A neural network for predicting occurrence of uterine fibroids in women of reproductive age
https://doi.org/10.17749/2313-7347/ob.gyn.rep.2025.605
Abstract
Aim: to create a model for predicting emergence of uterine leiomyoma (UL) using neural network analysis of risk factors and to evaluate its prognostic characteristics.
Materials and Methods. A retrospective case-control study with 209 patients aged 20–47 years was performed covering the years from 2022 to 2024. Two groups of patients were identified: 1 – 106 women with UL, 2 – 103 patients without UL. Preliminary data processing was carried out, followed by a quantitatively analyzed relationship between risk factors and UL development using neural network analysis. The multilayer perceptron method was used to create a prognostic model for predicting UL emergence.
Results. During the study, there were selected 12 model-based factors showing statistically significant inter-group differences: body mass index (BMI), age at menarche, number of abortions and spontaneous abortions, age at first birth, presence of arterial hypertension (AH), benign ovarian tumors, history of in vitro fertilization, level of anti-Müllerian hormone, number of pregnancies, serum cholesterol and glucose levels. The prediction accuracy for the developed model was 92.3 %, sensitivity – 90.6 %, specificity – 94.2 %. The predictive value was confirmed using ROC analysis – the area under the curve was 0.93 (95 % confidence interval = 0.91–0.94; p < 0.001), which proves the promise of this method for clinical practice. Modifiable and potentially modifiable factors included increased BMI, AH, benign ovarian tumors, cholesterol and glucose levels. Such factors are considered as most relevant, due to an opportunity to be directly or indirectly affected, which proves an importance for preventive approach to this disease.
Conclusion. The developed model is an effective tool for predicting UL emergence (accuracy 92.3%), the use of which in clinical practice will allow shifting from the established paradigm of radical treatment to a preventive approach.
About the Authors
A. M. Ziganshin
Bashkir State Medical University, Ministry of Health of the Russian Federation
Russian Federation
Russian Federation
Aidar M. Ziganshin, MD, Dr Sci Med, Prof.
3 Lenin Str., Ufa 450008
G. B. Dikke
Inozemtsev Academy of Medical Education
Russian Federation
Russian Federation
Galina B. Dikke, MD, Dr Sci Med, Prof.
22 lit. М, Moskovskiy Prospekt, Saint Petersburg 190013
A. R. Yanbarisova
Bashkir State Medical University, Ministry of Health of the Russian Federation
Russian Federation
Russian Federation
Aliya R. Yanbarisova
3 Lenin Str., Ufa 450008
References
1. Sanoev B.A., Niyozova G.Sh., Hikmatova N.I. Macro- and microscopic manifestations of uterine leiomyomas. [Makro- i mikroskopicheskie proyavleniya lejomiomy matki]. Novyj den' v medicine. 2020;30(2):526–8. (In Russ.).
2. Cheng L.-C., Li H.-Y., Gong Q.-Q. et al. Global, regional, and national burden of uterine fibroids in the last 30 years: Estimates from the 1990 to 2019 Global Burden of Disease Study. Front Med. 2022;9:1003605. https://doi.org/10.3389/fmed.2022.1003605.
3. Giuliani E., As-Sanie S., Marsh E.E. Epidemiology and management of uterine fibroids. Int J Gynaecol Obstet. 2020;149(1):3–9. https://doi.org/10.1002/ijgo.13102.
4. Adamyan L.V., Sonova M.M., Arslanyan K.N., Loginova O.N. Modern aspects of complex treatment of hysteromyoma. [Sovremennye aspekty kompleksnogo lecheniya miomy matki]. Lechashchij vrach. 2019;(3):46–50. (In Russ.).
5. Navarro A., Bariani M.V., Yang Q., Al-Hendy A. Understanding the impact of uterine fibroids on human endometrium function. Front Cell Dev Biol. 2021;9:633180. https://doi.org/10.3389/fcell.2021.633180.
6. Aganezova N.V., Aganezov S.S., Shilo M.M. Uterine fibroids: modern practical aspects of the disease. [Mioma matki: sovremennye prakticheskie aspekty zabolevaniya]. Problemy reprodukcii. 2022;28(4):97–105. (In Russ.). https://doi.org/10.17116/repro20222804197.
7. Krasnopolskaya K.V., Kogan I.Yu. Uterine fibroids and infertility: coping strategies: a guide for physicians. [Mioma matki i besplodie: strategii preodoleniya: rukovodstvo dlya vrachej]. Moscow: GEOTAR-Media, 2021. 144 p. (In Russ.).
8. Don E.E., Mijatovic V., van Eekelen R., Huirne J.A.F. The effect of myomectomy on reproductive outcomes in patients with uterine fibroids: A retrospective cohort study. Reprod Biomed Online. 2022;45(5):970–8. https://doi.org/10.1016/j.rbmo.2022.05.025.
9. Gupta J.K., Sinha A.S., Lumsden M.A., Hickey M. Uterine artery embolization for symptomatic uterine fibroids. Cochrane Database Syst Rev. 2014;2014(12):CD005073. https://doi.org/10.1002/14651858.CD005073.pub4.
10. Strizhakov A.N., Davydov A.I., Pashkov V.M., Lebedev V.A. Benign diseases of the uterus. [Dobrokachestvennye zabolevaniya matki]. Moscow: GEOTAR-Media, 2011. 288 p. (In Russ.).
11. Strauss J.F., Barbieri R.L., Gargiulo A.R. Yen and Jaffe’s Rеproduсtive Еndocrinologу. 8th ed. [Reproduktivnaya endokrinologiya Jena i Dzhaffe. Fiziologiya, patofiziologiya, klinika, diagnostika i lechenie. 8-e izd]. Moscow: MIA, 2022. 1220 p. (In Russ.).
12. Sohn G.S., Cho S., Kim Y.M. et al.; Working Group of Society of Uterine Leiomyoma. Current medical treatment of uterine fibroids. Obstet Gynecol Sci. 2018;61(2):192–201. https://doi.org/10.5468/ogs.2018.61.2.192.
13. Makatsariya A.D., Vorobev A.V. Up-to-date research and clinical strategies in gynecology and perinatology. [Novejshie issledovaniya i klinicheskie praktiki v oblasti ginekologii i perinatologii]. Obstetrics, Gynecology and Reproduction. 2024;18(5):620–4. (In Russ.). https://doi.org/10.17749/2313-7347/ob.gyn. rep.2024.583.
14. Clinical guidelines – Uterine fibroids – 2024-2025-2026 (25.09.2024). [Klinicheskie rekomendacii – Mioma matki – 2024-2025-2026 (25.09.2024). Moscow: Ministerstvo zdravoohraneniya Rossijskoj Federacii, 2024. 23 p. (In Russ.). Available at: http://disuria.ru/_ld/14/1468_kr24O34p1D39p0M.pdf. [Accessed: 03.12.2024].
15. Srinivas T., Lulseged B., Attari M.M.A. et al. Patient characteristics associated with embolization versus hysterectomy for uterine fibroids: a systematic review and meta-analysis. J Am Coll Radiol. 2024;21(5):729–39. https://doi.org/10.1016/j.jacr.2023.12.018.
16. Borah B.J., Yao X., Laughlin-Tommaso S.K. et al. Comparative effectiveness of uterine leiomyoma procedures using a large insurance claims database. Obstet Gynecol. 2017;130(5):1047–56. https://doi.org/10.1097/AOG.0000000000002331.
17. Yang J., Fan X., Gao J. et al. Cost effectiveness analysis of total laparoscopic hysterectomy versus total abdominal hysterectomy for uterine fibroids in Western China: a societal perspective. BMC Health Serv Res. 2022;22(1):252. https://doi.org/10.1186/s12913-022-07644-9.
18. Stewart E.A. Clinical practice. Uterine fibroids. N Engl J Med. 2015;372(17):1646–55. https://doi.org/10.1056/nejmcp1411029.
19. MacEachern S.J., Forkert N.D. Machine learning for precision medicine. Genome. 2020;64(4):416–25. https://doi.org/10.1139/gen-2020-0131.
20. Ratna M.B., Bhattacharya S., Abdulrahim B., McLernon D.J. A systematic review of the quality of clinical prediction models in in vitro fertilisation. Hum Reprod. 2020;35(1):100–16. https://doi.org/10.1093/humrep/dez258.
21. El Sabeh M., Borahay M. A. The future of uterine fibroid management: a more preventive and personalized paradigm. Reprod Sci. 2021;28(11):3285–8. https://doi.org/10.1007/s43032-021-00618-y.
22. Wise L.A., Laughlin-Tommaso S.K. Epidemiology of uterine fibroids: from menarche to menopause. Clin Obstet Gynecol. 2016;59(1):2–24. https://doi.org/10.1097/GRF.0000000000000164.
23. Harmon Q.E., Brasky T.M. Risk factors for uterine fibroids: time to build on what we have learned. Fertil Steril. 2020;114(4):755–6. https://doi.org/10.1016/j.fertnstert.2020.07.059.
24. Bajwa J., Munir U., Nori A. et al. Artificial intelligence in healthcare: transforming the practice of medicine. Future Healthc J. 2021;8(2):e188–e194. https://doi.org/10.7861/fhj.2021-0095.
25. Briganti G., Le Moine O. Artificial intelligence in medicine: today and tomorrow. Front Med. 2020;7:509744. https://doi.org/10.3389/fmed.2020.00027
What is already known about this subject?
► Uterine leiomyoma (UL) holds a leading position in the pattern of female genital organ diseases, being in second place among all gynecological diseases.
► Today, a paradigm shift in the approach to UL is required as well as development of a model for personalized primary and secondary prevention taking into consideration of the expected risk factors.
► Neural network analysis can become a promising tool for optimizing medical processes, which determines its usefulness and relevance in healthcare.
What are the new findings?
► A model for predicting the UL emergence using neural network analysis of risk factors is described, where the number of input neurons comprised 12 units; two hidden layers containing 5 and 7 units, and 2 output neurons (UL present/not present) are included.
► The prediction accuracy for the developed model was 92.3 %, sensitivity – 90.6 %, specificity – 94.2 %, which proves the promise of this method for clinical practice.
► ROC analysis characterizing the informativeness of neural network data analysis in the early UL diagnostics emphasizes the method predictive value: area under the curve = 0.93 (95 % confidence interval = 0.91–0.94; p < 0.001).
How might it impact on clinical practice in the foreseeable future?
► In the future, the developed model can be used for the early UL detection among women undergoing annual screening, which will shift from the established paradigm of radical treatment to a preventive approach.
► A deeper understanding of the tumor etiology will be а key to developing new methods for UL treatment and prevention.
Review
For citations:
Ziganshin A.M., Dikke G.B., Yanbarisova A.R. A neural network for predicting occurrence of uterine fibroids in women of reproductive age. Obstetrics, Gynecology and Reproduction. 2025;19(2):180-191. (In Russ.) https://doi.org/10.17749/2313-7347/ob.gyn.rep.2025.605
Views:
803
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Email this article 
