Artificial intelligence technologies in predicting outcomes and adopting therapeutic tactics in patients with recurrent intracranial meningiomas

INTRODUCTION. Meningiomas are common primary intracranial and spinal tumors in adults. Aggressive meningiomas can recur after surgical removal and radiotherapy. There are no treatment standards for such tumors. Modern artificial intelligence (AI) technologies can help a neurosurgeon predict the behavior of a neoplastic process in the central nervous system.
AIM. Development and evaluation of the effectiveness of a neural network algorithm predicting the further development of a neoplastic process in recurrent intracranial meningiomas.
MATERIALS AND METHODS. To solve the problem, an Excel database was used with patient information obtained from the analysis of medical records. More than 160 multimodal features grouped into sections were used. According to the results of statistical analysis, correlated, uninformative, and features with uneven data distribution within classes were removed. Finally, two of the most appropriate classification models were chosen: decision tree and random forest algorithms.
RESULTS. Four models were built and evaluated based on the results of the work. The basic random forest model showed the best classification accuracy (about 90 %). It also helped to assess the significance of the studied features.
CONCLUSION. Due to the constant growth of multimodal data in neuro-oncology, it is difficult for doctors to analyze them using traditional approaches and predict the behavior of a neoplastic process. Therefore, neurosurgeons need to turn to modern artificial intelligence (AI) technologies for help.

1. Roland G., Pantelis S., Michael D. et al. EANO guideline on the diagnosis and management of meningiomas. Neurooncol. 2021;23(11):1821–1834. Doi: https://doi.org/10.1093/neuonc/noab150.

2. Priya K., Sean A., Roxanne T. et al. A multi-institutional phase II trial of bevacizumab for recurrent and refractory meningioma. Neurooncol Adv. 2022;4(1):1–10. Doi: https://doi.org/10.1093/noajnl/vdac123.

3. Maximilian J., Anna S., Priscilla K., Matthias P. Emerging systemic treatment options in meningioma. J Neuro-oncolog. 2023;161(2):245–258. Doi: http://doi.org/10.1007/s11060-022-04148-8.

4. Ostrom Q. T., Patil N., Cioffi G., Waite K., Kruchko C., Barnholtz-Sloan J. S. CBTRUS Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2013–2017. Neuro-Oncology. 2020;22(1):1–96. Doi: https://doi.org/10.1093/neuonc/noaa200

5. Kukanov K. K., Vorobyova O. M., Zabrodskaya Yu. M., Potemkina E. G., Ushanov V. V., Tastanbekov M. M., Ivanova N. E. Intracranial meningiomas: clinical, intrascopic and pathomorphological causes of recurrence (literature review). Siberian journal of oncology. 2022;21(4):110–123. (In Russ.). Doi: https://doi.org/10.21294/1814-4861-2022-21-4-110-123

6. Kukanov K. K., Ushanov V. V., Zabrodskaya Yu. M., Tastanbekov M. M., Vorobyova O. M., Sitovskaya D. A., Dikonenko M. V. Ways to personalize the treatment of patients with relapse and continued growth of intracranial meningiomas. Russian Journal for Personalized Medicine. 2023;3(3):48–63. (In Russ.). Doi: https://doi.org/10.18705/2782-38062023-3-3-48-63.

7. Certificate of state registration of the database No. RU 2023621571. Register of patients with recurrence and continued growth of intracranial meningiomas; Kukanov K. K., Ushanov V. V., Voinov N. E. 02.05.2023. (In Russ.). EDN: https://elibrary.ru/vbrsbm.

8. Violaris K., Katsarides V., Sakellariou P. The Recurrence Rate in Meningiomas: Analysis of Tumor Location, Histological Grading, and Extent of Resection. Open J Modern Neurosurg. 2012;(2):6–10. Doi: https://doi.org/10.4236/ojmn.2012.21002.

9. Kotecha R. S., Pascoe E. M., Rushing E. J., Rorke-Adams L. B., Zwerdling T., Gao X., Li X., Greene S., Amirjamshidi A., Kim S. K., Lima M. A., Hung P. C., Lakhdar F., Mehta N., Liu Y., Devi B. I., Sudhir B. J., Lund-Johansen M., Gjerris F., Cole C. H., Gottardo N. G. Meningiomas in children and adolescents: a meta-analysis of individual patient data. Lancet Oncol. 2011;12(13):1229–1239. Doi: https://doi.org/10.1016/S1470-2045(11)70275-3.

10. Huntoon K., Toland A. M. S., Dahiya S. Meningioma: a review of clinicopathological and molecular aspects. Front Oncol. 2020;10(10):1–14. Doi: https://doi.org/10.3389/fonc.2020.579599.

11. Commins D., Atkinson R., Burnett M. Review of meningioma histopathology. Neurosurg Focus. 2007;23(4):1–9. Doi: https://doi.org/10.3171/FOC-07/10/E3.

12. Brastianos P., Galanis E., Butowski N. et al. Advances in multidisciplinary therapy for meningiomas. Neuro Oncol. 2019;21(1):118–131. Doi: http://doi.org/10.1093/neuonc/noy136.

13. Chen R., Aghi M. K. Atypical meningiomas. Handb Clin Neurol. 2020; (170):233–244. Doi: https://doi.org/10.1016/B978-0-12-822198-3.00043-4.

14. Debus J., Wuendrich M., Pirzkall A. et al. High efficacy of fractionated stereotactic radiotherapy of large baseof-skull meningiomas: long-term results. J Clin Oncol. 2001;19(15):3547–3553. Doi: https://doi.org/10.1200/JCO.2001.19.15.3547.

15. Cao X., Hao S., Wu Z. et al. Treatment Response and Prognosis After Recurrence of Atypical Meningiomas. World Neurosurg. 2015;84(4):1014–1019. Doi: https://doi.org/10.1016/j.wneu.2015.05.032.

16. Danilov G. V., Ishankulov T. A., Kotik K. V., Shifrin M. A., Potapov A. A. Artificial intelligence technologies in clinical neurooncology. Burdenko’s Journal of Neurosurgery = Zhurnal voprosy neirokhirurgii imeni N. N. Burdenko. 2022;86(6):127–133. (In Russ.). Doi: https://doi.org/10.17116/neiro202286061127

17. Danilov G. V., Shifrin M. A., Kotik K. V., Ishankulov T. A., Orlov Y. N., Kulikov A. S., Potapov A. A. Artificial intelligence in neurosurgery: A systematic review using topic modeling. Part I: Major research areas. Sovremennye Tehnologii v Medicine. 2020;12(5):106–112. Doi: https://doi.org/10.17691/stm2020.12.5.122.

18. Danilov G. V., Shifrin M. A., Kotik K. V., Ishankulov T. A., Orlov Y. N., Kulikov A. S., Potapov A. A. Artificial Intelligence Technologies in Neurosurgery: a Systematic Literature Review Using Topic Modeling. Part II: Research Objectives and Perspectives. Sovremennye Tehnologii v Medicine. 2021;12(6):111–118. Doi: https://doi.org/10.17691/stm2020.12.6.12.

19. Breiman L. Random Forests. Machine Learning. 2001;(45):5–32. Doi: https://doi.org/10.1023/A:1010933404324

20. Kittler J., Hatef M., Duin R. P. W., Matas J. On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998;20(3):226–239.

21. Caruana R., Niculescu-Mizil, A. An Empirical Comparison of Supervised Learning Algorithms. Proceedings of the 23rd International Conference on Machine Learning (Pittsburgh, 25–29 June 2006). 2006. Doi: http://dx.doi.org/10.1145/1143844.1143865.

22. Melamed I. I., Sigal I. H. The study of linear convolution of criteria in multi-criteria discrete programming. Journal. mathem. and mathem. physical. 1995;35(8):1260–1270. (In Russ.).

23. Ho J., Hull S. N. Srihari Decision combination in multiple classifier systems. IEEE Transaction Pattern Analysis and Machine Intelligence. 1994;16(l):66–75.

24. Hajiyev Ya., Shalbuzova K. I. Application of machine learning methods in predicting and early detection of cancer. Sciences of Europe. 2022;(108):48. (In Russ.).

25. Krasko O. V. Statistical analysis of data in medical research. Minsk: Minsk State University of Economics named after A. D. Sakharov; 2014. 127 р..

26. Lemeshko B. Yu. Criteria for checking the deviation of the distribution from the normal law (application guide); Novosibirsk State Technical University. 2014. 192 p. (In Russ.).

27. Explain the random forest method. Available from: https://nerdit.ru/obiasnieniiemietoda-sluchainogho-liesa [Accessed 4 October 2024].