Machine Learning–Based Prediction of Hemodynamic Instability after Spinal Anesthesia
-
Atiyeh sadat Sajadi
,
Mehrdad Mesbah Kiaei
,
Raheleh Charmchi
,
Zeinab Barzegar
,
Kimia Khonakdar
,
Shahnam Sedigh Maroufi
,
Mahsa Atri Roozbahani
,
Parisa Moradimajd
Abstract
Background: Hypotension, heart rate changes, and postoperative nausea and vomiting (PONV) are common complications of spinal anesthesia in urologic surgeries, which may lead to hemodynamic instability, increased therapeutic interventions, and reduced patient satisfaction. Early identification of high-risk patients can play a crucial role in the prevention and management of these complications.
Methods: In this study, data from patients undergoing urologic surgeries under spinal anesthesia were collected, cleaned, and preprocessed. Various machine learning models, including logistic regression, support vector machine, decision tree, random forest, and multilayer perceptron (MLP) neural networks, were trained to predict hypotension, heart rate changes, and PONV. Feature selection was performed using the Boruta algorithm and correlation analysis.
Results: The MLP model achieved the strongest predictive performance for hypotension (AUC ≈ 0.86), heart rate changes (AUC ≈ 0.91), and PONV (AUC ≈ 0.87–0.90). The most important predictors were baseline blood pressure and heart rate, ASA status, age, surgical type and duration, and intraoperative medication use.
Conclusion: Machine learning models may be useful for identifying patients at high risk before complications develop after spinal anesthesia, offering a basis for building clinical decision support systems.
[1] Bembenick KN, Nguyen A, Jackson C, Shekoohi S, Kaye AJ, Kaye AD, et al. Neuraxial anesthesia for vaginal delivery. In: Pharmacology, physiology, and practice in obstetric anesthesia. Elsevier; 2025;163-73.
[2] Stewart J, Gasanova I, Joshi GP. Spinal anesthesia for ambulatory surgery: current controversies and concerns. Curr Opin Anesthesiol. 2020; 33(6):746-52.
[3] Ebert KM, Jayanthi VR, Alpert SA, Ching CB, DaJusta DG, Fuchs ME, et al. Benefits of spinal anesthesia for urologic surgery in the youngest of patients. J Pediatr Urol. 2019; 15(1):49.e1-49.e6.
[4] Šklebar I, Bujas T, Habek D. Spinal anaesthesia-induced hypotension in obstetrics: prevention and therapy. Acta Clin Croat. 2019; 58(Suppl 1):90-5.
[5] Hofhuizen C, Lemson J, Snoeck M, Scheffer G-J. Spinal anesthesia-induced hypotension is caused by a decrease in stroke volume in elderly patients. Local Reg Anesth. 2019; 12:19-26.
[6] Ferré F, Martin C, Bosch L, Kurrek M, Lairez O, Minville V. Control of spinal anesthesia-induced hypotension in adults. Local Reg Anesth. 2020; 13:39-46.
[7] Ju JW, Kwon J, Yoo S, Lee HJ. Retrospective analysis of the incidence and predictors of postoperative nausea and vomiting after orthopedic surgery under spinal anesthesia. Korean J Anesthesiol. 2023; 76(2):99-106.
[8] Shitemaw T, Jemal B, Mamo T, Akalu L. Incidence and associated factors for hypotension after spinal anesthesia during cesarean section at Gandhi Memorial Hospital Addis Ababa, Ethiopia. PLoS One. 2020; 15(8):e0236755.
[9] Kang AR, Lee J, Jung W, Lee M, Park SY, Woo J, et al. Development of a prediction model for hypotension after induction of anesthesia using machine learning. PLoS One. 2020; 15(4):e0231172.
[10] Chumpathong S, Chinachoti T, Visalyaputra S, Himmunngan T. Incidence and risk factors of hypotension during spinal anesthesia for cesarean section at Siriraj Hospital. J Med Assoc Thai. 2006; 89(10):1804.
[11] Trolice MP, Curchoe C, Quaas AM. Artificial intelligence-the future is now. J Assist Reprod Genet. 2021; 38(7):1607-12.
[12] Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017; 69:S36-S40.
[13] El Naqa I, Murphy MJ. What is machine learning? In: Machine learning in radiation oncology: theory and applications. Springer; 2015;3-11.
[14] Mackenzie A. The production of prediction: What does machine learning want? Eur J Cult Stud. 2015; 18(4-5):429-45.
[15] Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019; 380(14):1347-58.
[16] Ray S. 2019 international conference on machine learning, big data, cloud and parallel computing (COMITCon). IEEE; 2019;35-39.
[17] Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY, Van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019; 110:12-22.
[18] Bisong E. Building machine learning and deep learning models on Google cloud platform. Springer; 2019.
[19] Schonlau M, Zou RY. The random forest algorithm for statistical learning. Stata J. 2020; 20(1):3-29.
[20] Devika R, Avilala SV, Subramaniyaswamy V. Comparative study of classifier for chronic kidney disease prediction using naive bayes, KNN and random forest. In: 2019 3rd International conference on computing methodologies and communication (ICCMC). IEEE; 2019;679-84.
[21] Amato F, López A, Peña-Méndez EM, Vaňhara P, Hampl A, Havel J. Artificial neural networks in medical diagnosis. J Appl Biomed. 2013; 11(2):47-58.
[22] Shanmuganathan S. Artificial neural network modelling: An introduction. In: Artificial neural network modelling. Springer; 2016;1-14.
[23] Tully JL, Zhong W, Simpson S, Curran BP, Macias AA, Waterman RS, et al. Machine learning prediction models to reduce length of stay at ambulatory surgery centers through case resequencing. J Med Syst. 2023; 47(1):71.
[24] Bellini V, Valente M, Bertorelli G, Pifferi B, Craca M, Mordonini M, et al. Machine learning in perioperative medicine: a systematic review. J Anesth Analg Crit Care. 2022; 2(1):2.
[25] Bishara A, Chiu C, Whitlock EL, Douglas VC, Lee S, Butte AJ, et al. Postoperative delirium prediction using machine learning models and preoperative electronic health record data. BMC Anesthesiol. 2022; 22(1):8.
[26] Mehrad M, Nojavan M, Raissi S, Javadi M. A two-stage approach using artificial neural networks for diagnosis of heart diseases based on ECG data. J Arak Univ Med Sci. 2022; 25(2):230-43.
[27] Abedini A, Jabarpour E, Keshtkar A. Predicting the risk of osteoporosis using decision tree and neural network. J Health Biomed Inform. 2020; 7(3):304-17.
[28] Lee J, Woo J, Kang AR, Jeong Y-S, Jung W, Lee M, et al. Comparative analysis on machine learning and deep learning to predict post-induction hypotension. Sensors. 2020; 20(16):4575.
[2] Stewart J, Gasanova I, Joshi GP. Spinal anesthesia for ambulatory surgery: current controversies and concerns. Curr Opin Anesthesiol. 2020; 33(6):746-52.
[3] Ebert KM, Jayanthi VR, Alpert SA, Ching CB, DaJusta DG, Fuchs ME, et al. Benefits of spinal anesthesia for urologic surgery in the youngest of patients. J Pediatr Urol. 2019; 15(1):49.e1-49.e6.
[4] Šklebar I, Bujas T, Habek D. Spinal anaesthesia-induced hypotension in obstetrics: prevention and therapy. Acta Clin Croat. 2019; 58(Suppl 1):90-5.
[5] Hofhuizen C, Lemson J, Snoeck M, Scheffer G-J. Spinal anesthesia-induced hypotension is caused by a decrease in stroke volume in elderly patients. Local Reg Anesth. 2019; 12:19-26.
[6] Ferré F, Martin C, Bosch L, Kurrek M, Lairez O, Minville V. Control of spinal anesthesia-induced hypotension in adults. Local Reg Anesth. 2020; 13:39-46.
[7] Ju JW, Kwon J, Yoo S, Lee HJ. Retrospective analysis of the incidence and predictors of postoperative nausea and vomiting after orthopedic surgery under spinal anesthesia. Korean J Anesthesiol. 2023; 76(2):99-106.
[8] Shitemaw T, Jemal B, Mamo T, Akalu L. Incidence and associated factors for hypotension after spinal anesthesia during cesarean section at Gandhi Memorial Hospital Addis Ababa, Ethiopia. PLoS One. 2020; 15(8):e0236755.
[9] Kang AR, Lee J, Jung W, Lee M, Park SY, Woo J, et al. Development of a prediction model for hypotension after induction of anesthesia using machine learning. PLoS One. 2020; 15(4):e0231172.
[10] Chumpathong S, Chinachoti T, Visalyaputra S, Himmunngan T. Incidence and risk factors of hypotension during spinal anesthesia for cesarean section at Siriraj Hospital. J Med Assoc Thai. 2006; 89(10):1804.
[11] Trolice MP, Curchoe C, Quaas AM. Artificial intelligence-the future is now. J Assist Reprod Genet. 2021; 38(7):1607-12.
[12] Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017; 69:S36-S40.
[13] El Naqa I, Murphy MJ. What is machine learning? In: Machine learning in radiation oncology: theory and applications. Springer; 2015;3-11.
[14] Mackenzie A. The production of prediction: What does machine learning want? Eur J Cult Stud. 2015; 18(4-5):429-45.
[15] Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019; 380(14):1347-58.
[16] Ray S. 2019 international conference on machine learning, big data, cloud and parallel computing (COMITCon). IEEE; 2019;35-39.
[17] Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY, Van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019; 110:12-22.
[18] Bisong E. Building machine learning and deep learning models on Google cloud platform. Springer; 2019.
[19] Schonlau M, Zou RY. The random forest algorithm for statistical learning. Stata J. 2020; 20(1):3-29.
[20] Devika R, Avilala SV, Subramaniyaswamy V. Comparative study of classifier for chronic kidney disease prediction using naive bayes, KNN and random forest. In: 2019 3rd International conference on computing methodologies and communication (ICCMC). IEEE; 2019;679-84.
[21] Amato F, López A, Peña-Méndez EM, Vaňhara P, Hampl A, Havel J. Artificial neural networks in medical diagnosis. J Appl Biomed. 2013; 11(2):47-58.
[22] Shanmuganathan S. Artificial neural network modelling: An introduction. In: Artificial neural network modelling. Springer; 2016;1-14.
[23] Tully JL, Zhong W, Simpson S, Curran BP, Macias AA, Waterman RS, et al. Machine learning prediction models to reduce length of stay at ambulatory surgery centers through case resequencing. J Med Syst. 2023; 47(1):71.
[24] Bellini V, Valente M, Bertorelli G, Pifferi B, Craca M, Mordonini M, et al. Machine learning in perioperative medicine: a systematic review. J Anesth Analg Crit Care. 2022; 2(1):2.
[25] Bishara A, Chiu C, Whitlock EL, Douglas VC, Lee S, Butte AJ, et al. Postoperative delirium prediction using machine learning models and preoperative electronic health record data. BMC Anesthesiol. 2022; 22(1):8.
[26] Mehrad M, Nojavan M, Raissi S, Javadi M. A two-stage approach using artificial neural networks for diagnosis of heart diseases based on ECG data. J Arak Univ Med Sci. 2022; 25(2):230-43.
[27] Abedini A, Jabarpour E, Keshtkar A. Predicting the risk of osteoporosis using decision tree and neural network. J Health Biomed Inform. 2020; 7(3):304-17.
[28] Lee J, Woo J, Kang AR, Jeong Y-S, Jung W, Lee M, et al. Comparative analysis on machine learning and deep learning to predict post-induction hypotension. Sensors. 2020; 20(16):4575.
| Files | ||
| Issue | Article in Press |
|
| Section | Research Article(s) | |
| Keywords | ||
| anesthesia spinal hypotention Postoperative Nausea and Vomiting Heart Rate Urologic Surgery Machine Learning Artificial Intelligence | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
How to Cite
1.
Sajadi A sadat, Mesbah Kiaei M, Charmchi R, Barzegar Z, Khonakdar K, Sedigh Maroufi S, Atri Roozbahani M, Moradimajd P. Machine Learning–Based Prediction of Hemodynamic Instability after Spinal Anesthesia. Arch Anesth & Crit Care. 2026;.
