A Hybrid XFEM-ML Framework for High-Fidelity, Rapid Fracture Prediction in Cortical Bone: From Microstructure to Clinical Translation

Authors

• Noor T. Al-Sharify, Medical Instrumentation Engineering Department, Al-Esraa University, Baghdad, Iraq AND Department of Electrical & Electronic Engineering, College of Engineering, Universiti Tenaga Nasional, Kajang 43000, MalaysiaFollow
• Ammar Fadhil Hussein AL-Maliki, Mechanical Engineering Department College of Engineering, Mustansiriyah University, Baghdad 10052, IraqFollow
• Ahmed Ali Farhan Ogaili, Mechanical Engineering Department College of Engineering, Mustansiriyah University, Baghdad 10052, IraqFollow
• Abdul-Rasool Kareem Jweri, College of Agricultural Engineering Sciences, University of Baghdad, Baghdad, IraqFollow
• Alaa Abdulhady Jaber, College of Mechanical Engineering, University of Technology-Iraq, Baghdad 10066, IraqFollow
• Luttfi A. Al-Haddad, College of Mechanical Engineering, University of Technology-Iraq, Baghdad 10066, IraqFollow

Corresponding Author

Ahmed Ali Farhan Ogaili

Authors ORCID

Noor T. Al-Sharify: https://orcid.org/0000-0002-8161-0729

Ammar Fadhil Hussein AL-Maliki: https://orcid.org/0000-0003-2228-8159

Ahmed Ali Farhan Ogaili: https://orcid.org/0000-0001-5623-295X

Abdul-Rasool Kareem Jweri: https://orcid.org/0009-0004-0490-0361

Alaa Abdulhady Jaber: https://orcid.org/0000-0001-5709-195X

Luttfi A. Al-Haddad: https://orcid.org/0000-0001-7832-1048

Document Type

Article

Keywords

Cortical bone, Fracture Load prediction, Extended finite element method, Machine learning, Computational efficiency, Biomedical

Abstract

This paper proposes a hybrid computational model, which combines the eXtended Finite Element Method (XFEM) with machine learning (ML) to forecast the fracture behavior of cortical bone while maintaining microstructural fidelity. It has created a parametric dataset of about 450 three-dimensional XFEM models of single-edge notched bend (SENB) specimens, including important μ-structure features (e.g., osteon orientation, cement line properties, interfacial connectivity, etc.). Based on these simulations, 47 quantitative descriptors were obtained, and these were used to model supervised ML models, namely, Random Forest and Artificial Neural Networks, to estimate fracture load. The Random Forest model demonstrated exceptional predictive performance (R² = 0.952, MAE = 6.1 N, MAPE = 1.9%, Pearson r = 0.980), significantly outperforming the ANN model (R² = 0.831, MAE = 11.8 N, MAPE = 3.7%), The Random Forest model demonstrated strong predictive performance (R² = 0.95, MAE = 6.1 N, MAPE = 1.9%), while reducing computational time by nearly 300-fold and memory requirements by over 20-fold compared to full XFEM analyses. For fracture resistance, feature importanceanalysis indicated the most salient features were osteon orientation, cement line strength, and pore topology. The methodology was also robust, as further led to by sensitivity analyses and uncertainty quantification. The hybrid method provides microstructure-based predictions of fracture that are very automated and precise and result in a significant decrease in computational cost, hence allowing a scalable route to clinical translation to characterize bone integrity.

How to Cite This Article

Al-Sharify, Noor T.; AL-Maliki, Ammar Fadhil Hussein; Ogaili, Ahmed Ali Farhan; Jweri, Abdul-Rasool Kareem; Jaber, Alaa Abdulhady; and Al-Haddad, Luttfi A. (2026) "A Hybrid XFEM-ML Framework for High-Fidelity, Rapid Fracture Prediction in Cortical Bone: From Microstructure to Clinical Translation," Mesopotamian Journal of Computer Science: Vol. 6: Iss. 1, Article 1.
Available at: https://map.researchcommons.org/mjcsc/vol6/iss1/1