Diagnostic machine learning model for preoperative stratification of patients with benign ovarian tumor-like lesions
Toneeva S.N., Toneev E.A., Volkova N.A., Klinysheva S.Yu., Safiullina A.N., Pisklyukov D.R.
Objective: To develop and evaluate a diagnostic model for stratifying patients with ovarian tumor-like lesions to optimize treatment strategies and reduce the risk of overtreatment.
Materials and methods: This study included 288 patients who underwent laparoscopic surgery for ovarian tumor-like lesions. According to histological findings, 44 (15.3%) patients had functional cysts, while 244 (84.7%) had non-functional benign lesions. The model incorporated the following predictors: HE4, CA125, neutrophil-to-lymphocyte ratio (NLR), body mass index (BMI), lesion size on ultrasound, and the number of years since menopause. A Decision Tree Classifier algorithm was used to construct the model. Seventy percent of the dataset (202 patients) was allocated for training, and the remaining 30% (86 patients) served as an independent test set.
Results: In the training set, the model achieved an AUC of 0.852. In the test set, the AUC was 0.835, with a sensitivity and specificity of 81.1% and 84.6%, respectively. The application of the model improves the accuracy of stratifying patients by the likelihood of a functional lesion and reduces the risk of unnecessary surgical intervention.
Conclusion: The developed diagnostic model may serve as an effective clinical decision-support tool for managing patients with ovarian tumor-like lesions. External validation of this model is required.
Authors' contributions: Toneeva S.N. – conception and design of the study, data analysis, editing of the manuscript; Toneev E.A., Safiullina A.N. – collection of materials, statistical analysis; Volkova N.A. – checking of critical content; Klinysheva S.Yu. – data analysis, editing of the manuscript; Pisklyukov D.R. – drafting of the manuscript.
Conflicts of interest: The authors have no conflicts of interest to declare.
Funding: There was no funding for this study.
Ethical Approval: The study was reviewed and approved by the Research Ethics Committee of the Ulyanovsk Regional Clinical Hospital.
Patient Consent for Publication: All patients provided informed consent for the publication of their data.
Authors' Data Sharing Statement: The data supporting the findings of this study are available upon request from the corresponding author after approval from the principal investigator.
For citation: Toneeva S.N., Toneev E.A., Volkova N.A., Klinysheva S.Yu., Safiullina A.N., Pisklyukov D.R.
Diagnostic machine learning model for preoperative stratification of patients with benign ovarian tumor-like lesions.
Akusherstvo i Ginekologiya/Obstetrics and Gynecology. 2026; (3): 112-118 (in Russian)
https://dx.doi.org/10.18565/aig.2025.230
Keywords
ovarian cyst
benign ovarian neoplasm
References
- Seguin C.L., Lietz A.P., Wright J.D., Wright A.A., Knudsen A.B., Pandharipande P.V. Surveillance in older women with incidental ovarian cysts: maximal projected benefits by age and comorbidity level. J. Am. Coll. Radiol. 2021; 18(1PtA): 10-8. https://dx.doi.org/10.1016/j.jacr.2020.09.048
- Zeng S., Wang X.L., Yang H. Radiomics and radiogenomics: extracting more information from medical images for the diagnosis and prognostic prediction of ovarian cancer. Mil. Med. Res. 2024; 11(1): 77. https://dx.doi.org/10.1186/s40779-024-00580-1
- Srivastava S., Koay E.J., Borowsky A.D., De Marzo A.M., Ghosh S., Wagner P.D. Cancer overdiagnosis: a biological challenge and clinical dilemma. Nat. Rev. Cancer. 2019. 19(6): 349-58. https://dx.doi.org/10.1038/s41568-019-0142-8
- Feeney L., Harley I.J.G., McCluggage W.G., Mullan P.B., Beirne J.P. Liquid biopsy in ovarian cancer: catching the silent killer before it strikes. World J. Clin. Oncol. 2020; 11(11): 868-89. https://dx.doi.org/10.5306/wjco.v11.i11.868
- Vlăduţ C., Bilous D., Ciocîrlan M. Real-life management of pancreatic cysts: simplified review of current guidelines. J. Clin. Med. 2023; 12(12): 4020. https://dx.doi.org/10.3390/jcm12124020
- Sahu S.A., Shrivastava D. A comprehensive review of screening methods for ovarian masses: towards earlier detection. Cureus. 2023; 15(11): e48534. DOI: https://dx.doi.org/10.7759/cureus.43225
- Timmerman D., Planchamp F., Bourne T., Landolfo C., du Bois A., Chiva L. et al. ESGO/ISUOG/IOTA/ESGE Consensus Statement on pre-operative diagnosis of ovarian tumors. Int. J. Gynecol. Cancer. 2021; 31(7): 961-82. https://dx.doi.org/10.1136/ijgc-2021-002565
- Radwan S.M.A.A. The role of interventional radiology in the management of malignant and benign gynecological diseases. Kaunas; 2024. Available at: https://search.proquest.com/openview/a3fb1eaf1cb33f89fae40dc561208fc8/1
- Rai Talapadi N. Biochemical markers and combination testing for the diagnosis of ovarian cancer in women with symptoms or signs suspicious of ovarian cancer. University of Birmingham. Thesis. 2021. Available at: https://etheses.bham.ac.uk/id/eprint/11145/7/RaiTalapadi2021MD.pdf
- Холова С.Х., Хушвахтова Э.Х. Роль онкомаркеров в диагностике женщин с доброкачественными новообразованиями яичников. Вестник медико-социального института Таджикистана. 2024; 4: 66-72. [Kholova S.Kh., Khushvakhtova E.Kh. The role of tumor markers in the diagnosis of women with benign ovarian tumors. Herald of the Medical and Social Institute of Tajikistan. 2024; 4: 66-72 (in Russian)].
- American College of Obstetricians and Gynecologists’ Committee on Practice Bulletins—Gynecology. Practice Bulletin No. 174: Evaluation and Management of Adnexal Masses. Obstet. Gynecol. 2016; 128(5): e210-e226. https://dx.doi.org/10.1097/AOG.0000000000001768
- Jing B., Chen G., Yang M., Zhang Z., Zhang Y., Zhang J. et al. Development of prediction model to estimate future risk of ovarian lesions: a multi-center retrospective study. Prev. Med. Rep. 2023; 35: 102296. https://dx.doi.org/10.1016/j.pmedr.2023.102312
- Li Y., Zhao X., Zhou Y., Gong L., Peng E. Decision tree model for predicting ovarian tumor malignancy based on clinical markers and preoperative circulating blood cells. BMC Med. Inform. Decis. Mak. 2025; 25(1): 94. https://dx.doi.org/10.1186/s12911-025-02934-8
- Zhang T., Pang A., Lyu J., Ren H., Song J., Zhu F. et al. Application of nonlinear models combined with conventional laboratory indicators for the diagnosis and differential diagnosis of ovarian cancer. J. Clin. Med. 2023; 12(3): 844. https://dx.doi.org/10.3390/jcm12030844
- Liu H., Ai H., Liu Y. Exploring the current state and research innovation in endometrial cancer screening. Oncol. Adv. 2025; 3(1): 50-60. https://dx.doi.org/10.14218/OnA.2024.00034
- Moro F., Giudice M.T., Ciancia M., Zace D. et al. Application of artificial intelligence to ultrasound imaging for benign gynecological disorders: systematic review. Ultrasound Obstet. Gynecol. 2025; 65(3): 295-302. https://dx.doi.org/10.1002/uog.29171
Received 25.08.2025
Accepted 28.11.2025
About the Authors
Svetlana N. Toneeva, obstetrician-gynecologist, Gynecological Department, Ulyanovsk Regional Clinical Hospital, 432017, Russia, Ulyanovsk, Third International str., 7, s.toneeva@inbox.ru, https://orcid.org/0009-0003-3101-881XEvgeniy A. Toneev, PhD, thoracic surgeon at the Department of Thoracic Oncology, Regional Clinical Oncology Dispensary; Associate Professor, Department of Hospital Surgery, Faculty of Medicine named after T.Z. Biktimirov, Institute of Medicine, Ecology and Physical Culture, Ulyanovsk State University, 432000, Russia, Ulyanovsk,
L. Tolstoy str., 42, e.toneev@inbox.ru, SPIN-code 2236-3277, AuthorID: 1043371, https://orcid.org/0000-0001-8590-2350
Natalia A. Volkova, Deputy Chief Physician for Obstetric and Gynecological Care, Ulyanovsk Regional Clinical Hospital, 432017, Russia, Ulyanovsk, Third International str., 7; Senior lecturer at the Department of Obstetrics and Gynecology, Faculty of Medicine named after T.Z. Biktimirov, Institute of Medicine, Ecology and Physical Culture, Ulyanovsk State University, 432000, Russia, Ulyanovsk, L. Tolstoy str., 42, n_volkova2010@mail.ru, https://orcid.org/0009-0009-3018-4852
Svetlana Yu. Klinysheva, 2nd year resident at the Faculty of Postgraduate Medical and Pharmaceutical Education, Ulyanovsk State University, 432000, Russia, Ulyanovsk,
L. Tolstoy str., 42, klinyshevazs99@list.ru, https://orcid.org/0009-0007-7686-8593
Aliia N. Safiullina, 6th year student at the Faculty of Medicine named after T.Z. Biktimirov, Institute of Medicine, Ecology and Physical Culture, Ulyanovsk State University, 432000, Russia, Ulyanovsk, L. Tolstoy str., 42, awesome.mukhutdinova@yandex.ru, SPIN-code: 6344-1106, https://orcid.org/0009-0009-1455-8287
Daniil R. Pisklyukov, 2nd year student at the the Faculty of Medicine named after T.Z. Biktimirov, Institute of Medicine, Ecology and Physical Culture, Ulyanovsk State University, 432000, Russia, Ulyanovsk, L. Tolstoy str., 42, danilovdaniil1999@yandex.ru, https://orcid.org/0009-0002-7967-4528
Corresponding author: Aliia N. Safiullina, awesome.mukhutdinova@yandex.ru
Similar Articles
