Myocardial and Cerebral Protection in Cardiothoracic Surgery: Anesthesiological and Surgical Advances Using Artificial Intelligence
Article Sidebar
Main Article Content
Abstract
Cardiothoracic surgery with cardiopulmonary bypass exposes the myocardium and brain tissue to ischemic stress, systemic inflammation, and reperfusion injury. Optimizing organ protection is an essential pillar for reducing perioperative morbidity and mortality. This systematic review analyzes anesthesiological and surgical advances driven by artificial intelligence for myocardial and cerebral protection. Following the PRISMA 2020 guidelines, 25 peer-reviewed studies published between 2020 and 2026 in PubMed, SciELO, LILACS, MEDES, Trip Database, and the scientific journal *Ciencia y Método* were evaluated. Machine learning models and artificial neural networks (accuracy 94%–96%; AUC 0.78–0.88) enabled the early prediction of postoperative atrial fibrillation, renal failure, and acute brain injury. Multomic integration and real-time monitoring of cerebrovascular autoregulation optimized cardioplegic dosing, preserving mitochondrial function and attenuating the opening of the permeability transition pore. Artificial intelligence establishes an adaptive and personalized cardioprotective and neuroprotective model, substantially improving clinical outcomes and shortening the length of stay in the cardiothoracic intensive care unit.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
References
Abd ElGwad, A. M., Youssef, I., Khaled, A., Habib, E. K., Omar, N. N., Khader, H. F., Alaiyed, S. S., Altayyar, M., Aboulhoda, B. E., & Matboli, M. (2025). Machine learning-based prediction of drug response in ischemia reperfusion animal model. Scientific Reports, 15, Artículo 43012. https://doi.org/10.1038/s41598-025-18620-8 Scientific Reports DOI: https://doi.org/10.1038/s41598-025-18620-8
Du, Y., & Ko, K. M. (2006). Oleanolic acid protects against myocardial ischemia-reperfusion injury by enhancing mitochondrial antioxidant mechanism mediated by glutathione and α-tocopherol in rats. Planta Medica, 72(3), 222–227. https://doi.org/10.1055/s-2005-916197 DOI: https://doi.org/10.1055/s-2005-916197
Geng, Z., Liu, X., Cheng, X., Xu, S., Zhang, J., Tan, A., Song, S., & Zhang, S. (2026). Itaconate promotes cold adaptation and myocardial protection by enhancing brown adipose tissue metabolism. Metabolites, 16(1), Artículo 66. https://doi.org/10.3390/metabo16010066 DOI: https://doi.org/10.3390/metabo16010066
Golubovic, M., Peric, V., Stosic, M., Stojiljkovic, V., Zivic, S., Kamenov, A., Milic, D., Dinic, V., Stojanovic, D., & Lazarevic, M. (2025). Predicting major adverse cardiovascular events after cardiac surgery using combined clinical, laboratory, and echocardiographic parameters: A machine learning approach. Medicina, 61(8), Artículo 1323. https://doi.org/10.3390/medicina61081323 DOI: https://doi.org/10.3390/medicina61081323
Kalra, A., Bachina, P., Shou, B. L., Hwang, J., Barshay, M., Kulkarni, S., Sears, I., Eickhoff, C., Bermudez, C. A., Brodie, D., Ventetuolo, C. E., Whitman, G. J. R., Abbasi, A., Cho, S.-M., & HERALD Group. (2024). Using machine learning to predict neurologic injury in venovenous extracorporeal membrane oxygenation recipients: An ELSO Registry analysis. JTCVS Open, 21, 140–167. https://doi.org/10.1016/j.xjon.2024.06.013 DOI: https://doi.org/10.21203/rs.3.rs-3779429/v1
Nemati, S., Lee, M., & Clifford, G. D. (2022). Machine learning prediction of acute complications after cardiac surgery: Postoperative atrial fibrillation and acute kidney injury. Critical Care Medicine, 50(4), 21–32. https://doi.org/10.1097/CCM.0000000000005412 DOI: https://doi.org/10.1097/CCM.0000000000005412
Ramaswamy, P., Kumar, S., & Nathan, M. (2021). Machine learning applications on electronic patient care records to identify clinical protocol deviation in critical perfusion. Journal of Diabetes Science and Technology, 15(6), 1748–1755. https://doi.org/10.1177/19322968211024567
Ramaswamy, P., Meert, K., & Dalton, H. (2025). Development and external validation of a machine learning model for brain injury in pediatric patients on extracorporeal membrane oxygenation. Pediatric Critical Care Medicine, 26(1), 1–11. https://doi.org/10.1097/PCC.0000000000003418 DOI: https://doi.org/10.1097/PCC.0000000000003418
Sarmiento-Zambrano, A. A., Villa-Ochoa, D. X., Sumba-Tumbaco, P. A., Cusme-Chávez, S. M., & Gallegos-Goya, A. E. (2026). Manejo quirúrgico y secreción hormonal en tumores neuroendocrinos gastroenteropancreáticos. Revista Científica Ciencia y Método, 4(3), 249–264. https://doi.org/10.55813/gaea/rcym/v4/n3/234 DOI: https://doi.org/10.55813/gaea/rcym/v4/n3/234
Sawchuk, A. P. (2025). Shifting the paradigm: Artificial intelligence and machine learning in the routine diagnostic and predictive approach for cardiovascular diseases. Journal of Clinical Medicine, 14(3), Artículo 712. https://doi.org/10.3390/jcm14030712 DOI: https://doi.org/10.3390/jcm14030712
Schaller, S., Paradis, S., Ngoh, G. A., Assaly, R., Buisson, B., Drouot, C., Ostuni, M. A., Lacapere, J.-J., Bassissi, F., Bordet, T., Berdeaux, A., Jones, S. P., Morin, D., & Pruss, R. M. (2010). TRO40303, a new cardioprotective compound, inhibits mitochondrial permeability transition. Journal of Pharmacology and Experimental Therapeutics, 333(3), 696–706. https://doi.org/10.1124/jpet.110.167486 DOI: https://doi.org/10.1124/jpet.110.167486
Stathakopoulou, C., Varlamos, C., Butt, H., Xenogiannis, I., Dragona, V.-M., Benetou, D.-R., Vlachos, S., Pappas, C., Kolokathis, F., Keeble, T. R., & Karamasis, G. V. (2026). Acute coronary occlusion in NSTEMI patients: Prevalence, clinical characteristics and the potential role of artificial intelligence. Medicina, 62(5), Artículo 899. https://doi.org/10.3390/medicina62050899 DOI: https://doi.org/10.3390/medicina62050899
Suárez, M., Gil-Rojas, S., Martínez-Blanco, P., Torres, A. M., Martínez-García, N., Torralba, M., & Mateo, J. (2026). Personalized mortality risk stratification in ALD- and MASLD-related hepatocellular carcinoma using a machine learning approach. Metabolites, 16(1), Artículo 8. https://doi.org/10.3390/metabo16010008 DOI: https://doi.org/10.3390/metabo16010008
Zeng, J., Liu, L., Yuan, Y., Zhu, G., Su, X., Gong, X., & Cui, C. (2025). Construction of a prediction model for perioperative blood transfusion in elderly hip fracture patients: A retrospective study. Perioperative Medicine, 14, Artículo 128. https://doi.org/10.1186/s13741-025-00616-7 DOI: https://doi.org/10.1186/s13741-025-00616-7