Artificial Neural Networks Outperformed by Random Forest Models in Tooth Shape and Sex Estimation

Strategic Insights -

A recent study published in 3 Biotech has shed light on the performance of three artificial intelligence (AI) algorithms - support vector machine (SVM), artificial neural network (ANN), and Random Forest (RF) - in sex estimation using 3D geometric morphometric data derived from nine permanent tooth classes in 120 individuals. The research, conducted by a team of scientists from Manipal Academy of Higher Education, found that RF outperformed SVM and ANN across all tooth types, achieving the highest accuracy and balanced precision/recall.

Key Takeaways:

  • The study evaluated the performance of three AI algorithms - SVM, ANN, and RF - in sex estimation using 3D geometric morphometric data from 120 individuals.
  • RF outperformed SVM and ANN across all tooth types, achieving the highest accuracy (97.95% for mandibular second premolars) and balanced precision/recall (0.85-1.0).
  • Maxillary first molars (95.83% accuracy) and mandibular second premolars (97.95%) exhibited the highest sexual dimorphism.
  • RF demonstrated minimal sex bias, whereas ANN struggled with female classification (recall: 0.33-0.88 vs. males: 0.36-1.0).
  • Feature analysis highlighted mandibular premolars as most dimorphic, with RF leveraging complex spatial relationships between landmarks effectively.
  • The study concluded that traditional machine learning models (RF, SVM) outperformed ANN, suggesting data set structure and feature engineering influence AI efficacy.
  • Future research should explore hybrid models combining AI strengths with traditional morphometrics for improved reliability.

Statistics:

  • The study used 3D geometric morphometric data from 120 individuals (60 males, 60 females) aged 13-20.
  • RF achieved the highest accuracy among the three AI algorithms (97.95% for mandibular second premolars).
  • SVM showed moderate performance (70-88% accuracy), while ANN had the lowest metrics (58-70% accuracy).
  • Maxillary first molars and mandibular second premolars exhibited the highest sexual dimorphism (95.83% and 97.95% accuracy, respectively).

Sources:

  • Science and Engineering research board
  • Manipal Academy of Higher Education
  • Springer Heidelberg (publisher of 3 Biotech)
  • Junaid Ahmed et al. (authors of the study)
  • Srikant Natarajan et al. (authors of the study)