Machine learning with ultrasound examination for prediction of intraoperative hypotension during robot-assisted radical prostatectomy

Introduction. Robot-assisted radical prostatectomy is one of the leading methods of prostate cancer treatment. A common complication of general anesthesia during this operation is intraoperative hypotension. In recent years, the use of preoperative ultrasound examinations to predict this condition and carry out personalized prevention has been gaining popularity. Machine learning methods trained with additional predictors

can improve the accuracy of these predictions.

Objective. To improve the treatment outcomes of patients with prostate cancer by optimizing their volemic status in the perioperative period before robot-assisted prostatectomy.

Materials and methods. The prospective study included 64 patients scheduled for robot-assisted radical prostatectomy. Before surgery, patients underwent bedside ultrasound examination to determine the diameters and collapsibility indices of the inferior vena cava and subclavian veins, corrected carotid flow time (cCFT), and respiratory variation of blood flow peak velocity (ΔV). These data were used in the training of machine learning predictive models to ameliorate intraoperative hypotension prediction efficacy.

Results. The respiratory variation of blood flow peak velocity had the highest predictive value (AUROC 0.843, accuracy 75 %). The indicator’s optimal threshold for intraoperative hypotension prediction was 8.33 %. The accuracy of the prediction has been increased using the machine learning model based on gradient boosting with additional predictors (AUROC 0.933, accuracy 95 %).

Conclusions. Determining the respiratory variation of blood flow peak velocity is the most prognostically valuable indicator for intraoperative hypotension prediction during robot-assisted radical prostatectomy. The use of machine learning methods to predict intraoperative hypotension increases the accuracy of prediction.

1. Leonova E. A., Moroz G. B., Shmyrev V. A., Lomivorotov V. V. Intraoperative hypotension. Annals of Critical Care. 2018; (3): 87–96. (In Russ.). https://doi.org/10.21320/1818-474X-2018-3-87-96

2. Guarracino F., Bertini P. Perioperative hypotension: causes and remedies. Journal of Anesthesia, Analgesia and Critical Care. 2022; 2 (1): 17. https://doi.org/10.1186/s44158-022-00045-8

3. Wijnberge M., Schenk J., Bulle E., Vlaar A. P., Maheshwari K., Hollmann M. W., Binnekade J. M., Geerts B. F., Veelo D. P. Association of intraoperative hypotension with postoperative morbidity and mortality: systematic review and meta-analysis. BJS Open. 2021; 5 (1): zraa018. https://doi.org/10.1093/bjsopen/zraa018

4. Tassoudis V., Vretzakis G., Petsiti A., Stamatiou G., Bouzia K., Melekos M., Tzovaras G. Impact of intraoperative hypotension on hospital stay in major abdominal surgery. Journal of Anesthesia. 2011; 25 (4): 492–499. https://doi.org/10.1007/s00540-011-1152-1

5. Gregory A., Stapelfeldt W. H., Khanna A. K., Smischney N. J., Boero I. J., Chen Q., Stevens M., Shaw A. D. Intraoperative Hypotension Is Associated With Adverse Clinical Outcomes After Noncardiac Surgery. Anesthesia & Analgesia. 2021; 132 (6): 1654–1665. https://doi.org/10.1213/ANE.0000000000005250

6. Weinberg L., Li S. Y., Louis M., Karp J., Poci N., Carp B. S., Miles L. F., Tully P., Hahn R., Karalapillai D., Lee D.-K. Reported definitions of intraoperative hypotension in adults undergoing non-cardiac surgery under general anaesthesia: a review. BMC Anesthesiology. 2022; 22 (1): 69. https://doi.org/10.1186/s12871-022-01605-9

7. Kouz K., Hoppe P., Briesenick L., Saugel B. Intraoperative hypotension: Pathophysiology, clinical relevance, and therapeutic approaches. Indian Journal of Anaesthesia. 2020; 64 (2): 90–96. https://doi.org/10.4103/ija.IJA_939_19

8. Temesgen N., Fenta E., Eshetie C., Gelaw M. Early intraoperative hypotension and its associated factors among surgical patients undergoing surgery under general anesthesia: An observational study. Annals of Medicine and Surgery. 2021; 71: 102835. https://doi.org/10.1016/j.amsu.2021.102835

9. Mukkamala R., Schnetz M. P., Khanna A. K., Mahajan A. Intraoperative Hypotension Prediction: Current Methods, Controversies, and Research Outlook. Anesthesia & Analgesia. 2022; 141 (1): 61–73. https://doi.org/10.1213/ANE.0000000000007216

10. Christensen A. L., Jacobs E., Maheshwari K., Xing F., Zhao X., Simon S. E., Domino K. B., Posner K. L., Stewart A. F., Sanford J. A., Sessler D. I. Development and Evaluation of a Risk-Adjusted Measure of Intraoperative Hypotension in Patients Having Nonemergent, Noncardiac Surgery. Anesthesia & Analgesia. 2021; 133 (2): 445–454. https://doi.org/10.1213/ANE.0000000000005287

11. Maheshwari K., Cywinski J. B., Papay F., Khanna A. K., Mathur P. Artificial Intelligence for Perioperative Medicine: Perioperative Intelligence. Anesthesia & Analgesia. 2023; 136 (4): 637–645. https://doi.org/10.1213/ANE.0000000000005952

12. Singhal M., Gupta L., Hirani K. A Comprehensive Analysis and Review of Artificial Intelligence in Anaesthesia. Cureus. 2023; 15 (9): e45038. https://doi.org/10.7759/cureus.45038

13. Varghese C., Harrison E. M., O’Grady G., Topol E. J. Artificial intelligence in surgery. Nature Medicine. 2024; 30 (5): 1257–1268. https://doi.org/10.1038/s41591-024-02970-3

14. Hashemi S., Yousefzadeh Z., Abin A. A., Ejmalian A., Nabavi S., Dabbagh A. Machine Learning-Guided Anesthesiology: A Review of Recent Advances and Clinical Applications. Journal of Cellular & Molecular Anesthesia. 2024; 9 (1): e145369. https://doi.org/10.5812/jcma-145369

15. Kang A. R., Lee J., Jung W., Lee M., Park S. Y., Woo J., Kim S. H. Development of a prediction model for hypotension after induction of anesthesia using machine learning. PloS One. 2020; 15 (4): e0231172. https://doi.org/10.1371/journal.pone.0231172

16. Kouz K., Brockmann L., Timmermann L. M., Bergholz A., Flick M., Maheshwari K., Sessler D. I., Krause L., Saugel B. Endotypes of intraoperative hypotension during major abdominal surgery: a retrospective machine learning analysis of an observational cohort study. British Journal of Anaesthesia. 2023; 130 (3): 253–261. https://doi.org/10.1016/j.bja.2022.07.056

17. Zhao A., Elgendi M., Menon C. Machine learning for predicting acute hypotension: A systematic review. Frontiers in Cardiovascular Medicine. 2022; 9. https://doi.org/10.3389/fcvm.2022.937637

18. Bellini V., Valente M., Bertorelli G., Pifferi B., Craca M., Mordonini M., Lombardo G., Bottani E., Del Rio P., Bignami E. Machine learning in perioperative medicine: a systematic review. Journal of Anesthesia, Analgesia and Critical Care. 2022; 2 (1): 2. https://doi.org/10.1186/s44158-022-00033-y

19. Kim N. Y., Kim K. J., Kim T. L., Shin H. J., Oh C., Lee M. H., Min J. Y., Kim S. Y. Prediction of hypotension after postural change in robot-assisted laparoscopic prostatectomy using esophageal Doppler monitoring: a prospective observational trial. Scientific Reports. 2021; 11 (1): 14589. https://doi.org/10.1038/s41598-021-93990-3

20. Park J.-Y., Yu J., Kim C.-S., Baek J.-W., Jo Y., Kim Y.-K. Effect of pneumatic leg compression on post-induction hypotension in elderly patients undergoing robot-assisted laparoscopic prostatectomy: a double-blind randomised controlled trial. Anaesthesia. 2023; 76 (6): 730–738. https://doi.org/10.1111/anae.15994

21. Antonella C., Discenza A., Rauseo M., Matella M., Caggianelli G., Ciaramelletti R., Mirabella L., Cinnella G. Intraoperative hypotension during robotic-assisted radical prostatectomy: A randomised controlled trial comparing standard goal-directed fluid therapy with hypotension prediction index-guided goal-directed fluid therapy. European Journal of Anaesthesiology. 2025; 42 (10): 916–923. https://doi.org/10.1097/EJA.0000000000002211

22. Lang R. M., Badano L. P., Mor-Avi V., Afilalo J., Armstrong A., Ernande L., Flachskampf F. A., Foster E., Goldstein S. A., Kuznetsova T., Lancellotti P., Muraru D., Picard M. H., Rietzschel E. R., Rudski L., Spencer K. T., Tsang W., Voigt J.-U. Recommendations for Cardiac Chamber Quantification by Echocardiography in Adults: An Update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. European Heart Journal – Cardiovascular Imaging. 2015; 16 (3): 233–271. https://doi.org/10.1093/ehjci/jev014

23. Saugel B., Fletcher N., Gan T. J., Grocott M. P.W., Myles P. S., Sessler D. I., Auzinger G., Chappell D., Gan T. J., Edwards M., Fletcher N., Forni L. G., Grocott M. P.W., Kunst G., Miller T. E., Morton-Bailey V., Myles P. S., Ostermann M., Raphael J., Saugel B., Sessler D. I., Shaw A. D., Zarbock A. PeriOperative Quality Initiative (POQI) international consensus statement on perioperative arterial pressure management. British Journal of Anaesthesia. 2024; 133 (2): 264–276. https://doi.org/10.1016/j.bja.2024.04.046

24. Maheshwari K., Shimada T., Yang D., Khanna S., Cywinski J. B., Irefin S. A., Ayad S., Turan A., Ruetzler K., Qiu Y., Saha P., Mascha E. J., Sessler D. I. Hypotension Prediction Index for Prevention of Hypotension during Moderate- to High-risk Noncardiac Surgery: A Pilot Randomized Trial. Anesthesiology. 2020; 133 (6): 1214–1222. https://doi.org/10.1097/ALN.0000000000003557

25. Kazakov A. S., Kolontarev K. B., Gorelova E. S., Grebenchikov O. A. Correction of the Elevated Blood Pressure in Patients Undergoing Robot-Assisted Radical Prostatectomy. General Reanimatology. 2022; 18 (4): 29–35. (In Russ.). https://doi.org/10.15360/1813-9779-2022-4-39-35

26. Lutfarakhmanov I. I., Mironov P. I., Galeev I. R., Pavlov V. N. Influence of Trendelenburg position and pneumoperitoneum on the cardiovascular system during robotic-assisted radical prostatectomy. Experimental and Clinical Urology, 2020; (4): 10–17. (In Russ.). https://doi.org/10.29188/2222-8543-2020-13-4-10-17

27. Kim T. L., Kim N., Shin H. J., Cho M. R., Park H. R., Kim S. Y. Intraoperative mean arterial pressure and acute kidney injury after robot-assisted laparoscopic prostatectomy: a retrospective study. Scientific Reports. 2023; 13 (1): 3318. https://doi.org/10.1038/s41598-023-30506-1

28. Wang J., Li Y., Su H., Zhao J., Tu F. Carotid artery corrected flow time and respiratory variations of peak blood flow velocity for prediction of hypotension after induction of general anesthesia in elderly patients. BMC geriatrics. 2022; 22 (1): 882. https://doi.org/10.1186/s12877-022-03619-x

29. Chen Y., Liu Z., Fang J., Xie Y., Zhang M., Yang J. Correlation of carotid corrected flow time and respirophasic variation in blood flow peak velocity with stroke volume variation in elderly patients under general anaesthesia. BMC anesthesiology. 2022; 22 (1): 246. https://doi.org/10.1186/s12871-022-01792-5

30. Feld S. I., Hippe D. S., Miljacic L., Polissar N. L., Newman S.-F., Nair B. G., Vavilala M. S. A Machine Learning Approach for Predicting Real-time Risk of Intraoperative Hypotension in Traumatic Brain Injury. Journal of Neurosurgical Anesthesiology. 2023; 35 (2): 215–223. https://doi.org/10.1097/ANA.0000000000000819

31. Park I., Park J. H., Koo Y. H., Koo C.-H., Koo B.-W., Kim J.-H., Oh A.-Y. Feasibility of a Machine Learning Classifier for Predicting Post-Induction Hypotension in Non-Cardiac Surgery. Yonsei Medical Journal. 2025; 66 (3): 160–171. https://doi.org/10.3349/ymj.2024.0020

32. Zhang G., Yuan J., Yu M., Wu T., Luo X., Chen F. A machine learning method for acute hypotensive episodes prediction using only non-invasive parameters. Computer Methods and Programs in Biomedicine. 2021; 200: 105845. https://doi.org/10.1016/j.cmpb.2020.105845

33. Lee J., Woo J., Kang A. R., Jeong Y.-S., Jung W., Lee M., Kim S. H. Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension. Sensors. 2020; 20 (16): 4575. https://doi.org/10.3390/s20164575