Preliminary assessment of blood loss during surgical treatment of endocrine diseases using decision trees

Medical institutions and clinics accumulate a significant amounts of data that can and should be used in planning clinical and operational activities. There are intuitive connections between influencing factors and target KPIs that cannot be described by functional dependencies. Such conditions give rise to a wide range of tasks that can be addressed using machine learning and artificial intelligence methods. This article examines the task of predicting blood loss during the surgical treatment of endocrine system disorders. Machine learning methods based on decision trees are used to estimate blood loss. The data for the study were provided by one of the world’s leading clinics of endocrine surgery from St. Petersburg.

1. Kobrinskii BA. Artificial intelligence systems in surgery: A review of opportunities, limitations, and prospects. Review. Russian Journal of Pediatric Surgery, Anesthesia and Intensive Care. 2023; 13(3): 385-404. (In Russ.) doi: 10.17816/psaic1547.

2. Boldina YS, Ivshin AA. Machine learning opportunities to predict obstetric haemorrhages. Akusherstvo, Ginekologia i Reprodukcia = Obstetrics, Gynecology and Reproduction. 2024; 18(3): 365-381. (In Russ.) doi: 10.17749/2313-7347/ob.gyn.rep.2024.491.

3. Al-Yusef N, Bulatova L, Gurov O. Artificial Intelligence in Vascular Surgery: an Ethico- Philosophical Analysis of Technological Advancement. Artificial societies. 2025; 20(2). (In Russ.) doi: 10.18254/S207751800034958-2.

4. Geltser BI, Shahgeldyan KJ, Rublev VY, et al. Machine Learning Methods for Prediction of Hospital Mortality in Patients with Coronary Heart Disease after Coronary Artery Bypass Grafting. Kardiologiia. 2020; 60(10): 38-46 (In Russ.)

5. Ovcharenko EA, Klyshnikov KYu, Kutikhin AG, Frolov AV. Machine learning in the problem of adverse cardiovascular events prognosis in patients after coronary artery bypass surgery. Clinical and Experimental Surgery. Petrovsky Journal. 2023; 11(3): 16-28. (In Russ.) doi: 10.33029/2308-1198-2023-11-3-16-28.

6. Baranov AA, Namazova-Baranova LS, Smirnov IV, et al. Methods and means of complex intellectual analysis of medical data. Proceedings of the Institute of System Analysis of the Russian Academy of Sciences. 2015; 65(2): 81-93. (In Russ.)

7. Gusev AV. Perspectives of neural networks and deep machine learning in the creation of solutions for health care. Physician and information technologies. 2017; 3: 92-105.(In Russ.)

8. Sakhibgareeva MV, Zaozersky AYu. Development of the system of forecasting disease diagnoses on the basis of artificial intelligence. Bulletin of the Russian State Medical University. 2017; 6: 42-46. (In Russ.)

9. Mednikov DA, Protasova ZU, Krikunova EV. Intellectual systems to support medical decision-making in cardiology practice. In Collection: Youth and knowledge – guarantee of success-2021. Collection of scientific papers of the 8th International Youth Scientific Conference. In 3 v. Kursk, 2021. Р.225-245.(In Russ.)

10. Boulitsakis LS, Green D, Holland M, Al Moubayed N. Predicting acute clinical deterioration with interpretable machine learning to support emergency care decision making. Sci. Rep. 2023; 13: 13563.

11. Nohara Y, Matsumoto K, Soejima H, Nakashima N. Explanation of machine learning models using shapley additive explanation and application for real data in hospital. Comput. Methods Programs Biomed. 2022; 214: 106584.

12. Feretzakis G, Sakagianni A, Anastasiou A, et al. Integrating Shapley Values into Machine Learning Techniques for Enhanced Predictions of Hospital Admissions. Appl. Sci. 2024; 14: 5925. 13. Зюзин В.С. Предоперационная оценка риска кровотечения у кардиохирургических пациентов // Хирургическая практика. – 2024. – №9(2). – С.80-96. [Zyuzin VS. Preoperative bleeding risk assessment in cardiac surgery patients. Surgical practice. 2024; 9(2): 80-96. (In Russ.)] dоi: 10.5922/2223-2427-2024-9-2-6.

13. Matinyan NV, Gyokova EV, Ivanova TE, et al. Massive blood loss in pediatric cancer surgery. Anesteziologiya i Reanimatologiya. 2024; 1: 31-40. (In Russ.) doi: 10.17116/anaesthesiology202401131.

14. Boldina YS, Ivshin AA. Machine learning opportunities to predict obstetric haemorrhages. Akusherstvo, Ginekologia i Reprodukcia. 2024; 18(3): 365-381.(In Russ.) doi: 10.17749/2313-7347/ob.gyn.rep.2024.491.

15. Abdualimov TP, Obrezan AG. Detection of coronary arterial lesions using deep learning algorithms. Cardiology: news, opinions, training. 2021; 9(2): 9-13. (In Russ.)

16. Drapkina YS, Makarova NP, Vasiliev RA, Amelin VV, Kalinina EA. Comparison of prognostic models built using different methods of machine learning, by the example of predicting the results of infertility treatment by assisted reproductive technologies. Obstetrics and Gynecology. 2024; 2: 97-105. (In Russ.)

17. Korchagin MP, Govorov AV, Vasiliev AO, Gritskov IO, Pushkar DYu. Neural networks in oncourology. Vestnik urologii. 2024; 12(4): 91-101.(In Russ.)

18. Drapkina YS, Makarova NP, Vasiliev RA, et al. Study of analytical processing of clinical-anamnestic and embryological data of patients in the program of assisted reproductive technologies by different methods of machine learning. Obstetrics and Gynecology. 2024; 3: 96-107. (In Russ.)

19. Huang T, Le D, Yuan L, Xu S, Peng X. Machine learning for prediction of in-hospital mortality in lung cancer patients admitted to intensive care unit. PLoS ONE. 2023; 18: e0280606.

20. Xie F, Zhou J, Lee JW, et al. Benchmarking emergency department prediction models with machine learning and public electronic health records. Sci. Data. 2022; 9: 658.

21. Tschoellitsch T, Seidl P, Böck C, et al. Using emergency department triage for machine learning-based admission and mortality prediction. Eur. J. Emerg. Med. 2023; 30: 408-416.

22. GotoT, Camargo CA, Faridi MK, et al. Machine learning-based prediction of clinical outcomes for children during emergency department triage. JAMA Netw. Open. 2019; 2: e186937.

23. Feretzakis G, Sakagianni A, Loupelis E, et al. Predicting Hospital Admission for Emergency Department Patients: A Machine Learning Approach. Stud. Health Technol. Inform. 2022; 289: 297-300.

24. Gafanovich EY, Sokolov IM, Konobeeva EV, Kashirina IL, Firyulina MA. Study of the main factors of influence of adherence to treatment with statins using “decision trees”. Modeling, optimization and information technologies. 2021; 9(3). (In Russ.)

25. Golubkov AV, Gavrilova MP. Classification of epidemiologic forecasts and application of gradient bousting in prophylactic medicine. Medline.ru. Russian Biomedical Journal. 2021; 22: 328-343.(In Russ.)

26. Mironov DS, Spirin IA, Usynina AA, Postoev VA. Possibilities of applying machine learning methods to improve the quality of prenatal diagnosis of congenital malformations: scoping review. Medical Doctor and Information Technologies. 2025; 3: 22-35. (In Russ.) doi: 10.25881/18110193_2025_3_22.

27. Friedman JH. Greedy Function Approximation: A Gradient Boosting Machine. Ann. Stat. 2001; 29: 1189-1232.

28. James G, Whitton D, Hastie T, Tibshirani R. Introduction to statistical learning with examples in R. Moscow: DMK-press, 2018. (In Russ.)

29. Kabakov RI. R in action. Data analysis and visualization in the R language. Moscow: DMK-press, 2014. (In Russ.)

30. Parshakova MS, Semenov AA, Laskin MB. Operation duration estimation by ensemble methods of decision trees. Informatization and communication. 2025; 3: 89-97. (In Russ.) doi: 10.34219/2078-8320-2025-16-3-89-97.