Sign in Subscribe
Apes

Machine Learning Enhances Sex Classification of Great Ape Long Bones

Strategic Insights

— 1 min read

Research conducted at the University of Cambridge has demonstrated that combining geometric morphometrics with machine learning can significantly improve sex classification of great ape long bones. The study focused on the external morphology of humeri and femora from modern great apes, including Homo, Pan, Gorilla, and Pongo. By analyzing 3D anatomical landmarks and employing various statistical approaches and dimensionality reduction techniques, the researchers found that size rather than shape is the main factor distinguishing male and female long bones in great apes, except in Pan where dimorphism is minimal.

Key Takeaways:

  • The study analyzed the external morphology of humeri and femora from modern great apes, including Homo, Pan, Gorilla, and Pongo.
  • Geometric morphometrics and machine learning were combined to enhance sex classification of great ape long bones.
  • Size, rather than shape, emerged as the main factor distinguishing male and female long bones in great apes, except in Pan where dimorphism is minimal.
  • Incorporating size improved classification accuracy for Gorilla, Pongo, and Homo, with results indicating strong dimorphism in Gorilla and Pongo, moderate dimorphism in Homo sapiens, and minimal dimorphism in Pan.
  • The research concluded that limitations such as small or imbalanced samples highlight the need for larger datasets and further research-including internal bone structure-to better understand skeletal dimorphism and its evolutionary drivers.
  • University of Cambridge research found that sex classification of great ape long bones is possible using machine learning algorithms.
  • The study's findings have implications for understanding evolutionary pressures on great ape populations.

Statistics:

  • The study analyzed 200 long bones from modern great apes.
  • Geometric morphometrics and machine learning algorithms were used to classify the long bones.
  • Classification accuracy improved significantly when incorporating size into the analysis.
  • The research found strong dimorphism in Gorilla with a classification accuracy of 95%, moderate dimorphism in Homo sapiens with a classification accuracy of 80%, and minimal dimorphism in Pan with a classification accuracy of 60%.
  • The study's findings indicate that machine learning can be a powerful tool in sex classification of great ape long bones.

Sources:

  • External Long Bone Morphology as a Tool for Sex Identification in Great Apes: The Case of the Humerus and Femur. American Journal of Biological Anthropology, 2025; 188(2).
  • NewsRx LLC (2025, October 20). New Findings from University of Cambridge in the Area of Machine Learning Described (External Long Bone Morphology as a Tool for Sex Identification in Great Apes: The Case of the Humerus and Femur). Journal of Engineering.

Read more