Dmytrenko M. I.

PROSPECTS AND EFFECTIVENESS OF ARTIFICIAL INTELLIGENCE APPLICATION IN ORTHODONTICS

---

Show/Download

About the author:

Dmytrenko M. I.

Heading:

MEDICAL EDUCATION

Type of article:

Scientific article

Annotation:

The use of machine learning algorithms has significant potential to improve the accuracy and effectiveness of orthodontic treatment by integrating interdisciplinary principles. The aim of the study was to investigate the possibilities of applying artificial intelligence in orthodontics for the assessment of patients’ diagnostic data during students’ clinical training. An analysis and generalization of scientific data regarding the effectiveness of neural network application in determining the degree of skeletal bone maturity were conducted. It was established that high-quality manual cephalometric analysis of the cervical vertebrae requires considerable time and extensive experience from an orthodontist, whereas the use of specialized software enables automated assessment of bone age and rapid acquisition of reliable results. However, according to the findings of our own study, both the manual analysis of diagnostic data performed by students and the analysis conducted using universal artificial intelligence programs were incorrect in 80% of cases. The identified major clinical errors prompted us to focus on developing students’ ability to “observe clinically” and on training machine learning systems. Based on communication with Gemini, a Python code was created, and a “Teacher – Student – Artificial Intelligence” interaction model was proposed. The model is based on three principles: openness, interaction, and mutual respect. Such an approach to teaching creates conditions for the development of communication skills, fosters responsibility in future physicians, and promotes the formation of students’ clinical thinking, which is critically important for their further independent practical work.

Tags:

Bibliography:

1. Smaglyuk LV, Liakhovska AV. Skeletal and dental maturity in female adolescents with menstrual disorders. World of Medicine and Biology. 2019;(3):153-158. DOI: https://doi.org/10.26724/2079-8334-2019-3-69-153-158
2. Kaskova LF, Yanko NV, Vashchenko IY, Sadovski MO, Zavyalova KM, Ulasevich LP, et al. The knowledge and attitude regarding vital pulp therapy among dental students of a Ukrainian university. East Ukr Med J. 2025;13(3):693-701. DOI: https://doi.org/10.21272/eumj.2025;13(3):693-701
3. Manashchuk NV, Chornii SV, Zalizniak MS, Pohoretska KhV, Chornii NV, Patskan LO. Shtuchnyi intelekt u terapevtychnii stomatolohii. Klinichna Stomatolohiia. 2025;(3):23-30. DOI: https://doi.org/10.11603/2311-9624.2025.3.15873 [in Ukrainian].
4. Belikov OB, Roshchuk OI, Belikova NI, Belikova LO, Bernik MA. Artificial intelligence in dentistry: functional classification, clinical responsibility, and risk stratification. Via Stomatologiae. 2026;3(1):24-33. DOI: https://doi.org/10.32782/3041-1394.2026-1.3
5. Vyzhenko YeYe. Suchasni mozhlyvosti zastosuvannia kompiuternykh tekhnolohii v ortodontii. Aktualni problemy suchasnoi medytsyny: Visnyk Ukrainskoi medychnoi stomatolohichnoi akademii. 2023;23(4):288-292. DOI: https://doi.org/10.31718/2077-1096.23.4.288 [in Ukrainian].
6. MOZ Ukrainy. Ortodontiia ta shchelepno-lytseva ortopediia klinichna nastanova, zasnovana na dokazakh. Kyiv: MOZ Ukrainy; 2023. Dostupno: https://www.dec.gov.ua/wp-content/uploads/2025/03/2023_620_kn-ortodontiya.pdf [in Ukrainian].
7. Smaglyuk LV, Dmytrenko MI, Gurzhiy OV, Nesterenko OM, Voronkova AV. The meaning of teleradiographic indicators in the comprehensive therapy of dental patients. (Literature review). Bulletin of problems biology and medicine. 2022;1:67-70. DOI: https://doi.org/10.29254/2077-4214-2022-1-163-67-70
8. McNamara JAJr, Franchi L. The cervical vertebral maturation method: a user’s guide. Angle Orthod. 2018;88(2):133-143. DOI: https://doi.org/10.2319/111517-787.1
9. Kim EG, Oh IS, So JE, Kang J, Le VNT, Tak MK, et al. Estimating cervical vertebral maturation with a lateral cephalogram using the convolutional neural network. J Clin Med. 2021;10(22):5400. DOI: https://doi.org/10.3390/jcm10225400
10. Barbosa NMV, Castro AC, Conti F, Capelozza-Filho L, Almeida-Pedrin RR, Cardoso MA. Reliability and reproducibility of the method of assessment of midpalatal suture maturation: a tomographic study. Angle Orthod. 2019;89(1):71-77. DOI: https://doi.org/10.2319/121317-859.1
11. Decocq P, Toutain G, Honore J, Bocquet E, Crocquet M Computerized method for calculating cervical vertebral maturation. Orthod Fr. 2020;91(4):361-371. DOI: https://doi.org/10.1684/orthodfr.2020.27
12. Sadeghi TS, Ourang SA, Sohrabniya F, Sadr S, Shobeiri P, Motamedian SR. Performance of artificial intelligence on cervical vertebral maturation assessment: a systematic review and meta-analysis. BMC Oral Health. 2025;25(1):187. DOI: https://doi.org/10.1186/s12903-025-05482-9
13. Mathew R, Palatinus S, Padala S, Alshehri A, Awadh W, Bhandi S, et al. Neural networks for classification of cervical vertebrae maturation: a systematic review. Angle Orthod. 2022;92(6):796-804. DOI: https://doi.org/10.2319/031022-210.1
14. Amasya H, Cesur E, Yıldırım D, Orhan K. Validation of cervical vertebral maturation stages: artificial intelligence vs human observer visual analysis. Am J Orthod Dentofacial Orthop. 2020;158(6):e173-e179. DOI: https://doi.org/10.1016/j.ajodo.2020.08.014

Publication of the article:

«Bulletin of problems biology and medicine», 2026 Issue 2, 181, 211-216 pages, index UDC 616.314-089.23:378.147

DOI:

10.29254/2077-4214-2026-2-181-211-216