Skip to main content
SpringerLink
Log in

Sex estimation from long bones: a machine learning approach

  • Original Article
  • Published:
International Journal of Legal Medicine Aims and scope Submit manuscript

Abstract

Sex estimation from skeletal remains is one of the crucial issues in forensic anthropology. Long bones can be a valid alternative to skeletal remains for sex estimation when more dimorphic bones are absent or degraded, preventing any estimation from the first intention methods. The purpose of this study was to generate and compare classification models for sex estimation based on combined measurement of long bones using machine learning classifiers. Eighteen measurements from four long bones (radius, humerus, femur, and tibia) were taken from a total of 2141 individuals. Five machine learning methods were employed to predict the sex: a linear discriminant analysis (LDA), penalized logistic regression (PLR), random forest (RF), support vector machine (SVM), and artificial neural network (ANN). The different classification algorithms using all bones generated highly accuracy models with cross-validation, ranging from 90 to 92% on the validation sample. The classification with isolated bones ranked between 83.3 and 90.3% on the validation sample. In both cases, random forest stands out with the highest accuracy and seems to be the best model for our investigation. This study upholds the value of combined long bones for sex estimation and provides models that can be applied with high accuracy to different populations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Data availability

Only the Goldman collection is freely accessible at https://web.utk.edu/~auerbach/DATA.htm. Other data are not in open access. For further information, please contact the authors.

References

  1. Daubert V (1993) Merrell Dow Pharmaceuticals. Inc. 509 U.S. 579, p 589

    Google Scholar 

  2. Cattaneo C (2007) Forensic anthropology: developments of a classical discipline in the new millennium. Forensic Sci Int 165:185–193. https://doi.org/10.1016/j.fosciint.2006.05.018

    Article  PubMed  Google Scholar 

  3. Corron L, Adalian P, Condemi S et al (2019) Sub-adult aging method selection (SAMS): A decisional tool for selecting and evaluating sub-adult age estimation methods based on standardized methodological parameters. Forensic Sci Int 304:109897. https://doi.org/10.1016/j.forsciint.2019.109897

    Article  PubMed  Google Scholar 

  4. Rösing FW, Graw M, Marré B et al (2007) Recommendations for the forensic diagnosis of sex and age from skeletons. Homo 58:75–89. https://doi.org/10.1016/j.jchb.2005.07.002

    Article  PubMed  Google Scholar 

  5. Scheuer L (2002) Application of osteology to forensic medicine. Clin Anat 15:297–312. https://doi.org/10.1002/ca.10028

    Article  PubMed  Google Scholar 

  6. Spradley MK, Jantz RL (2011) Sex estimation in forensic anthropology: skull versus postcranial elements. J Forensic Sci 56:289–296. https://doi.org/10.1111/j.15564029.2010.01635

    Article  PubMed  Google Scholar 

  7. Correia H, Balseiro S, De Areia M (2005) Sexual dimorphism in the human pelvis: testing a new hypothesis. HOMO 56:153–160. https://doi.org/10.1016/j.jchb.2005.05.003

    Article  CAS  PubMed  Google Scholar 

  8. Rosenberg K, Trevathan W (2005) Bipedalism and human birth: the obstetrical dilemma revisited. Evol Anthropol 4:161–168. https://doi.org/10.1002/evan.1360040506

    Article  Google Scholar 

  9. Schultz AH (1949) Sex differences in the pelves of primates. Am J Phys Anthropol 7:401–423. https://doi.org/10.1002/ajpa.1330070307

    Article  CAS  PubMed  Google Scholar 

  10. Tague RG (1989) Variation in pelvic size between males and females. Am J Phys Anthropol 80:59–71. https://doi.org/10.1002/ajpa.1330800108

    Article  CAS  PubMed  Google Scholar 

  11. Tague RG (1991) Commonalities in dimorphism and variability in the anthropoid pelvis, with implications for the fossil record. J Human Evol 21:153–176. https://doi.org/10.1016/0047-2484(91)90059-5

    Article  Google Scholar 

  12. Weaver TD, Hublin J-J (2009) Neandertal birth canal shape and the evolution of human childbirth. Proc Natl Acad Sci USA 106:8151–8156. https://doi.org/10.1073/pnas.0812554106

    Article  PubMed  PubMed Central  Google Scholar 

  13. Murail P, Brůžek J, Houët F & Cunha (2005). DSP: a tool for probabilistic sex diagnosis using worldwide variability in hip-bone measurements. Bull Mem Soc Anthropol Paris, 17(17 (3-4)), 167-176.

  14. Alunni-Perret V, Staccini P, Quatrehomme G (2008) Sex determination from the distal part of the femur in a French contemporary population. Forensic Sci Int 175:113–117. https://doi.org/10.1016/j.forsciint.2007.05.018

    Article  CAS  PubMed  Google Scholar 

  15. Curate F, Umbelino C, Perinha A et al (2017) Sex determination from the femur in Portuguese populations with classical and machine-learning classifiers. J Forensic Leg Med 52:75–81. https://doi.org/10.1016/j.jflm.2017.08.011

    Article  CAS  PubMed  Google Scholar 

  16. Curate F, Coelho J, Gonçalves D et al (2016) A method for sex estimation using the proximal femur. Forensic Sci Int 266:579.e1–579.e7. https://doi.org/10.1016/j.forsciint.2016.06.011

    Article  PubMed  Google Scholar 

  17. Işcan MY, Shihai D (1995) Sexual dimorphism in the Chinese femur. Forensic Sci Int 74:79–87. https://doi.org/10.1016/0379-0738(95)01691-b

    Article  PubMed  Google Scholar 

  18. Slaus M, Bedić Z, Strinović D, Petrovečki V (2013) Sex determination by discriminant function analysis of the tibia for contemporary Croats. Forensic Sci Int 226:302.e1–302.e4. https://doi.org/10.1016/j.forsciint.2013.01.025

    Article  PubMed  Google Scholar 

  19. Steyn M, Işcan MY (1997) Sex determination from the femur and tibia in South African whites. Forensic Sci Int 90:111–119. https://doi.org/10.1016/s0379-0738(97)00156-4

    Article  CAS  PubMed  Google Scholar 

  20. Albanese J (2013) A method for estimating sex using the clavicle, humerus, radius, and ulna. J Forensic Sci 58:1413–1419. https://doi.org/10.1111/1556-4029.12188

    Article  PubMed  Google Scholar 

  21. Kranioti EF, Michalodimitrakis M (2009) Sexual dimorphism of the humerus in contemporary Cretans—a population-specific study and a review of the literature*. J Forensic Sci 54:996–1000. https://doi.org/10.1111/j.1556-4029.2009.01103.x

    Article  PubMed  Google Scholar 

  22. Tallman SD, Blanton AI (2020) Distal humerus morphological variation and sex estimation in modern Thai individuals. J Forensic Sci 65:361–371. https://doi.org/10.1111/1556-4029.14218

    Article  PubMed  Google Scholar 

  23. Jongmuenwai W, Boonpim M, Monum T et al (2021) Sex estimation using radius in a Thai population. Anat Cell Biol 54:321–331. https://doi.org/10.5115/acb.20.319

    Article  PubMed  PubMed Central  Google Scholar 

  24. Nogueira L, Santos F, Castier F et al (2023) Sex assessment using the radius bone in a French sample when applying various statistical models. Int J Legal Med. https://doi.org/10.1007/s00414-023-02981-8

  25. Purkait R (2001) Measurements of ulna—a new method for determination of sex. J Forensic Sci 46:924–927

    Article  CAS  PubMed  Google Scholar 

  26. Cowal LS, Pastor RF (2008) Dimensional variation in the proximal ulna: evaluation of a metric method for sex assessment. Am J Phys Anthropol 135:469–478. https://doi.org/10.1002/ajpa.20771

    Article  PubMed  Google Scholar 

  27. Introna F, Dragone M, Frassanito P, Colonna M (1993) Determination of skeletal sex using discriminant analysis of ulnar measurements. Boll Soc Ital Biol Sper 69:517–523

    PubMed  Google Scholar 

  28. Srivastava R, Saini V, Rai RK et al (2013) Sexual dimorphism in ulna: an osteometric study from India. J Forensic Sci 58:1251–1256. https://doi.org/10.1111/1556-4029.12158

    Article  PubMed  Google Scholar 

  29. Bidmos MA, Mazengenya P (2021) Accuracies of discriminant function equations for sex estimation using long bones of upper extremities. Int J Legal Med 135:1095–1102. https://doi.org/10.1007/s00414-020-02458-y

    Article  PubMed  Google Scholar 

  30. Krüger GC, L’Abbé EN, Stull KE (2017) Sex estimation from the long bones of modern South Africans. Int J Legal Med 131:275–285. https://doi.org/10.1007/s00414-016-1488-z

    Article  PubMed  Google Scholar 

  31. Stull KE, L’Abbé EN, Ousley SD (2017) Subadult sex estimation from diaphyseal dimensions. Am J Phys Anthropol 163:64–74. https://doi.org/10.1002/ajpa.23185

    Article  PubMed  Google Scholar 

  32. Alunni V, du Jardin P, Nogueira L et al (2015) Comparing discriminant analysis and neural network for the determination of sex using femur head measurements. Forensic Sci Int 253:81–87. https://doi.org/10.1016/j.forsciint.2015.05.023

    Article  PubMed  Google Scholar 

  33. Hinić-Frlog S, Motani R (2010) Relationship between osteology and aquatic locomotion in birds: determining modes of locomotion in extinct Ornithurae. J Evol Biol 23:372–385. https://doi.org/10.1111/j.1420-9101.2009.01909.x

    Article  PubMed  Google Scholar 

  34. Nikita E, Nikitas P (2020) On the use of machine learning algorithms in forensic anthropology. Legal Medicine 47:101771. https://doi.org/10.1016/j.legalmed.2020.101771

    Article  PubMed  Google Scholar 

  35. Attia MH, Attia MH, Farghaly YT et al (2022) Performance of the supervised learning algorithms in sex estimation of the proximal femur: a comparative study in contemporary Egyptian and Turkish samples. Science & Justice 62:288–309. https://doi.org/10.1016/j.scijus.2022.03.003

    Article  Google Scholar 

  36. Ammer S, d’Oliveira Coelho J, Cunha EM (2019) Outline shape analysis on the trochlear constriction and olecranon fossa of the humerus: insights for sex estimation and a new computational tool. J Forensic Sci 64:1788–1795. https://doi.org/10.1111/1556-4029.14096

    Article  PubMed  Google Scholar 

  37. Darmawan MF, Yusuf SM, Kadir MRA, Haron H (2015) Comparison on three classification techniques for sex estimation from the bone length of Asian children below 19 years old: an analysis using different group of ages. Forensic Sci Int 247:130.e1–130.11. https://doi.org/10.1016/j.forsciint.2014.11.007

    Article  CAS  PubMed  Google Scholar 

  38. Toneva D, Nikolova S, Agre G et al (2021) Machine learning approaches for sex estimation using cranial measurements. Int J Legal Med 135:951–966. https://doi.org/10.1007/s00414-020-02460-4

    Article  PubMed  Google Scholar 

  39. Magoulas GD, Prentza A (2001) Machine learning in medical applications. In: Paliouras G, Karkaletsis V, Spyropoulos CD (eds) Machine learning and its applications. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 300–307

    Chapter  Google Scholar 

  40. Wang Y-H, Liu T-A, Wei H et al (2016) Automated classification of epiphyses in the distal radius and ulna using a support vector machine. J Forensic Sci 61:409–414. https://doi.org/10.1111/1556-4029.13006

    Article  PubMed  Google Scholar 

  41. Auerbach BM, Ruff CB (2004) Human body mass estimation: a comparison of morphometric and mechanical methods. Am J Phys Anthropol 125:331–342. https://doi.org/10.1002/ajpa.20032

    Article  PubMed  Google Scholar 

  42. Auerbach BM, Ruff CB (2006) Limb bone bilateral asymmetry: variability and commonality among modern humans. J Human Evol 50:203–218. https://doi.org/10.1016/j.jhevol.2005.09.004

    Article  Google Scholar 

  43. Hunt DR, Albanese J (2005) History and demographic composition of the Robert J. Terry anatomical collection. Am J Phys Anthropol 127:406–417. https://doi.org/10.1002/ajpa.20135

    Article  PubMed  Google Scholar 

  44. Guo G, Wang H, Bell D et al (2003) KNN model-based approach in classification. In: Meersman R, Tari Z, Schmidt DC (eds) On the move to meaningful Internet systems 2003: CoopIS, DOA, and ODBASE. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 986–996

    Chapter  Google Scholar 

  45. Breiman L (2001) Random Forests. Mach Learn 45(5):32. https://doi.org/10.1023/A:1010933404324

    Article  Google Scholar 

  46. d'Oliveira Coelho J (2019) Curate F CADOES: An interactive machine-learning approach for sex estimation with the pelvis. Forensic Sci Int. 302:109873. https://doi.org/10.1016/j.forsciint.2019.109873

    Article  PubMed  Google Scholar 

  47. Vapnik V (1998) The support vector method of function estimation. In: Nonlinear modeling: Advanced black-box techniques. Springer, pp 55–85

    Chapter  Google Scholar 

  48. Mollalo A, Mao L, Rashidi P, Glass GE (2019) A GIS-based artificial neural network model for spatial distribution of tuberculosis across the continental United States. Int J Environ Res Public Health 16(1):157

    Article  PubMed  PubMed Central  Google Scholar 

  49. Zhang Z (2018) Artificial neural network, in Multivariate time series analysis in climate and environmental research. Springer, pp 1–35

    Google Scholar 

  50. Maroco J, Silva D, Guerreiro M, Santana I, de Mendonça A (2011) Data mining methods in the prediction of dementia: a real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, sup- port vector machines, classification trees and random forest. BMC res Notes 4:299

    Article  PubMed  PubMed Central  Google Scholar 

  51. Hastie T, Tibshirani RJ, Friedman JH (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer-Verlag, New York

    Book  Google Scholar 

  52. Kuhn M (2015) caret: classification and regression training. https://cran.r-project.org/web/packages/caret/index.html. Accessed 2023

  53. Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159–174

    Article  CAS  PubMed  Google Scholar 

  54. Quatrehomme G (2015) Traité d’anthropologie médico-légale, 1st edn. De Boeck, Paris

    Google Scholar 

  55. Slaus M, Tomicić Z (2005) Discriminant function sexing of fragmentary and complete tibiae from medieval Croatian sites. Forensic Sci Int 147:147–152. https://doi.org/10.1016/j.forsciint.2004.09.073

    Article  PubMed  Google Scholar 

  56. Nieves JW, Formica C, Ruffing J et al (2004) Males have larger skeletal size and bone mass than females, despite comparable body size. J Bone Miner Res 20:529–535. https://doi.org/10.1359/JBMR.041005

    Article  PubMed  Google Scholar 

  57. Sarker IH (2021) Machine learning: algorithms, real-world applications and research directions. SN Comput Sci 2:160. https://doi.org/10.1007/s42979-021-00592-x

    Article  PubMed  PubMed Central  Google Scholar 

  58. Santos F, Guyomarc’h P, Rmoutilova R, Bruzek J (2019) A method of sexing the human os coxae based on logistic regressions and Bruzek’s nonmetric traits. Am J Phys Anthropol 169:435–447. https://doi.org/10.1002/ajpa.23855

    Article  PubMed  Google Scholar 

  59. Constantinou C, Nikita E (2022) SexEst: An open access web application for metric skeletal sex estimation. Intl J of Osteoarchaeology 32:832–844. https://doi.org/10.1002/oa.3109

    Article  Google Scholar 

  60. Curate F, d’Oliveira Coelho J, Silva AM (2021) CalcTalus: an online decision support system for the estimation of sex with the calcaneus and talus. Archaeol Anthropol Sci 13:74. https://doi.org/10.1007/s12520-021-01327-y

    Article  Google Scholar 

  61. Nikita E, Nikitas P (2020) 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. Int J Legal Med 134:1213–1225. https://doi.org/10.1007/s00414-019-02148-4

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Aix Marseille Univ, CNRS, EFS, ADES, 13007, Marseille, France

    Siam Knecht, Yann Ardagna & Pascal Adalian

  2. Institut Universitaire d’Anthropologie Médico-Légale, Faculté de Médecine, Université Côte d’Azur, 28 Avenue de Valombrose, 06107, Cedex 2, Nice, France

    Siam Knecht, Véronique Alunni & Luísa Nogueira

  3. Université de Bordeaux – CNRS-MCC, UMR 5199 PACEA, Bâtiment B8A, Allée Geoffroy Saint-Hilaire, 33615, Pessac Cedex, CS 50023, France

    Fréderic Santos

  4. CEPAM (UMR CNRS 7264), 24 avenue des Diables Bleus, 06300, Nice, France

    Véronique Alunni

Authors
  1. Siam Knecht
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fréderic Santos
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yann Ardagna
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Véronique Alunni
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Pascal Adalian
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Luísa Nogueira
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Siam Knecht.

Ethics declarations

Ethics approval

The present study was performed in accordance with the ethical standards.

Informed consent

Not applicable.

Conflict of interest

The authors have no conflict of interest to declare.

Research involving human participants and/or animals

Not applicable.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Knecht, S., Santos, F., Ardagna, Y. et al. Sex estimation from long bones: a machine learning approach. Int J Legal Med 137, 1887–1895 (2023). https://doi.org/10.1007/s00414-023-03072-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00414-023-03072-4

Keywords

Search

Navigation