Prototype of an artificial intelligence system for spinal diseases diagnostics with integration into a web application and a telegram bot

Background. Spinal disorders are observed in a significant number of people of different ages. Improving the accuracy of diagnosing spinal disorders using medical artificial intelligence systems (MAIS) enables timely treatment initiation, preventing serious complications.
Research Objective. Rationale for the development and application of new AI services for the diagnosis of spinal diseases. Analysis of the diagnostic accuracy of AI services. Development of a physician-friendly AI system for the automatic analysis of spinal X-rays. Identification of conditions for increasing physician interest in AI services. Materials and Methods. To implement the study, a preliminary analysis of the accuracy of existing AI services for disease diagnosis and the potential for improving accuracy through the careful selection of neural network models (NNMs) was conducted. The process of creating a neural network-based software system for classifying and identifying pathologies based on spinal X-rays is described. The developed user interfaces for a web application and a Telegram bot providing quick access to diagnostic results using mobile devices are presented.
Results. Benchmarks for the accuracy of spinal disease diagnostics were determined. A dataset available on Kaggle. com was used for the first stage of developing and training a neural network for spinal disease diagnostics. The developed NNM was integrated into a web application and Telegram bot to provide automated diagnostic solutions. Potential conditions for increasing physician interest in AI services are demonstrated.
Conclusion. The developed MAIS prototype ensures the specified accuracy in diagnosing scoliosis and spondylosis using X-ray images from the test dataset and can be used to analyze labeled and prepared images provided by medical institutions. The results open up opportunities for further development and improvement of the developed system.

1. Ukaz Prezidenta RF №124 ot 15.02.2024 g. «O vnesenii izmenenij v Ukaz Prezidenta Rossijskoj Federacii ot 10 oktyabrya 2019 g. №490 «O razvitii iskusstvennogo intellekta v Rossijskoj Federacii» i v Nacional'nuyu strategiyu, utverzhdennuyu etim Ukazom». Available at: http://publication.pravo.gov.ru/document/0001202402150063 Accessed 05.06.2025. (In Russ.)

2. National Legal Internet Portal of the Republic of Belarus. Artificial Intelligence in Belarus: what technologies are being developed and how they will be regulated. 09.06.2025. Available at: https://pravo.by/novosti/obshchestvenno-politicheskie-i-v-oblasti-prava/2025/june/88987. Accessed 12.06.2025. (In Russ.)

3. Pain in the spine: types, why the back hurts, symptoms, diagnosis and treatment. RAMSEY. Medical diagnostic center. June 3, 2025. Available at: https://msk.ramsaydiagnostics.ru/blog/bol-v-spine/ Accessed 20.06.2025. (In Russ.)

4. Diseases of the spine treatment, symptoms, causes, diagnosis. The Moscow centers of V.I.Dikul. 2020-01-20. Available at: https://www.dikul.net/wiki/zabolevanija-pozvonochnika/ Accessed 20.06.2025. (In Russ.)

5. What are spinal diseases? Treatment. 2024. Clinic of aesthetic medicine. Available at: https://clinikanika.ru/blog/kakie-byvayut-zabolevaniya-pozvonochnika-lechenie Accessed 20.06.2025. (In Russ.)

6. Diagnosis of spinal diseases: types, methods. Workshop. Health. 2025 Available at: https://mz-clinic.ru/articles/diagnostika-zabolevanij-pozvonochnika/?ysclid=mc1wa86bmi492651975 Accessed 20.06.2025. (In Russ.)

7. Diseases of the spine. Arthromed Center. 2025. Clinic of joints and spine. Available at: https://artrombst.ru/bolezni-pozvonochnika/?ysclid=mc1qqtb5iu168807640 Accessed 20.06.2025. (In Russ.)

8. Esper.Scoliosis. An AI service. Center for Diagnostics and Telemedicine. Available at: https://mosmed.ai/service_catalog/esperscoliosis/Accessed 20.06.2025. (In Russ.)

9. MRI of the spine and artificial inteligence. Analysis of MRI images of the spine using AI. Savings Bank AI. 02.12.2024. Available at: https://sbermed.ai/mrt-pozvonochnika-i-iskusstvenniy-intellekt Accessed 20.06.2025. (In Russ.)

10. Trufanov GE, Efimtsev AY. Artificial intelligence technologies in MR-neuroimaging. The radiologist's View. Russian Journal of Personalized Medicine. 2023; 3(1): 6-7. (In Russ.) doi: 10.18705/2782-3806-2023-3-1-6-17.

11. Bobrovskaya TM, Vasilev YuA, Nikitin NYu, Arzamasov КM. Approaches to building radiology datasets. Medical Doctor and Information Technologies. 2023; 4: 14-23. (In Russ.) doi: 10.25881/18110193_2023_4_14.

12. Fraiwan M, Audat Z, Fraiwan L, Manasreh T. Using deep transfer learning to detect scoliosis and spondylolisthesis from x-ray images. PLoS ONE. 2022; 17(5). (In Russ.) doi: 10.1371/journal.pone.0267851.

13. Zhang J, Lin H, Wang H, Xue M, et al. Detection and localization of lumbar spondylolisthesis using a deep learning system. Frontiers in Bioengineering and Biotechnology. 2023. (In Russ.) doi: 10.3389/fbioe.2023.1194009.

14. Kassab DK, Kamyshanskaya IG, Trukhan SV. A new artificial intelligence program for the automatic evaluation of scoliosis on frontal spinal radiographs: Accuracy, advantages and limitations. Digital Diagnostics. 2024; 5(2): 243-254. (In Russ.) doi: 10.17816/DD630093.

15. Berezovsky V, Vygovskaya N. An overview of neural networks for medical image recognition. E3S Web of Conferences. 2023; 460: 04028. (In Russ.) doi: 10.1051/e3sconf/202346004028.

16. Human-AI Interfaces: the key to the future of interaction / Habr. October 28, 2024. Available at: https://habr.com/ru/articles/854038/ Accessed 05.06.2025. (In Russ.)

17. Tumanov NA. The use of a web application based on artificial intelligence for registration of medical documentation. Obstetrics and Gynecology. 2025; 4: 125-130. (In Russ.) doi: 10.18565/aig.2025.54.

18. The web interface of the network of express laboratories of Russian Railways Medicine. Multilingual "landing" with a personal account of the client and integration with the website of Public Services. 2024. // Projects Initium. Available at: https://initium.ru/projects/rzd_medicine_web/ Accessed 05.06. 2025. (In Russ.)

19. Chatbots for a medical clinic Internet. November 5, 2024. Available at: https://developers.sber.ru/help/salutebot/chatbot-for-medical-clinic?ysclid=m9s6balont731801598 Accessed June 19, 2025. (In Russ.)

20. What is a bot? AI STUDIOS. Published on June 4, 2025. Available at: https://www.aistudios.com/ru/tech-and-ai-explained/what-is-a-bot Accessed June 19, 2025. (In Russ.)

21. Frolova M. Dr. Aibolit the first medical Telegram bot has been created in Russi Internet. Available at: https://iz.ru/1588332/mariia-frolova/doktor-ai-bolit-v-rossii-sozdali-pervyi-meditcinskii-telegram-bot Accessed June 29, 2025. (In Russ.)

22. Telegram as a tool for medical consultations. LinkBaza. 07.06.2024. Available at: https://linkbaza.com/blog/articles/medicina-tv?ysclid=mbxkuzz7ic169497422. Accessed June 29, 2025. (In Russ.)

23. PNRPU has taught artificial intelligence to diagnose scoliosis. 29.01.2024. Available at: https://naked-science.ru/article/column/v-pnt-diagnostirovat-skol. Accessed 29.06. 2025. (In Russ.)

24. Shitov ID, Nikitin VN, Ivanova MD, et al. The use of computer vision to determine reference points in the assessment of posture disorders. Applied Mathematics and Control Sciences. 2023; 4: 94-106. (In Russ.) doi: 10.15593/2499-9873/2023.4.06.

25. How AI services help therapists make diagnoses. Savings Bank AI. Available at: https://sbermed.ai/ii-v-postanovke-diagnozov Accessed 05.06. 2025. (In Russ.)

26. Improve the accuracy of diagnosis of ear, throat, and nose diseases with Pirogov.AI. Available at: https://pirogov.ai Accessed 05.06. 2025. (In Russ.)

27. Artificial intelligence for medical imaging. BOTKIN AI. Available at: https://botkin.ai/ Accessed 05.06. 2025. (In Russ.)

28. Borisov DA. Using a neural network for analyzing medical images. Medical Consulting Center «Private Healthcare». Available at: https://www.csi-med.ru/news/625/ Accessed 05.06. 2025. (In Russ.)

29. Vasilev YuA, Zinchenko VV, Kudryavtsev ND, et al. Assessment of satisfaction and involvement of radiologists when using artificial intelligence software. Medical doctor and information technology. 2024; 1: 70-81. (In Russ.) doi: 10.25881/18110193_2024_1_70.

30. The specifics of designing medical interfaces • UX design. Pavlov's dog. Available at: https://new.sobakapav.ru/publications/medical-interfaces/ Accessed 19.06.2025. (In Russ.)

31. Datasets: what they are and how to find them. An overview of datasets for various tasks and machine learning. SKILLFACTORY. Available at: https://blog.skillfactory.ru/datasety-chto-eto-takoe-i-kak-ih-nayti/ Accessed 05.06. 2025. (In Russ.)

32. Fraiwan M, Audat Z, Manasreh T. The vertebrae X-ray images: A dataset of scoliosis, spondylolisthesis, and normal vertebrae X-ray images. Internet. Available at: https://www.kaggle.com/datasets/yasserhessein/the-vertebrae-xray-images. Accessed June 29, 2025. (In Russ.)

33. Banachevich K, Massaron L. Kaggle book. Machine learning and data analysis. Translated from English St. Petersburg: BHV-Petersburg, 2024. 448 p. (In Russ.)

34. Google's Collaborative Lab. Internet. Available at: https://colab.google Accessed 29.05.2025. (In Russ.)

35. Pwtorch Documentation: Official website Internet. Available at: https://pytorch.org/docs/stable/index.html Accessed 29.06.2025. (In Russ.)

36. ResNet-18 and ResNet-50 architectures. Internet. Available at: https://proproprogs.ru/nn_pytorch/pytorch-arhitektury-resnet-18-i-resnet-50 Accessed 29.06.2025. (In Russ.)

37. Florian J. Optimization algorithm: from SGD to Adam. Internet. Available at: https://medium.com/@florian_algo/optimization-algorithm-from-sgd-to-adam-50ea22187951 Accessed 29.06.2025. (In Russ.)

38. Amar R. We implement and compare model optimizers in deep learning. The blog of the Skillfactory company. Internet. Available at: https://habr.com/ru/companies/skillfactory/articles/525214 Accessed 29.06.2025. (In Russ.)

39. Deval S. Cross-entropy losses: introduction, applications, code. Internet. Available at: https://www.v7labs.com/blog/cross-entropy-loss-guide Accessed 29.06.2025. (In Russ.)

40. Sachin P. Intuitive Guide to Data Augmentation in Deep Learning – Techniques with examples. Internet. Available at: https://geekpython.in/data-augmentation-in-deep-learning Accessed 29.06.2025. (In Russ.)

41. Aman Kh. Class Balancing in Machine Learning. Internet. Available at: https://thecleverprogrammer.com/2021/04/25/class-balancing-in-machine-learning Accessed 29.06.2025. (In Russ.)

42. How to properly visualize data at work. Courses and materials from SF Education. Internet. Available at: https://blog.sf.education/kak-pravilno-vizualizirovat-dannye-v-data-science Accessed 29.06.2025. (In Russ.)

43. Выговская Н.В. Обнаружение сколиоза и спондилолистеза по рентгеновским снимкам поз­воночника с визуализацией результатов обучения модели интернет. Доступно по: https://github.com/VygovskayaNatalya/AI_system_diagnostic_Scoliosis_Spond/blob/main/%D0%A4%D0%98%D0%9D%D0%90%D0%9B_%D1%81_%D0%B2%D0%B8%D0%B7%D1%83%D0%B0%D0%BB%D0%B8%D0%B7_%D0%B1%D0%BB%D0%BE%D0%BA%D0%BD__ResNet50_aug_balans_95__.ipynb Ссыл­ка активна на 29.06.2025.

44. Frederik vom Lehn Interpreting Training/ Validation Accuracy and Loss. Nov 7, 2023 Internet. Available at: https://medium.com/@frederik.vl/interpreting-training-validation-accuracy-and-loss-cf16f0d5329f Accessed 29.06.2025. (In Russ.)

45. Error matrix confusion_matrix() in scikit-learn. Habr. Internet. Available at: https://habr.com/ru/articles/868636 Accessed 29.06.2025. (In Russ.)

46. Aiogram Documentation. Release 3.20.0. post0 aiogram Team. Official website. Available at: https://aiogram.readthedocs.io/_/downloads/en/latest/pdf/ Accessed April 29, 2025.

47. Guide to FastAPI. Documentation FastAPI. Available at: https://rhkina.gitlab.io/fastapi/ Accessed 29.06.2025. (In Russ.)

48. Service catalogs AI. The Med. AI platform. Available at: https://mosmed.ai/service_catalog/ Accessed 29.06.2025. (In Russ.)

49. Vankov VV, Artemova OR, Karpov OE, et al. Results of the implementation of artificial intelligence in the Russian healthcare. Medical doctor and information technologies. 2024; 3: 32-43. (In Russ.) doi: 10.25881/18110193_2024_3_32.