Research Progress on Prognostic Prediction Models for Veno-Arterial Extracorporeal Membrane Oxygenation (VA-ECMO)
DOI:
https://doi.org/10.54097/14f6d853Keywords:
Veno-arterial Extracorporeal Membrane Oxygenation, Prognostic Prediction, Machine Learning, Risk Stratification, Prediction ModelAbstract
Veno-arterial extracorporeal membrane oxygenation (VA-ECMO), a critical life-support technology for refractory cardiogenic shock and cardiac arrest, has seen a significant increase in utilization over the past decade. However, its high medical costs, complex operational requirements, and substantial mortality rate necessitate precise prognostic tools for clinical decision-making. This article systematically reviews the recent advancements in prognostic prediction models for VA-ECMO, focusing on the paradigm shift from traditional scoring systems to machine learning and deep learning models. Traditional prediction models, such as the SAVE score and SOFA score, are developed based on logistic regression and Cox regression. While offering strong clinical interpretability, they possess inherent limitations. Machine learning models (e.g., logistic regression, random forest, deep neural networks) demonstrate superior predictive performance by processing complex non-linear relationships. Multicenter validation studies underscore the importance of model generalizability. Lactate, age, and albumin have been identified as key predictive factors across multiple studies. Future directions should concentrate on prospective multicenter research, the development of dynamic prediction models, and the implementation of standardized reporting guidelines to facilitate the clinical translation and application of VA-ECMO prognostic prediction models.
Downloads
References
[1] Yehya, N., Fazelinia, H., Lawrence, G. G., Spruce, L. A., Mai, M. V., Worthen, G. S., & Christie, J. D. (2021). Plasma Nucleosomes Are Associated With Mortality in Pediatric Acute Respiratory Distress Syndrome. Critical Care Medicine, 49(7), 1149–1158.
[2] Bartlett, R. H., Carlet, J., Cook, D., Gattinoni, L., Harvey, M., Jacobi, J., Parker, M. M., Sprung, C. L., Suter, P., Thompson, A., & Vincent, J.-L. (2023). The Impact of the Society of Critical Care Medicine's Flagship Journal: Critical Care Medicine: Reflections of Critical Care Pioneers. *Critical Care Medicine*, *51*(2), 164–181.
[3] Rabinowitz, E. J., Ouyang, A., Armstrong, D. R., Wallendorf, M., & Said, A. S. (2022). Poor Reliability of Common Measures of Anticoagulation in Pediatric Extracorporeal Membrane Oxygenation. *ASAIO Journal*, *68*(6), 850–858.
[4] Wang, S., Tao, S., Zhu, Y., Gu, Q., Ni, P., Zhang, W., Wu, C., Zhao, R., Hu, W., & Diao, M. (2025). AI-powered model for predicting mortality risk in VA-ECMO patients: a multicenter cohort study. *Scientific Reports*, *15*(1).
[5] Gao, H., & Lu, J. (2022). [Research progress on prognostic prediction models for patients undergoing extracorporeal membrane oxygenation]. [Original Chinese reference - Note: Needs verification]
[6] Huang, W., Guo, W., & Wang, L. (2022). [Research Progress of Survival Predictive Score in Veno-Arterial Extracorporeal Membrane Oxygenation]. [Original Chinese reference - Note: Needs verification]
[7] Pladet, L. C. A., Barten, J. M. M., Vernooij, L. M., Kraemer, C. V. E., Bunge, J. J. H., Scholten, E., Montenij, L. J., Kuijpers, M., Donker, D. W., Cremer, O. L., & Meuwese, C. L. (2023). Prognostic models for mortality risk in patients requiring ECMO. *Intensive Care Medicine*, *49*(2), 131–141.
[8] Qian, S., Li, P., Hou, X., & Dong, N. (2025). Development and internal validation of the PROFIT and POSITIVE prognostic nomograms for patients undergoing VA-ECMO therapy. Scientific Reports, 15(1).
[9] Hashem, A., Mohamed, M. S., Alabdullah, K., Elkhapery, A., Khalouf, A., Saadi, S., Nayfeh, T., Rai, D., Alali, O., Kinzelman-Vesely, E. A., Parikh, V., & Feitell, S. C. (2023). Predictors of Mortality in Patients With Refractory Cardiac Arrest Supported With VA-ECMO: A Systematic Review and a Meta-Analysis. Current Problems in Cardiology, 48(6), 101658.
[10] Stephens, A. F., Šeman, M., Diehl, A., Pilcher, D., Barbaro, R. P., Brodie, D., Pellegrino, V., Kaye, D. M., Gregory, S. D., & Hodgson, C. (2023). ECMO PAL: using deep neural networks for survival prediction in venoarterial extracorporeal membrane oxygenation. Intensive Care Medicine, 49(9), 1090–1099.
[11] Braun, J., Sahli, S. D., Spahn, D. R., Röder, D., Neb, H., Lotz, G., Aser, R., Wilhelm, M. J., & Kaserer, A. (2023). Predicting Survival for Veno-Arterial ECMO Using Conditional Inference Trees—A Multicenter Study. Journal of Clinical Medicine, 12(19), 6243.
[12] Kresoja, K. P., Zweymer, U., Akin, I., Rassaf, T., Mahabadi, A. A., Lehmann, R., Eitel, I., Graf, T., Schuster, A., Skurk, C., Lurz, P., Schneider, S., Desch, S., Freund, A., & Thiele, H. (2024). Identifying prognostic factors in patients with cardiogenic shock undergoing VA-ECMO treatment: insights from ECLS-SHOCK using machine learning. European Heart Journal, 45(Supplement_1).
[13] Amin, F., Lombardi, J., Alhussein, M., Posada, J. D., Suszko, A., Koo, M., Fan, E., Ross, H., Rao, V., Alba, A. C., & Billia, F. (2021). Predicting Survival After VA-ECMO for Refractory Cardiogenic Shock: Validating the SAVE Score. CJC Open, 3(1), 71–81.
[14] Kosmopoulos, M., Bartos, J. A., & Yannopoulos, D. (2019). Abstract 210: Effects of Indication for Veno-Arterial Extracorporeal Membrane Oxygenation on Predictive Value of Save Score. Circulation, 140(Suppl_2).
[15] Ayyad, A., Fadel, R., Kollman, P., Parson, A., Almajed, M. R., Shadid, A. M., Jabri, A., Basir, M. B., & Alqarqaz, M. (2025). Surviving venoarterial extracorporeal membrane oxygenation (VA-ECMO): The roles of severity scores and post-operative lactate clearance. Cardiovascular Revascularization Medicine, 76, 73–76.
[16] Fisser, C., Rincon-Gutierrez, L. A., Enger, T. B., Taccone, F. S., Broman, L. M., Belliato, M., Nobile, L., Pappalardo, F., & Malfertheiner, M. V. (2021). Validation of Prognostic Scores in Extracorporeal Life Support: A Multi-Centric Retrospective Study. Membranes, 11(2), 84.
[17] Sudarsanan, S., Sivadasan, P., Chandra, P., Omar, A. S., Atuel, K. L. G., Lone, H. U., Ragab, H. O., Ehsan, I., Carr, C. S., Pattath, A. R., Alkhulaifi, A. M., Shouman, Y., & Almulla, A. (2024). Comparison of Four Intensive Care Scores in Predicting Outcomes After Venoarterial Extracorporeal Membrane Oxygenation: A Single-center Retrospective Study. In Journal of Cardiothoracic and Vascular Anesthesia, 2024.
[18] Shou, B. L., Leng, A., Bachina, P., Kalra, A., Zhou, A. L., Whitman, G., & Cho, S.-M. (2025). A Novel, Interpretable Machine Learning Model to Predict Neurological Outcomes Following Venoarterial Extracorporeal Membrane Oxygenation. Neurocritical Care, 43(2), 403–413.
[19] 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., Kim, B. S., Whitman, G. J. R., Abbasi, A., & Cho, S.-M. (2024). Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life Support Organization Registry.
[20] Lee, Y. C., Cha, J., Shim, I., Park, W.-Y., Kang, S. W., Lim, D. H., & Won, H.-H. (2023). Multimodal deep learning of fundus abnormalities and traditional risk factors for cardiovascular risk prediction. Npj Digital Medicine, 6(1).
[21] Kim, J. S., Kwon, D., Kim, K., Lee, S. H., Lee, S.-B., Kim, K., Kim, D., Lee, M. W., Park, N., Choi, J. H., Jang, E. S., Cho, I. R., Paik, W. H., Lee, J. K., Ryu, J. K., & Kim, Y.-T. (2024). Machine learning-based prediction of pulmonary embolism to reduce unnecessary computed tomography scans in gastrointestinal cancer patients: a retrospective multicenter study. Scientific Reports, 14(1).
[22] Teng, X., Han, K., Jin, W., Ma, L., Wei, L., Min, D., Chen, L., & Du, Y. (2024). Development and validation of an early diagnosis model for bone metastasis in non-small cell lung cancer based on serological characteristics of the bone metastasis mechanism. eClinicalMedicine, 72, 102617.
[23] Antony, B., Blau, H., Casiraghi, E., Loomba, J. J., Callahan, T. J., Laraway, B. J., Wilkins, K. J., Antonescu, C. C., Valentini, G., Williams, A. E., Robinson, P. N., Reese, J. T., Murali, T. M., & Chute, C. (2023). Predictive models of long COVID. eBioMedicine, 96, 104777.
[24] Gurcan, F., & Soylu, A. (2024). Learning from Imbalanced Data: Integration of Advanced Resampling Techniques and Machine Learning Models for Enhanced Cancer Diagnosis and Prognosis. Cancers, 16(19), 3417.
[25] Xiong, P., Chen, J., Zhang, Y., Shu, L., Shen, Y., Gu, Y., Liu, Y., Guan, D., Zheng, B., & Yang, Y. (2024). Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches. iScience, 27(2), 108928.
[26] Wang, M., Feng, Z., Zhou, L., Zhang, L., Hao, X., & Zhai, J. (2021). Computed-Tomography-Based Radiomics Model for Predicting the Malignant Potential of Gastrointestinal Stromal Tumors Preoperatively: A Multi-Classifier and Multicenter Study. Frontiers in Oncology, 11.
[27] Hyndman, M. E., Paproski, R. J., Kinnaird, A., Fairey, A., Marks, L., Pavlovich, C. P., Fletcher, S. A., Zachoval, R., Adamcova, V., Stejskal, J., Aprikian, A., Wallis, C. J. D., Pink, D., Vasquez, C., Beatty, P. H., & Lewis, J. D. (2024). Development of an effective predictive screening tool for prostate cancer using the ClarityDX machine learning platform. Npj Digital Medicine, 7(1).
[28] Yan, P., Duan, S.-B., Luo, X.-Q., Zhang, N.-Y., & Deng, Y.-H. (2022). Development and validation of a deep neural network–based model to predict acute kidney injury following intravenous administration of iodinated contrast media in hospitalized patients with chronic kidney disease: a multicohort analysis. Nephrology Dialysis Transplantation, 38(2), 352–361.
[29] Hsu, W., Ko, A., Weng, C., Chang, C., Jan, Y., Lin, J., Chien, H., Lin, W., Sun, F., Wu, K., & Lee, J. (2023). Explainable machine learning model for predicting skeletal muscle loss during surgery and adjuvant chemotherapy in ovarian cancer. Journal of Cachexia, Sarcopenia and Muscle, 14(5), 2044–2053.
[30] Zhu, J., Guo, D., Liu, L., & Zhong, J. (2023). Serum Galectin-3 Predicts Mortality in Venoarterial Extracorporeal Membrane Oxygenation Patients. Cardiology Research and Practice, 2023, 1–8. https://doi.org/10.1155/2023/3917156.
[31] Goncalves Teixeira, P. M., Passos Silva, M., Mbala, D., Ana Canelas, M., Varela, M., Raquel Barbosa, A., Guerreiro, C., Mosalina, A., Dias, T., Queiros, P., Fontes-Carvalho, R., Ponte, M., Dias, A., Caeiro, D., & Braga, P. (2019). P5739Venoarterial Extracorporeal Membrane Oxygenation in Cardiogenic Shock: exploring prognostic variables and risk prediction tools. European Heart Journal, 40(Supplement_1).
[32] Cheewatanakornkul, S., Duangpakdee, P., Khwannimit, B., Bhurayanontachai, R., Geater, S. L., & Geater, A. F. (2023). Validation of the prognostic scoring system for in-hospital mortality prediction in cardiogenic shock patients requiring veno-arterial extracorporeal membrane oxygenation. Asian Cardiovascular and Thoracic Annals, 31(4), 321–331.
[33] Laimoud, M., Alanazi, M., Maghirang, M., Machado, P., Hakami, E., Lo, G., & Al-Halees, Z. (2025). Predictors of mortality in patients with cardiogenic shock and veno-arterial extracorporeal membrane oxygenation.
[34] Dettling, A., Kellner, C., Sundermeyer, J., Beer, B. N., Besch, L., Bertoldi, L. F., Blankenberg, S., Dauw, J., Eckner, D., Eitel, I., Graf, T., Horn, P., Jozwiak‐Nozdrzykowska, J., Kirchhof, P., Kluge, S., Krais, J., von Lewinski, D., Linke, A., Luedike, P., ... Mangner, N. (2025). Incidence and predictors of weaning failure from veno‐arterial extracorporeal membrane oxygenation therapy in patients with cardiogenic shock. European Journal of Heart Failure, 27(5), 832–841.
[35] Jin, Y., Gao, P., Zhang, P., Bai, L., Li, Y., Wang, W., Feng, Z., Wang, X., & Liu, J. (2022). Mortality prediction in pediatric postcardiotomy veno-arterial extracorporeal membrane oxygenation: A comparison of scoring systems. Frontiers in Medicine, 9.
[36] Presume, J., Gomes, D. A., Albuquerque, F., Lopes, P., Bello, A. R., Brizido, C., Strong, C., Ferreira, J., Mendes, M., Neves, J. P., & Tralhao, A. (2023). Validation of SAVE score and the value of serum lactate in patients admitted for cardiogenic shock treated with VA-ECMO. European Heart Journal, 44(Supplement 2).
[37] Laimoud, M., Machado, P., Lo, M. G., Maghirang, M. J., Hakami, E., & Qureshi, R. (2024). The Absolute Lactate Levels Versus Clearance for Prognostication of Post-Cardiotomy Patients on Veno-Arterial ECMO. ESC Heart Failure, 11(6), 3511–3522.
[38] Wengenmayer, T., Staudacher, D. L., Philipp, A., Tigges, E., Dettling, A., Busse, H., Kriege, M., Padberg, J.-S., Voigt, I., Scherer, C., Graf, T., Scharpf, D., Noack, P., Britsch, S., Michels, G., Lunz, D., Müller, T., Springer, A., ... Lindner, S. (2025). Clinical use and predictors of outcome in venoarterial extracorporeal membrane (VA ECMO): insights from VERGE (VA ECMO Registry of Germany). Clinical Research in Cardiology, 114(10), 1377–1387.
[39] Shah, N., & Said, A. S. (2021). Extracorporeal Support Prognostication—Time to Move the Goal Posts? Membranes, 11(7), 537.
[40] Berger, R., Nemeth, A., Sandoval Boburg, R., Vöhringer, L., Lausberg, H. F., Acharya, M., Schlensak, C., & Popov, A.-F. (2022). Long-Term Follow-Up of Survivors of Extracorporeal Life Support Therapy for Cardiogenic Shock: Are They Really Survivors? Medicina, 58(3), 427.
[41] Acharya, D., Manandhar-Shrestha, N., Leacche, M., Rajapreyar, I., William, P., Kazui, T., Hooker, R., Tonna, J., Jovinge, S., & Loyaga-Rendon, R. (2023). Extracorporeal membrane oxygenation as a bridge to advanced heart failure therapies. The Journal of Heart and Lung Transplantation, 42(8), 1059–1071.
[42] Lakatos, B. K., Ladányi, Z., Fábián, A., Ehrenberger, R., Turschl, T., Bagyura, Z., Evrard, B., Vandroux, D., Goudelin, M., Lindner, S., Britsch, S., Dürschmied, D., Zima, E., Csikós, G. R., Túróczi, Z., Soltész, Á., Németh, E., Kovács, A., Édes, F. I., & Merkely, B. (2024). Non-invasive assessment of left ventricular contractility by myocardial work index in veno-arterial membrane oxygenation patients: rationale and design of the MIX-ECMO multicentre observational study. Frontiers in Cardiovascular Medicine, 11.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

