journal article·2025-09-18Open access

Data-Driven Design and Additive Manufacturing of Patient-Specific Lattice Titanium Scaffolds for Mandibular Bone Reconstruction

Nail Beisekenov, Bagdat Azamatov, Marzhan Sadenova, Dmitriy Dogadkin, Daniyar Kaliyev, Sergey Rudenko, Boris Syrnev

Abstract

The reconstruction of segmental bone defects requires patient-specific scaffolds that combine mechanical safety, biological functionality, and rapid manufacturing. We converted CT-derived mandibular geometry into a functionally graded Ti-6Al-4V lattice and optimised porosity, screw layout, and strut thickness through a cyber-physical loop that joins high-fidelity FEM, millisecond ANN, and a BN for uncertainty quantification. Fifteen candidate scaffolds were fabricated by direct metal laser sintering and hot isostatic pressing and were mechanically tested. FEM predicted stress and stiffness with 98% accuracy; the ANN reproduced these outputs with 94% fidelity while evaluating 10,000 designs in real time, and the BN limited failure probability to <3% under worst-case loads. The selected 55–65% porosity design reduced titanium use by 15%, shortened development time by 25% and raised multi-objective optimisation efficiency by 20% relative to a solid-plate baseline, while resisting a 600 N bite with a peak von Mises stress of 225 MPa and micromotion < 150 µm. Integrating physics-based simulation, AI speed, and probabilistic rigour yields a validated, additively manufactured scaffold that meets surgical timelines and biomechanical requirements, offering a transferable blueprint for functional scaffolds in bone and joint surgery.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Additive Manufacturing and 3D Printing Technologies · Additive Manufacturing Materials and Processes · Bone Tissue Engineering Materials

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Ecology and Conservation Biology, Texas A&M University, College Station, TX 77843, USA

Graduate School of Science and Technology, Niigata University, Niigata 950-2181, Japan

Smart Engineering Competence Centre, D. Serikbayev East Kazakhstan Technical University, 19 Serikbayev Street, Ust-Kamenogorsk 070010, Kazakhstan

Center of Excellence “VERITAS”, D. Serikbayev East Kazakhstan Technical University, Ust-Kamenogorsk 070004, Kazakhstan

Funding

Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan

References (50)

Show source-provided references
1. Finite Element Analysis of Bone and Implant Stresses for Customized 3D-Printed Orthopaedic Implants in Fracture Fixation10.1007/s11517-019-02104-9 ↗
2. Han, C., Yan, F., Yuan, D., Li, K., Yang, Y., Zhang, J., and Wang, D. (2024). Machine Learning Enabling Prediction in Mechanical Performance of Ti6Al4V Fabricated by Large-Scale Laser Powder Bed Fusion via a Stacking Model. Front. Mech. Eng., 19.10.1007/s11465-024-0796-0 ↗
3. On Stress/Strain Shielding and the Material Stiffness Paradigm for Dental Implants10.1111/cid.12509 ↗
4. Ceddia, M., Solarino, G., Giannini, G., De Giosa, G., Tucci, M., and Trentadue, B. (2024). A Finite Element Analysis Study of Influence of Femoral Stem Material in Stress Shielding in a Model of Uncemented Total Hip Arthroplasty: Ti-6Al-4V versus Carbon Fibre-Reinforced PEEK Composite. J. Compos. Sci., 8.10.3390/jcs8070254 ↗
5. Role of Machine Learning in Additive Manufacturing of Titanium Alloys—A Review10.1007/s11831-023-09969-y ↗
6. Neural Network Modeling of Titanium Alloy Composition-Microstructure-Property Relationships Based on Multimodal Data10.1016/j.msea.2023.145202 ↗
7. Kladovasilakis, N., Tsongas, K., and Tzetzis, D. (2020). Finite Element Analysis of Orthopedic Hip Implant with Functionally Graded Bioinspired Lattice Structures. Biomimetics, 5.10.3390/biomimetics5030044 ↗
8. Prediction of the Mechanical Properties of Titanium Alloy Castings Based on a Back-Propagation Neural Network10.1007/s11665-021-06035-1 ↗
9. Mahmoud, D., and Elbestawi, M. (2017). Lattice Structures and Functionally Graded Materials Applications in Additive Manufacturing of Orthopedic Implants: A Review. J. Manuf. Mater. Process., 1.10.3390/jmmp1020013 ↗
10. Machine Learning Assisted Tensile Strength Prediction and Optimization of TI Alloy10.1109/ACCESS.2024.3450511 ↗
11. The Impact of the Finite Element Method on Medical Device Design10.1007/s40846-018-0428-4 ↗
12. Griggs, J.A. (2023). Artificial Neural Networks for the Design Optimization of Implants. Artificial Intelligence in Dentistry, Springer.10.1007/978-3-031-43827-1_6 ↗
13. Mollica, F., and Ambrosio, L. (2009). The Finite Element Method for the Design of Biomedical Devices. Biomaterials in Hand Surgery, Springer.10.1007/978-88-470-1195-3_3 ↗
14. Combined Model Based on the Finite Element Method and Artificial Neural Networks for Modeling Laser Shock Peening of Titanium–Niobium Implants10.1134/S1052618823070208 ↗
15. Wu, M., and Briant, P. (2012). The Use of Finite Element Analysis in Design, Life Prediction, and Failure Analysis of Biomaterials and Medical Devices. Degradation of Implant Materials, Springer.10.1007/978-1-4614-3942-4_16 ↗
16. Lyakhov, P.A., Dolgalev, A.A., Lyakhova, U.A., Muraev, A.A., Zolotayev, K.E., and Semerikov, D.Y. (2022). Neural Network System for Analyzing Statistical Factors of Patients for Predicting the Survival of Dental Implants. Front. Neuroinform., 16.10.3389/fninf.2022.1067040 ↗
17. The Role of Artificial Neural Networks in Prediction of Mechanical and Tribological Properties of Composites—A Comprehensive Review10.1007/s11831-021-09691-7 ↗
18. Oktyabrova, D., Ashimov, K., Guclu, B., Abilmazhinov, M., Gorbunov, B., Zhanatay, R., Baidalin, T., Suleimenov, B., Beknazarov, A., and Azamatov, B. (2025). Mathematical Modeling and Biomechanical Analysis of a Derotation Plate for Treating Complex Hip Dysplasia. Appl. Sci., 15.10.3390/app15062991 ↗
19. Beisekenov, N., Sadenova, M., Azamatov, B., and Syrnev, B. (2025). Analysis of Biomechanical Characteristics of Bone Tissues Using a Bayesian Neural Network: A Narrative Review. J. Funct. Biomater., 16.10.3390/jfb16050168 ↗
20. Grozav, S.D., Sterca, A.D., Kočiško, M., Pollák, M., and Ceclan, V. (2023). Artificial Neural Network-Based Predictive Model for Finite Element Analysis of Additive-Manufactured Components. Machines, 11.10.3390/machines11050547 ↗
21. Application of Bayesian Neural Networks in Healthcare: Three Case Studies10.3390/make6040127 ↗
22. Bayesian Statistics for Medical Devices: Progress since 201010.1007/s43441-022-00495-w ↗
23. Hunte, J., Neil, M., and Fenton, N. (2022). A Hybrid Bayesian Network for Medical Device Risk Assessment and Management. arXiv.
24. Bayesian Approach for Design and Analysis of Medical Device Trials in the Era of Modern Clinical Studies10.1515/mr-2023-0026 ↗
25. Unmet Medical Need: An Introduction to Definitions and Stakeholder Perceptions10.1016/j.jval.2019.07.007 ↗
26. Ruhe, D., Ciná, G., Tonutti, M., De Bruin, D., and Elbers, P.W.G. (2019). Bayesian Modelling in Practice: Using Uncertainty to Improve Trustworthiness in Medical Applications. arXiv.
27. Accelerated Degradation Mechanism and Mechanical Behavior of 3D-Printed PLA Scaffolds for Bone Regeneration10.1007/s13726-023-01191-8 ↗
28. Elenskaya, N., Vindokurov, I., Sadyrin, E., Nikolaev, A., and Tashkinov, M. (2024). Experimental Evaluation of the Effect of Degradation on the Mechanical Behavior and Morphometric Characteristics of Functionally Graded Polymer Scaffolds. Polymers, 16.10.3390/polym16243474 ↗
29. An Explainable Machine Learning-Based Probabilistic Framework for the Design of Scaffolds in Bone Tissue Engineering10.1007/s10237-024-01817-7 ↗
30. Development and Validation of a Bayesian Network-Based Model for Predicting Coronary Heart Disease Risk from Electronic Health Records10.1161/JAHA.123.029400 ↗
31. Frøysa, H.G., Fallahi, S., and Blaser, N. (2018). Evaluating Model Reduction under Parameter Uncertainty. BMC Syst. Biol., 12.10.1186/s12918-018-0602-x ↗
32. Bayesian Inverse Inference of Material Properties from Microstructure Images10.1016/j.commatsci.2024.113306 ↗
33. A Bayesian Approach to Estimate Material Properties from Global Statistical Data10.1080/19648189.2012.667999 ↗
34. Bayesian Approach in Predicting Mechanical Properties of Materials: Application to Dual Phase Steels10.1016/j.msea.2018.11.106 ↗
35. A Bayesian Belief Network Model for the Risk Assessment and Management of Premature Screen-Out during Hydraulic Fracturing10.1016/j.ress.2021.108094 ↗
36. Investigation of Bayesian Network for Reliability Analysis and Fault Diagnosis of Complex Systems with Real Case Applications10.1177/1687814017728853 ↗
37. BN-SLIM: A Bayesian Network Methodology for Human Reliability Assessment Based on Success Likelihood Index Method (SLIM)10.1016/j.ress.2019.106647 ↗
38. Wang, Z., Yan, J., Meng, S., Li, J., Yu, Y., Zhang, T., Tsang, R.C.C., El-Ansary, D., Han, J., and Jones, A.Y.M. (2022). Reliability and Validity of Sit-to-Stand Test Protocols in Patients with Coronary Artery Disease. Front. Cardiovasc. Med., 9.10.3389/fcvm.2022.841453 ↗
39. Uncertainty and Sensitivity Analysis of Mechanical and Thermal Properties Computed through Embedded Atom Method Potential10.1016/j.commatsci.2019.03.060 ↗
40. Effects of Model Structural Uncertainty on Carbon Cycle Projections: Biological Nitrogen Fixation as a Case Study10.1088/1748-9326/10/4/044016 ↗
41. The Reporting Quality and Transparency of Orthopaedic Studies Using Bayesian Analysis Requires Improvement: A Systematic Review10.1016/j.conctc.2023.101132 ↗
42. Finite Element Model Calibration with Surrogate Model-Based Bayesian Updating: A Case Study of Motor FEM Model
43. Revisiting the Schrage Equation for Kinetically Limited Evaporation and Condensation10.1115/1.4054382 ↗
44. A Variational Bayesian Neural Network for Structural Health Monitoring and Cost-Informed Decision-Making in Miter Gates10.1177/1475921720904543 ↗
45. Deep Generative Bayesian Optimization for Sensor Placement in Structural Health Monitoring10.1111/mice.12799 ↗
46. (2021). Biological Evaluation of Medical Devices—Part 1: Evaluation and Testing Within a Risk Management Process; Under Publication (Replacing ISO 10993-1:2018); DIN EN Version (Standard No. ISO 10993-1).
47. (2021). Standard Specification for Additive Manufacturing Titanium-6 Aluminum-4 Vanadium with Powder Bed Fusion (Standard No. ASTM F2924-14).
48. (2021). Implants for Surgery—Metallic Materials—Part 3: Wrought Titanium 6-Aluminium 4-Vanadium Alloy (Standard No. ISO 5832-3:2021). Available online: https://www.iso.org/standard/79626.html.
49. (2016). Dentistry—Implants—Dynamic Fatigue Test for Endosseous Dental Implants (Standard No. ISO 14801:2016). Available online: https://www.iso.org/standard/63013.html.
50. Bayesian Optimization-Based Inverse Finite Element Analysis for Atrioventricular Heart Valves10.1007/s10439-023-03408-6 ↗