Clinical decision-making support system for dental implant design using machine learning

Purpose of research. A current challenge in digital dental implantation is the selection and design of a parametric implant, taking into account the volume and quality of bone tissue in the implantation area, bone density and structure, the planned prosthetic structure, and a number of other factors. The purpose of the study is to develop a medical decision-making support system with Artificial Intelligence for selection and design of a parametric dental implant.

Methods. As a result of the analysis of the features of the implant installation and decision support logic, knowledge base and machine learning components were included in the corresponding software package. The implementation of the knowledge base is made in the form of a computer ontology and contains rules arranged in a typical sequence of data processing. Artificial intelligence technology is used at the stage of determining the density of the trabecular bone and classifying it by bone type by analyzing the patient's cone beam computed tomography images using a neural network.

Results. In the experiment, computed tomography images of the lower jaw with different resolutions were used as initial images, pre-marked by bone density groups, 30 images in each group (120 cases in total). The best results were shown by the residual neural network model ResNet 34. The model achieved 0.875 accuracy on the validation sample and 0.75 accuracy on the test sample with a loss function value of about 0.72. Thus, we can conclude about the positive possibility of using machine learning technology.

Conclusion. The main scientific result of the study is the generalization of technical solutions within a unified set of visualization technologies, combined with a knowledge base in the form of computer ontology and a machine learning module, in accordance with the principles of personalized medicine. The proposed hybrid approach, combining ex pert rules with machine learning methods, combines the advantages of two paradigms: formalized clinical experience and adaptive detection of hidden patterns

1. Alekseeva M.G., Zubov A.I., Novikov M.Yu. Artificial intelligence in medicine. Mezhdunarodnyi nauchno-issledovatel'skii zhurnal = International Scientific Research Journal. 2022;(7):10-13. (In Russ.) https://doi.org/10.23670/IRJ.2022.121.7.038

2. Vankov V.V., Artemova O.R., Karpov O.E., Matvienko A.V., Gusev A.V., Enikeev I.M., Kostina E.V. Results of the introduction of artificial intelligence in Russian healthcare. Vrach i informatsionnye tekhnologii = Doctor and Information Technologies. 2024;(3):32-43. (In Russ.) https://doi.org/10.25881/18110193_2024_3_32

3. Kupatenko Ya.G., Miruk A.K., Lomonosova A.V., Kozlova A.A. Artificial intelligence in medicine: an overview of the current situation and trends. Cifra. Medikobiologicheskie nauki = Cifra. Medical and Biological Sciences. 2024;(2):1-13. (In Russ.) https://doi.org/10.60797/BMED.2024.2.4

4. Morozov D.Yu., Omelyanovsky V.V., Fedyaeva V.K. Artificial intelligence in the healthcare system. Clinical recommendations. Menedzher zdravookhraneniya = The Health Care Manager. 2025;(9):58-67. (In Russ.) https://doi.org/10.21045/1811-0185-2025-9-58-67

5. Sharova D.E., Mikhailova A.A., Gusev A.V., Garbuk S.V., Vladzimirsky A.V., Vasiliev Yu.A. Analysis of world experience in regulating the use of medical data for the purpose of creating artificial intelligence systems based on machine learning. Vrach i informatsionnye tekhnologii = Doctor and Information Technologies. 2022;(4):28-39. (In Russ.) https://doi.org/10.25881/18110193_2022_4_28

6. Kukreja B., Kukreja P. Integration of Artificial Intelligence in dentistry: a systematic review of educational and clinical implications. Cureus. 2025. Vol. 17. https://doi.org/10.7759/cureus.79350

7. Dedov I.I., Tulpakov A.N., Chekhonin V.P., Baklaushev V.P., Archakov A.I., Moshkovsky S.A. Personalized medicine: current state and prospects. Vestnik Rossiiskoi akademii meditsinskikh nauk = Bulletin of the Russian Academy of Medical Sciences. 2012;67(12):412. (In Russ.)

8. Bensmain W., Benlebna M., Serier B., Abbes B., Bouiadjra B. A. Parametric optimization of dental implants. Mechanics and Mechanical Engineering. 2018;22:1061-1076. https://doi.org/10.2478/mme-2018-0084

9. Rahmanivahid P., Heidari M. Design parameters of dental implants: a review. Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería. 2022;38(1):1-10. https://doi.org/10.23967/j.rimni.2022.03.002

10. Gribova V.V., Shalfeeva E.A., Okun D.B., Shevchenko O.N. Ontological complex of knowledge representation for rehabilitation of traumatological and orthopedic patients. Ontologiya proektirovaniya = The Ontology of Design. 2025;15(4):509-522. (In Russ.) https://doi.org/10.18287/2223-9537-2025-15-4-509-522

11. Vasanthapriyan S. An ontological approach for knowledge representation of dental extraction forceps. In: Artificial Intelligence: Second International Conference. Singapore: Springer; 2019. P. 147-160. https://doi.org/10.1007/978-981-13-9129-3_11

12. Biasi V., Rudek M., Szejka A., Canciglieri J. O. Formalization of a knowledge base applied to dental implant. In: Proceedings of the 8th International Conference on Information Society and Technology (ICIST 2018). Serbia: Kopaonik; 2018. Р. 1-6.

13. Szejka A., Canciglieri Junior O., Rudek M., Panetto H. A conceptual knowledgelink model for supporting dental implant process. Advanced Materials Research. 2014;945949:3424-3429. https://doi.org/10.4028/www.scientific.net/AMR.945-949.3424

14. Chen Q., Wu J., Li S., Lyu P., Wang Y., Li M. An ontology-driven, case-based clinical decision support model for removable partial denture design. Scientific Reports. 2016;6:27855. https://doi.org/ 10.1038/srep27855

15. Bida F., Naser H. Diagnostic of osteoporosis using backpropagation neural networks. Journal of Techniques. 2025;(7):10–20. https://doi.org/10.51173/jt.v7i2.2597

16. Qasrawi R., Thwib S., Issa G., Qdaih I., Abu Ghoush R., Arjah H. Optimized Hounsfield units transformation for explainable temporal stage-specific ischemic stroke classification in CT imaging. J. Imaging. 2025;(11):423. https://doi.org/10.3390/jimaging11120423

17. Zhao H., Zhang Yi, Zhang W., Wang L., Li K., Geng J., Cheng X., Wu T. An automatic deep learning-based bone mineral density measurement method using X-ray images of children. Quantitative Imaging in Medicine and Surgery. 2025;(15):2481–2493. https://doi.org/10.21037/qims-24-283

18. Epifanov A.V., Zheikov D.S., Ivashchenko A.V., Gerasimov G. P., Avsievich V.V., Ponomarev A.E., Panarin V.V., Avsievich A.V., Kolsanov A.V. Intelligent diagnostics of intervertebral hernias of the lumbar spine with telemedicine access. Menedzher zdravookhraneniya = The Health Care Manager. 2025;(10):90-96. (In Russ.) https://doi.org/10.21045/1811-0185-2025-10-90-96

19. Palani B., Rathee M., Tomar S., Singla S. U-Net-based deep learning architecture for automated CBCT segmentation of the mandibular canal in dental implant treatment planning: A systematic review and meta-analysis. The Journal of Prosthetic Dentistry. 2025;(25):00955-2. https://doi.org/10.1016/j.prosdent.2025.12.003

20. Liu M., Wang S., Chen H., et al. A pilot study of a deep learning approach to detect marginal bone loss around implants. BMC Oral Health. 2022;(22):11. https://doi.org/10.1186/s12903-021-02035-8

21. Cha J.-Y., Yoon H.-I., Yeo I.-S., Huh K.-H., Han J.-S. Peri-implant bone loss measurement using a region-based convolutional neural network on dental periapical radiographs. Journal of Clinical Medicine. 2021;(10):1009. https://doi.org/10.3390/jcm10051009

22. Shafiq M., Gu Z. Deep residual learning for Image Recognition: A Survey. Applied Sciences. 2022;(12):8972. https://doi.org/10.3390/app12188972