Sex determination based on craniometric parameters: a comparative approach between linear and non-linear machine learning algorithms


  • Matheus Jhonnata Santos Mota
  • Alberto Calson Alves Vieira
  • Lucas Silva Lima
  • João Victor Melquiades Sátiro
  • Carlos Mathias de Menezes Neto
  • Patrízia Lisieux Prado Paixão
  • Gabriel Pedro Gonçalves Lopes
  • Lauro Roberto de Azevedo Setton
  • Carlos Eduardo de Andrade
  • Richard Halti Cabral



regression analysis, forensic anthropology, machine learning, cephalometry, x determination from the skeleton


Introduction: Determining sex based on cranial characteristics is of great relevance in forensic anthropology. Most studies have employed linear methods (such as logistic regression) for this estimation with accuracies around 70%, rarely exceeding 90% accuracy. Several authors have tested non-linear models such as neural networks, support vector machines, and decision trees with good results, surpassing linear models. Objective: To compare linear models (logistic regression, linear regression, and linear discriminant analysis) with non-linear models (neural networks, extreme gradient boosting, support vector machine, naive Bayes, random forest, decision tree, k-nearest neighbors, and adaptive multivariate spline regression). Materials and Methods: 241 skulls used in this study were obtained from the collection of Center for Study and Research in Anatomy and Forensic Anthropology at Tiradentes University, Farolândia campus in Aracaju, Sergipe. Each skull in the collection has secure detailed records. Eighty-nine skulls with signs of craniotomy (n=58) or damage (n=30) and one unidentified were excluded. The 152 eligible skulls underwent cranial measurements. Using the Anaconda platform and Jupyter editor, the data were divided into a training group (80% of the sample) and then were tested (20% of the sample). Eleven machine learning algorithms, including both linear and non-linear models, were applied. Results: The best machine learning algorithm was a neural network with average accuracy of 93%, after 50 runs. The difference to logistic regression, which had an accuracy of 68%, was significantly (p-value of 0.01016). Conclusion: This study demonstrated the potential of the neural network for solving the sex classification problem. The study has a limitation in that neural networks perform better with a large volume of data, and this study used data from a single center. Nevertheless, in the future, more studies should be conducted testing neural networks with larger samples and skulls from other continents.


STEYN, Maryna; İŞCAN, M. Yaşar. Sexual dimorphism in the crania and mandibles of South African whites. Forensic science international, v. 98, n. 1-2, p. 9-16, 1998. DOI:

KRANIOTI, Elena F.; İŞCAN, Mehmet Yasar; MICHALODIMITRAKIS, Manolis. Craniometric analysis of the modern Cretan population. Forensic Science International, v. 180, n. 2-3, p. 110. e1-110. e5, 2008. DOI:

FRANKLIN, Daniel et al. Estimation of sex from cranial measurements in a Western Australian population. Forensic science international, v. 229, n. 1-3, p. 158. e1-158. e8, 2013. DOI:

DE ALMEIDA JÚNIOR, Erasmo et al. Investigação do sexo através de uma área triangular facial formada pela interseção dos pontos: forame infraorbital direito, esquerdo e o próstio, em crânios secos de adultos. Revista de Ciências Médicas e Biológicas, v. 9, p. 8-12, 2010. DOI:

DE ALMEIDA JÚNIOR, Erasmo et al. Investigação do sexo e idade por meio de mensurações interforames em crânios secos de adultos. Revista de Ciências Médicas e Biológicas, v. 12, n. 1, p. 55-59, 2013. DOI:

DE ALMEIDA JÚNIOR, Erasmo et al. Estimativa do sexo e idade por meio de mensurações cranianas. Journal of Dentistry & Public Health (inactive/archive only), v. 6, n. 2, 2015. DOI:

TELES, Helda Crystiane Cirilo et al. Estimativa do sexo e idade por meio de mensurações faciais em crânios secos de adultos. Brazilian Journal of Forensic Sciences, Medical Law and Bioethics, v. 9, n. 3, p. 292-307, 2020. DOI:

FERREIRA, Rogério Frederico Aves et al. Avaliação do dimorfismo sexual por meio de medidas lineares entre os processos mastoides e a espinha nasal anterior em crânios secos humanos. J Halth Sci Inst, v. 33, n. 2, p. 130-134, 2015.

PATIL, Kanchan R.; MODY, Rajendra N. Determination of sex by discriminant function analysis and stature by regression analysis: a lateral cephalometric study. Forensic science international, v. 147, n. 2-3, p. 175-180, 2005. DOI:

BELALDAVAR, Chetan; ACHARYA, Ashith B.; ANGADI, Punnya. Sex estimation in Indians by digital analysis of the gonial angle on lateral cephalographs. The Journal of forensic odonto-stomatology, v. 37, n. 2, p. 45, 2019.

NAIKMASUR, Venkatesh G.; SHRIVASTAVA, Rahul; MUTALIK, Sunil. Determination of sex in South Indians and immigrant Tibetans from cephalometric analysis and discriminant functions. Forensic Science International, v. 197, n. 1-3, p.122. e1-122. e6, 2010. DOI:

GAPERT, René; BLACK, Sue; LAST, Jason. Sex determination from the foramen magnum: discriminant function analysis in an eighteenth and nineteenth century British sample. International Journal of Legal Medicine, v. 123, n. 1, p. 25-33, 2009. DOI:

SASSI, Carlos et al. Sex determination in a Brazilian sample from cranial morphometric parameters-a preliminary study. The Journal of Forensic Odonto-stomatology, v. 38, n. 1, p. 8, 2020.

DE OLIVEIRA, Fortes et al. Sexual dimorphism in Brazilian human skulls: discriminant function analysis. The Journal of forensic odonto-stomatology, v. 30, n. 2, p. 26, 2012.

PELEG, Smadar et al. New methods for sex estimation using sternum and rib morphology. International Journal of Legal Medicine, v. 134, n. 4, p. 1519-1530, 2020. DOI:

HAN, Jiawei; PEI, Jian; TONG, Hanghang. Data mining: concepts and techniques. Morgan kaufmann, 2022.

TONEVA, Diana H. et al. Data mining for sex estimation based on cranial measurements. Forensic Science International, v. 315, p. 110441, 2020. DOI:

BERTONCELLI, Carlo M., et al. Predicting osteoarthritis in adults using statistical data mining and machine learning. Therapeutic Advances in Musculoskeletal Disease, 2022, 14: 1759720X221104935. DOI:

AL YOUSEF, Mohammed Zeyad, et al. Early prediction of diabetes by applying data mining techniques: A retrospective cohort study. Medicine, 2022, 101.29: e29588. DOI:

MUSILOVÁ, Barbora et al. Exocranial surfaces for sex assessment of the human cranium. Forensic science international, v. 269, p. 70-77, 2016. DOI:

BEWES, James et al. Artificial intelligence for sex determination of skeletal remains: Application of a deep learning artificial neural network to human skulls. Journal of Forensic and Legal Medicine, v. 62, p. 40-43, 2019. DOI:

MAHFOUZ, Mohamed et al. Patella sex determination by 3D statistical shape models and nonlinear classifiers. Forensic science international, v. 173, n. 2-3, p. 161-170, 2007. DOI:

DU JARDIN, Ph et al. A comparison between neural network and other metric methods to determine sex from the upper femur in a modern French population. Forensic science international, v. 192, n. 1-3, p. 127. e1-127. e6, 2009. DOI:

NAVEGA, David et al. Sex estimation from the tarsal bones in a Portuguese sample: a machine learning approach. International journal of legal medicine, v. 129, n. 3, p. 651-659, 2015. DOI:

NIKITA, Efthymia; NIKITAS, Panos. On the use of machine learning algorithms in forensic anthropology. Legal Medicine, v. 47, p. 101771, 2020. DOI:

SENOL, D. et al. Sex prediction with morphometric measurements of first and fifth metatarsal and phalanx obtained from X-ray images by using machine learning algorithms. Folia Morphologica, 2022. DOI:

TURAN, Muhammed Kamil et al. A trial on artificial neural networks in predicting sex through bone length measurements on the first and fifth phalanges and metatarsals. Computers in Biology and Medicine, v. 115, p. 103490, 2019. DOI:

YANG, Wen et al. Sex determination of three-dimensional skull based on improved backpropagation neural network. Computational and mathematical methods in medicine, v. 2019, 2019. DOI:

TONEVA, Diana et al. Machine learning approaches for sex estimation using cranial measurements. International Journal of Legal Medicine, v. 135, n. 3, p. 951-966, 2021. DOI:

TOY, Seyma et al. A study on sex estimation by using machine learning algorithms with parameters obtained from computerized tomography images of the cranium. Scientific Reports, v. 12, n. 1, p. 1-11, 2022. DOI:

NIKITA, Efthymia; NIKITAS, Panos. Sex estimation: a comparison of techniques based on binary logistic, probit and cumulative probit regression, linear and quadratic discriminant analysis, neural networks, and naïve Bayes classification using ordinal variables. International journal of legal medicine, v. 134, n. 3, p. 1213-1225, 2020. DOI:

BERTSATOS, Andreas et al. Advanced procedures for skull sex estimation using sexually dimorphic morphometric features. International Journal of Legal Medicine, v. 134, p. 1927-1937, 2020. DOI:

COELHO, João d’Oliveira; CURATE, Francisco. CADOES: An interactive machine-learning approach for sex estimation with the pelvis. Forensic science international, v. 302, p. 109873, 2019. DOI:

SANTOS, Frédéric; GUYOMARC’H, Pierre; BRUZEK, Jaroslav. Statistical sex determination from craniometrics: Comparison of linear discriminant analysis, logistic regression, and support vector machines. Forensic science international, v. 245, p. 204. e1-204. e8, 2014. DOI:

DAMACENO, Ana Gardenia; MAIA, Jéssica Souza. APLICAÇÃO DE METODOLOGIA PARA ESTIMATIVA DE ANCESTRALIDADE EM CRÂNIOS ORIUNDOS DO ESTADO DA BAHIA. 2019. Trabalho de Conclusão de Curso (Graduação em Odontologia). Universidade Tiradentes, Aracaju. 2019.

JELLINGHAUS, K. et al. Study of the KS distance on skulls from different modern populations for sex and ancestry determination. Rechtsmedizin, v. 30, 2020. DOI:




How to Cite

MOTA, M. J. S.; VIEIRA, A. C. A.; LIMA, L. S.; SÁTIRO, J. V. M.; MENEZES NETO, C. M. de; PAIXÃO, P. L. P.; LOPES, G. P. G.; SETTON, L. R. de A.; ANDRADE, C. E. de; CABRAL, R. H. Sex determination based on craniometric parameters: a comparative approach between linear and non-linear machine learning algorithms. Journal Archives of Health, [S. l.], v. 5, n. 1, p. 634–651, 2024. DOI: 10.46919/archv5n1-042. Disponível em: Acesso em: 14 apr. 2024.

Most read articles by the same author(s)