autopsies in the 1990s at the Institute of Legal Medicine of Milan. The transgender status of the individuals was determined from the autopsy records which indicated the co-existence of breast implants and male genitalia. The biological profile was created by estimating sex, age, ancestry, and stature, and the bones were investigated looking for evidence of Facial Feminization Surgery (FFS). Anthropological estimations revealed that the skeletons belong to male, adults, European individuals, between 164 and 184 cm. Fragmented gelatinous masses were found in association with two skeletons, which were interpreted as remnants of breast implants. In two cases, signs of remodeling of the cortical surface were observed on the zygomatic bones, although the bone marks observed here were not specific enough to link them to FFS. Despite some limitations, this study highlights the need for greater awareness among practitioners about this limitedly addressed issue, advocating for a more inclusive forensic anthropology that strives to improve methods and interpretation of evidence for the identification of transgender individuals.

The influence of age on greater sciatic notch morphology: testing the Walker method in an Australian population.

Sex estimation is an integral aspect of a forensic biological profile. The pelvis, being the most dimorphic part of the skeleton, has been studied in considerable detail relative to morphological and metric variation. However, empirical data on the effect of age on pelvic morphology relative to sex-specific morphological variation is limited, especially in regard to the estimation of skeletal sex. This study assesses whether there are age-related differences in the distribution of the Walker (2005) morphological scores for the greater sciatic notch (GSN) in an Australian population. Three-dimensional volumetric reconstructions derived from multi-detector computed tomography (MDCT) scans of 567 pelves of 258 females and 309 males aged 18 to 96 years were scored following Walker (2005). Differences in score distributions and means by sex and age group were tested using Pearson's chi-squared test and ANOVA, respectively. The accuracy of sex estimates derived from logistic regression equations was explored using leave-one-out cross-validation. Significant differences were found in score distribution and means among age groups in females, but not in males. There was a tendency toward higher scores in older females. The overall sex estimation accuracy was 87.5%. When comparing age groups 18-49 and 70 + years, estimation accuracy decreased in females (99% vs. 91%), while the opposite was found for males (79% vs. 87%). These findings suggest that age affects GSN morphology. Higher mean scores in older females imply that, on average, the GSN becomes narrower with increasing age. It is thus recommended due consideration of estimated age when assessing sex based on the GSN in unidentified human remains.

A comparison of maceration methods for the preparation of infant skeletal remains for forensic anthropological analysis.

Very little literature currently exists prescribing which maceration method to use when preparing infant human remains, resulting in bone quality that is suitable for forensic anthropological analysis. The aim of the study was to test five maceration methods to determine which is most suitable for infant remains for forensic anthropological analysis. The sample included five neonate pig carcasses (Sus scrofa domesticus), ranging between one to three days old. Five maceration methods were tested on the pig carcasses (one pig per maceration method) to determine their effectiveness. The methods included invertebrate maceration by meal worms, chemical maceration by bleach, chemical maceration by borax solution, enzymatic maceration by laundry detergent and sodium carbonate solution, and chemical maceration by sodium hypochlorite. A scoring method was created to assess the effectiveness of each maceration method. Invertebrate maceration and chemical maceration using bleach were the least successful methods of maceration (total maceration score = 8 respectively). Chemical maceration using borax and chemical maceration using sodium hypochlorite achieved complete maceration of the skeletal remains; however, they both resulted in artifacts that are unsuitable for forensic analysis (total maceration score = 14 respectively). Enzymatic maceration using laundry detergent and sodium carbonate was the most successful method (total maceration score = 17). The detergent technique subsequently successfully macerated all five sets of infant human remains. This study has validated that the enzymatic maceration technique using laundry detergent and sodium carbonate can be used to effectively macerate the remains of infant skeletal remains for forensic anthropological analysis.

Comparison of false starts by saw created on flesh and dry bones; as close as possible to the real conditions of criminal dismemberment.

In most experimental protocols, false starts are produced on dry bones obtained through a maceration process for anthropological analyses, for the sake of reproducibility. Although this allows for controlled experimental conditions, the absence of soft parts when experimentally creating false starts does not correspond to the real conditions of criminal dismemberment. The main objective of this study was to determine if the results of experimental work on the characteristics of false starts were valid under medico-legal conditions. In this experimental study, a hand saw (rip saw, wavy set, TPI 32) was used. 240 false starts were produced on human and pig bones. Randomly, the false starts were either produced on a dry bone or on a flesh bone. The criteria for microscopic analysis included the shape of the walls, the shape and visibility of striae on the floor, the shape of the profile, and the minimum width of the false start. On human bone, 100% of the false starts produced on a bone that had previously undergone a maceration process for anthropological analyses (dry bone) allowed the definition of all the blade characteristics. This was the case for 78.3% on bone in the presence of soft tissue (flesh bone). The striae on the floor of the false start are in some cases less visible with flesh bones, implying that it may be more difficult to conclude on the characteristics of a saw under medico-legal conditions.

Testing the accuracy of the DRNNAGE software for age estimation in a modern Greek sample.

Estimation of age-at-death from human skeletal remains is fundamental in forensic anthropology as part of the construction of the biological profile of the individual under study. At the same time, skeletal age-at-death estimation in adults is problematic due to the disparity between chronological and biological age, the important inter-individual variability at the rate of skeletal aging, and inherent biases in the available methodologies (e.g., age mimicry). A recent paper proposed a method for skeletal age-at-death estimation based on multiple anatomical traits and machine learning. A software was also created, DRNNAGE, for the easy implementation of this method. The authors of that study supported that their methods have very high repeatability and reproducibility, and the mean absolute error of the age estimation was ~6 years across the entire adult age span, which is particularly high and promising. This paper tests the proposed methodology on a modern documented Greek sample of 219 adult individuals from the Athens Collection, with age-at-death from 19 to 99 years old. The sample was split into males and females as well as into individuals under and over 50 years old. We also divided the sample in 10-year intervals. First, intra- and inter-observer error was estimated in order to assess repeatability and reproducibility of the variables employed for age-at-death estimation. Then, the validity (correct classification performance) of DRNNAGE for each anatomical region individually, as well as all combined, was evaluated on each demographic separately and on the pooled sample. According to the results, some of the variables showed very low repeatability and reproducibility, thus their use should be cautious. The DRNNAGE software showed overall highly accurate age-at-death estimates for individuals older than 50 years, but poor on younger adults, with only exception the cranial sutures, which performed surprisingly well for all age groups. Overall, these results support the importance of cross-validation and the use of population-specific methods in forensic anthropology.

Validation and recalibration of sex estimation methods using pubic nonmetric traits for the Chilean population.

Chile had a violent military coup (1973-1990) that resulted in 3,000 victims declared detained, missing or killed; many are still missing and unidentified. Currently, the Human Rights Unit of the Forensic Medical Service in Chile applies globally recognised forensic anthropological approaches, but many of these methods have not been validated in a Chilean sample. As current research has demonstrated population-specificity with extant methods, the present study aims to validate sex estimation methods in a Chilean population and thereafter establish population-specific equations. A sample of 265 os coxae of known age and sex of adult Chileans from the Santiago Subactual Osteology Collection were analysed. Visual assessment and scoring of the pelvic traits were performed in accordance with the Phenice (1969) and Klales et al. (2012) methods. The accuracy of Phenice (1969) in the Chilean sample was 96.98%, with a sex bias of 7.68%. Klales et al. (2012) achieved 87.17% accuracy with a sex bias of -15.39%. Although both methods showed acceptable classification accuracy, the associated sex bias values are unacceptable in forensic practice. Therefore, six univariate and eight multivariate predictive models were formulated for the Chilean population. The most accurate univariate model was the ventral arc at 96.6%, with a sex bias of 5.2%. Classification accuracy using all traits was 97.0%, with a sex bias of 7.7%. This study provides Chilean practitioners a population-specific morphoscopic standard with associated classification probabilities acceptable to accomplish legal admissibility requirements in human rights and criminal cases specific to the second half of the 20th century.

Comparison of the effectiveness and efficiency of the grid and link search methods to recover scattered skeletal remains.

The grid and link search methods are used to recover scattered skeletal remains. Neither have not been compared robustly and clear guidelines for the link method have not been sufficiently developed. The study aimed to compare the effectiveness and efficiency of both methods and propose guidelines for the link method. The scattering patterns of two scavengers of forensic relevance-slender mongooses (Galerella sanguinea) and black-backed jackals (Canis mesomelas)-were recreated using four pig skeletons (Sus scrofa domesticus). Two groups (n = 6 each) were assigned a different method to recover the scattered remains. The length of the search and when each bone was located for each scatter pattern was recorded for each group and scatter pattern. A Likert scale questionnaire assessed participants' perceptions of their assigned method. A paired t-test (p = 0.005) compared the efficiency of each method and the questionnaire answers. Both methods were effective, recovering 100% of all remains. The link method was more efficient for both scatter patterns, despite there being no statistical significance (jackal: p = 0.089; mongoose: p = 0.464). Participants indicated favorable views for both methods; however, the link method scored significantly more favorably (p = 0.01) for efficiency. Specific guidelines were developed for the use of the link method. The link method is suggested for the recovery of scattered remains in forensic contexts, especially when the scavenger, its behavior, and scattering pattern is known or suspected.

Validation of age estimation methods through the scapula in a Mediterranean non-adult population.

Age estimation methods through the metric study of bones in non-adult individuals are a frequently used tool in Biological and Forensic Anthropology; however, few methodological validation studies are available, given the limited number of adequate samples for their study. In this context, the aim of this work is to test the effectiveness of the methods of Fazekas and Kósa (1978), Saunders et al. (1993), Rissech and Black (2007) and Cardoso et al. (2017), for age estimation through the measurements of the scapula, in the non-adult osteological collection of the Anthropology Laboratory of the University of Granada (Spain), one of the most representative identified non-adult collections internationally. For this purpose, nine different measurements of the scapula were taken from a total of 149 non-adult individuals, applying the regression formulae proposed by the different authors and verifying their accuracy. Results have shown the existence of significant differences between the real age and the estimated age in almost all the tested methods, with degrees of error that differ from those obtained in the original study populations. Based on the obtained results, it is recommended to use the method of Cardoso et al. in postnatal individuals, always adjusting the degrees of error with those obtained in this work.

Estimation of ancestry from cranial measurements based on MDCT data acquired in a Japanese and Western Australian population.

The estimation of ancestry is important not only towards establishing identity but also as a required precursor to facilitating the accurate estimation of other attributes such as sex, age at death, and stature. The present study aims to analyze morphological variation in the crania of Japanese and Western Australian individuals and test predictive models based on machine learning for their potential forensic application. The Japanese and Western Australian samples comprise computed tomography (CT) scans of 230 (111 female; 119 male) and 225 adult individuals (112 female; 113 male), respectively. A total of 18 measurements were calculated, and machine learning methods (random forest modeling, RFM; support vector machine, SVM) were used to classify ancestry. The two-way unisex model achieved an overall accuracy of 93.2% for RFM and 97.1% for SVM, respectively. The four-way sex and ancestry model demonstrated an overall classification accuracy of 84.0% for RFM and 93.0% for SVM. The sex-specific models were most accurate in the female samples (♀ 95.1% for RFM and 100% for SVM; ♂91.4% for RFM and 97.4% for SVM). Our findings suggest that cranial measurements acquired in CT images can be used to accurately classify Japanese and Western Australian individuals into their respective population. This is the first study to assess the feasibility of ancestry estimation using three-dimensional CT images of the skull.

Exploring cranial macromorphoscopic variation and classification accuracy in a South African sample.

To date South African forensic anthropologists are only able to successfully apply a metric approach to estimate population affinity when constructing a biological profile from skeletal remains. While a non-metric, or macromorphoscopic approach exists, limited research has been conducted to explore its use in a South African population. This study aimed to explore 17 cranial macromorphoscopic traits to develop improved methodology for the estimation of population affinity among black, white and coloured South Africans and for the method to be compliant with standards of best practice. The trait frequency distributions revealed substantial group variation and overlap, and not a single trait can be considered characteristic of any one population group. Kruskal-Wallis and Dunn's tests demonstrated significant population differences for 13 of the 17 traits. Random forest modelling was used to develop classification models to assess the reliability and accuracy of the traits in identifying population affinity. Overall, the model including all traits obtained a classification accuracy of 79% when assessing population affinity, which is comparable to current craniometric methods. The variable importance indicates that all the traits contributed some information to the model, with the inferior nasal margin, nasal bone contour, and nasal aperture shape ranked the most useful for classification. Thus, this study validates the use of macromorphoscopic traits in a South African sample, and the population-specific data from this study can potentially be incorporated into forensic casework and skeletal analyses in South Africa to improve population affinity estimates.

Classification performance of the Sella-Tunis et al. (2017) sex estimation method in Czech population: different posterior probability threshold approaches.

In this study we tested classification performance of a sex estimation method from the mandible originally developed by Sella-Tunis et al. (2017) on a heterogeneous Israeli population. Mandibular linear dimensions were measured on 60 CT scans derived from the Czech living population. Classification performance of Israeli discriminant functions (DFs-IL) was analyzed in comparison with calculated Czech discriminant functions (DFs-CZ) while different posterior probability thresholds (currently discussed in the forensic literature) were employed. Our results comprehensively illustrate sensitivity of different discriminant functions to population differences in body size and degree of sexual dimorphism. We demonstrate that the error rate may be biased when presented per posterior probability threshold. DF-IL 1 showed least sensitivity to population origin and fulfilled criteria of sufficient classification performance when applied on the Czech sample with a minimum posterior probability threshold of 0.88 reaching overall accuracy ≥ 95%, zero sex bias, and 80% of classified individuals. The last parameter was higher in DF-CZ 1 which was the main difference between those two DFs suggesting relatively low dependance on population origin. As the use of population-specific methods is often prevented by complicated assessment of population origin, DF-IL 1 is a candidate for a sufficiently robust method that could be reliably applied outside the reference sample, and thus, its classification performance deserves further testing on more population samples.

Estimation of population affinity using proximal femoral measurements based on computed tomographic images in the Japanese and western Australian populations.

The present study analyzes morphological differences femora of contemporary Japanese and Western Australian individuals and investigates the feasibility of population affinity estimation based on computed tomographic (CT) data. The latter is deemed to be of practical importance because most anthropological methods rely on the assessment of aspects of skull morphology, which when damaged and/or unavailable, often hampers attempts to estimate population affinity. The study sample comprised CT scans of 297 (146 females; 151 males) Japanese and 330 (145 females; 185 males) Western Australian adult individuals. A total of 10 measurements were acquired in two-dimensional CT images of the left and right femora; two machine learning methods (random forest modeling [RFM]) and support vector machine [SVM]) were then applied for population affinity classification. The accuracy of the two-way (sex-specific and sex-mixed) model was between 71.38 and 82.07% and 76.09-86.09% for RFM and SVM, respectively. Sex-specific (female and male) models were slightly more accurate compared to the sex-mixed models; there were no considerable differences in the correct classification rates between the female- and male-specific models. All the classification accuracies were higher in the Western Australian population, except for the male model using SVM. The four-way sex and population affinity model had an overall classification accuracy of 74.96% and 79.11% for RFM and SVM, respectively. The Western Australian females had the lowest correct classification rate followed by the Japanese males. Our data indicate that femoral measurements may be particularly useful for classification of Japanese and Western Australian individuals.

Population affinity estimation using pelvic measurements based on computed tomographic data acquired from Japanese and Western Australian populations.

The present study analyzes morphological differences in the pelvis of Japanese and Western Australian individuals and investigates the feasibility of population affinity classification based on computed tomography (CT) data. The Japanese and Western Australian samples comprise CT scans of 207 (103 females; 104 males) and 158 (78 females; 80 males) adult individuals, respectively. Following volumetric reconstruction, a total of 19 pelvic landmarks were obtained on each sample, and 11 measurements, including two angles, were calculated. Machine learning methods (random forest modeling [RFM] and support vector machine [SVM]) were used to classify population affinity. Classification accuracy of the two-way models was approximately 80% for RFM: the two-way sex-specific and sex-mixed models for SVM achieved > 90% and > 85%, respectively. The sex-specific models had higher accurate classification rates than the sex-mixed models, except for the Japanese male sample. The classification accuracy of the four-way sex and population affinity model had an overall classification accuracy of 76.71% for RFM and 87.67% for SVM. All the correct classification rates were higher in the Japanese relative to the Western Australian sample. Our data suggest that pelvic morphology is sufficiently distinct between Japanese and Western Australian individuals to facilitate the accurate classification of population affinity based on measurements acquired in CT images. To the best of our knowledge, this is the first study investigating the feasibility of population affinity estimation based on CT images of the pelvis, which appears as a viable supplement to traditional approaches based on cranio-facial morphology.

Human identification: an investigation of 3D models of paranasal sinuses to establish a biological profile on a modern UK population.

Medical imaging is a valuable source for facilitating empirical research and provides an accessible gateway for developing novel forensic anthropological methods for analysis including 3D modelling. This is especially critical for the United Kingdom (UK), where methods developed from modern UK populations do not currently exist. This study introduces a new approach to assist in human identification using 3D models of the paranasal sinuses. The models were produced from a database of 500 modern CT scans provided by University College London Hospital. Linear measurements and elliptic Fourier coefficients taken from 1500 three-dimensional models across six ethnic groups assessed by one-way ANOVA and discriminant function analysis showed a range of classification rates with certain rates reaching 75-85.7% (p < 0.05) in correctly classifying age and sex according to size and shape. The findings offer insights into the potential for employing paranasal sinuses as an attribute for establishing the identification of unknown human remains in future crime reconstructions.

Forensic age estimation in adults based on multidetector computed tomography analysis of bone density in the medial meta-epiphyseal region of clavicle.

The aim of this study was to investigate the potential of using multidetector computed tomography (MDCT) to measure the bone mineral density (BMD) in the medial meta-epiphyseal region of clavicle (MERC) for adult age estimation. A total of 1064 chest MDCT scans from individuals aged 21 to 102 years were utilized to determine the MERC BMD. The Mimics software was used for the BMD measurements, and the average BMD of both MERC was also calculated. Regression analysis was conducted with chronological age as a dependent variable and MERC BMD as an independent variable to establish a mathematical model for age estimation. The mean absolute error (MAE) was calculated to evaluate the accuracy of the regression model using an independent validation sample. Among all the models, the cubic regression model showed the highest correlation between MERC BMD and chronological age and also provided the most accurate age prediction for both males and females (MAE = 9.41 for males, MAE = 10.38 for females). Our study suggests that BMD measured by MERC can be utilized for age estimation in adults when more reliable indicators are not available.

Exploratory analysis of new craniometric measures for the investigation of biological sex using open-access statistical and machine-learning tools on a cone-beam computed tomography sample.

Investigation of the biological sex of human remains is a crucial aspect of physical anthropology. However, due to varying states of skeletal preservation, multiple approaches and structures of interest need to be explored. This research aims to investigate the potential use of distances between bifrontal breadth (FMB), infraorbital foramina distance (IOD), nasal breadth (NLB), inter-canine width (ICD), and distance between mental foramina (MFD) for combined sex prediction through traditional statistical methods and through open-access machine-learning tools. Ethical approval was obtained from the ethics committee, and out of 100 cone beam computed tomography (CBCT) scans, 54 individuals were selected with all the points visible. Ten extra exams were chosen to test the predictors developed from the learning sample. Descriptive analysis of measurements, standard deviation, and standard error were obtained. T-student and Mann-Whitney tests were utilized to assess the sex differences within the variables. A logistic regression equation was developed and tested for the investigation of the biological sex as well as decision trees, random forest, and artificial neural networks machine-learning models. The results indicate a strong correlation between the measurements and the sex of individuals. When combined, the measurements were able to predict sex using a regression formula or machine learning based models which can be exported and added to software or webpages. Considering the methods, the estimations showed an accuracy rate superior to 80% for males and 82% for females. All skulls in the test sample were accurately predicted by both statistical and machine-learning models. This exploratory study successfully established a correlation between facial measurements and the sex of individuals, validating the prediction potential of machine learning, augmenting the investigative tools available to experts with a high differentiation potential.

Sex estimation from coxal bones using deep learning in a population balanced by sex and age.

In the field of forensic anthropology, researchers aim to identify anonymous human remains and determine the cause and circumstances of death from skeletonized human remains. Sex determination is a fundamental step of this procedure because it influences the estimation of other traits, such as age and stature. Pelvic bones are especially dimorphic, and are thus the most useful bones for sex identification. Sex estimation methods are usually based on morphologic traits, measurements, or landmarks on the bones. However, these methods are time-consuming and can be subject to inter- or intra-observer bias. Sex determination can be done using dry bones or CT scans. Recently, artificial neural networks (ANN) have attracted attention in forensic anthropology. Here we tested a fully automated and data-driven machine learning method for sex estimation using CT-scan reconstructions of coxal bones. We studied 580 CT scans of living individuals. Sex was predicted by two networks trained on an independent sample: a disentangled variational auto-encoder (DVAE) alone, and the same DVAE associated with another classifier (Crecon). The DVAE alone exhibited an accuracy of 97.9%, and the DVAE + Crecon showed an accuracy of 99.8%. Sensibility and precision were also high for both sexes. These results are better than those reported from previous studies. These data-driven algorithms are easy to implement, since the pre-processing step is also entirely automatic. Fully automated methods save time, as it only takes a few minutes to pre-process the images and predict sex, and does not require strong experience in forensic anthropology.