Situational algorithm for predicting postoperative hospitalization duration for cardiac surgery patients using neural networks

The article presents a situational algorithm for analyzing event sequences to predict postoperative time parameters – such as the duration of hospital and intensive care unit stays. It describes the construction of an event model using specialized neural language models. Algorithmic processing was performed using anonymized data from an electronic medical record archive and patient discharge summaries following cardiac surgery. Such approach enables the identification of operation clusters and the prediction of postoperative temporal parameters. The article presents an algorithm for constructing event sequences, describes the analysis method, and reports the results of the method's experimental validation.

1. Hramov A, Ghosh D, Pisarchik A, et al. Artificial intelligence and complex networks meet natural sciences. The European Physical Journal Special Topics. 2025. doi: 10.1140/epjs/s11734-025-01844-0.

2. Andrikov D.A. Open source ML framework algorithms for biophysical models. Eur. Phys. J. Spec. Top. 2025. doi: 10.1140/epjs/s11734-025-01621-z.

3. Bonde A, Varadarajan KM, Bonde N, et al. Assessing the utility of deep neural networks in predicting postoperative surgical complications: a retrospective study. Lancet Digit Health. 2021; 3(8): e471- e485. doi: 10.1016/S2589-7500(21)00084-4.

4. Gao J, et al. The Use of Artificial Neural Network to Predict Surgical Outcomes After Inguinal Hernia Repair. Journal of Surgical Research. 259: 372-378.

5. Tunthanathip T, Sae-Heng S, Oearsakul T, et al. Machine learning applications for the prediction of surgical site infection in neurological operations. Neurosurg Focus. 2019; 47(2): E7. doi: 10.3171/2019.5.FOCUS19241.

6. Andrikov D.A., Andrikov Dm.A., Berezkin, D.V., Popov A.Iu., Proletarsky A.V. Neural network graph architecture of transparent artificial intelligence in medicine. Medical doctor and information technology. 2025; 2: 70-83. (In Russ.) doi: 10.25881/18110193_2025_2_70.

7. Cypko M, Emmert MY, Falk V, Meyer A. Künstliche Intelligenz in der Herzchirurgie. Chirurg. 2020; 91(3): 235-239. doi: 10.1007/s00104-020-01132-8.

8. Sen E, Seckiner SU. The Use of Artificial Neural Networks to Determine In-Hospital Mortality After Coronary Artery Bypass Surgery. J Cardiothorac Vasc Anesth. 2021; 35(8): 2432-2437. doi: 10.1053/j.jvca.2021.03.049.

9. Wise ES, Hocking KM, Brophy CM. Prediction of in-hospital mortality after ruptured abdominal aortic aneurysm repair using an artificial neural network. Journal of Vascular Surgery. 2015; 62(1). doi: 10.1016/j.jvs.2015.02.038.

10. Vijayasimha A, Avanija J. Hybrid deep learning framework for cardiovascular disease diagnosis and prognosis using GAN, LSTM, GRU, VARMA, and deep DynaQ network. 2025; 15: 41346. doi: 10.1038/s41598-025-25296-7.

11. Li B, Verma R, Beaton D, et al. Predicting outcomes following lower extremity open revascularization using machine learning. Scientific Reports. 2024; 14. doi: 10.1038/s41598-024-52944-1.

12. Hassan AM, Rajesh A, Asaad M, et al. Artificial Intelligence and Machine Learning in Prediction of Surgical Complications: Current State, Applications, and Implications. Am Surg. 2023; 89(1): 25-30. doi: 10.1177/00031348221101488.

13. Yalunin A, Nesterov A, Umerenkov D. RuBioRoBERTa: a pre-trained biomedical language model for Russian language biomedical text mining. arXiv preprint arXiv:2204.03951. 2022.

14. Martynyuk P, Kozlov I, Panfilkin A. Applying the proposed method for creating structural models to multilingual collections of text documents using multi-and monolingual BERT models. International Russian Automation Conference. Cham: Springer Nature Switzerland, 2023: 334-343.

15. Blinov P, et al. RuMedBench: a Russian medical language understanding benchmark. International Conference on Artificial Intelligence in Medicine. Cham: Springer International Publishing, 2022: 383-392.

16. Satheakeerthy S, Stretton B, Tsimiklis J, et al. Zero-shot large language model application for surgical site infection auditing. Infection Disease & Health. 2025. doi: 10.1016/j.idh.2025.05.001.

17. Bonde A, Lorenzen S, Brixen G, Troelsen A, Sillesen, M. Assessing the utility of deep neural networks in detecting superficial surgical site infections from free text electronic health record data. Frontiers in Digital Health. 2024; 5. doi: 10.3389/fdgth.2023.1249835.

18. Karpov OE, Andrikov DA, Maksimenko VA, Hramov AE. Prozrachnyj iskusstvennyj intellekt dlya mediciny. Vrach i informacionnye tekhnologii. 2022; 2: 4-11. (In Russ.)

19. Karpov OE, Hramov AE. Prognosticheskaya medicina. Vrach i informacionnye tekhnologii. 2021; 3: 20. (In Russ.)

20. SHarova DE, Mihajlova AA, Gusev AV, et al. Analiz mirovogo opyta v regulirovanii ispol'zovaniya medicinskih dannyh dlya celej sozdaniya sistem iskusstvennogo intellekta na osnove mashinnogo obucheniya. Vrach i informacionnye tekhnologii. 2022; 4: 28-39. (In Russ.)

21. Karpov OE, Hramov AE. Informacionnye tekhnologii, vychislitel'nye sistemy i iskusstvennyj intellekt v medicine. М.: DPK Press, 2022. (In Russ.)

22. Andreev AM, Berezkin DV, Kozlov IA. Gibridnyj podhod k prognozirovaniyu razvitiya situacij na osnove izvlecheniya sobytij iz potokov raznorodnyh dannyh. V sbornike: Gibridnye i sinergeticheskie intellektual'nye sistemy. Materialy IV Vserossijskoj Pospelovskoj konferencii s mezhdunarodnym uchastiem. Pod red. A.V. Kolesnikova, 2018. Р.140-147. (In Russ.)

23. Kozlov IA, Andreev AM, Berezkin DV, Shouman MA. Automated monitoring and forecasting of the development of educational technologies. Handbook of Research on Engineering Education in a Global Context. 2019. Р.311-330.

24. ISO/IEC 20889:2018 Information technology — Security techniques — Privacy-enhancing data deidentification terminology and classification of techniques. 2018. Available from: https://www.iso.org/standard/69373.html. Сited 16.11.2025.

25. European DataProtection Board (EDPB). Guidelines4/2019 on Article 25 Data Protection by Design and by Default. Version 2.0. — 2020. Available from: https://edpb.europa.eu/system/files/2021-04/edpb_guidelines_201904_dataprotection_by_design_and_by_default_v2.0_ru.pdf. Сited 16.11.2025. 26. CVE-2019-25030 Detail. National Vulnerability Database, NIST. Available from: https://nvd.nist.gov/vuln/detail/CVE-2019-25030. Сited 16.11.2025.

26. Howell DC. Statistical methods for psychology. PWS-Kent Publishing Co, 1992.

27. Tukey JW. Comparing individual means in the analysis of variance. Biometrics, 1949. Р.99-114.