In fact, SA-AKI is usually detected only when there are signs of renal impairment; hence, little room remains for nurses to carry out prophylactic evaluation and intervention measures in advance. Therefore, this investigation established a readily understandable, nurse-centered model to predict early SA-AKI risks. External validation was then performed. Finally, based on the model’s predictions, a ladder-type nursing response mode was created accordingly. Then they used routinely recorded measurements taken during their patients’ first 24 hours in the ICU to try to predict which of these individuals developed new cases of SA-AKI sometime during their first 48 hours after entering the ICU. They developed models using the eICU Collaborative Research Database (eICU) and performed internal validation on this database alone. Then they externally validated their models using two other datasets: the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and a cohort from the First Affiliated Hospital of Hainan Medical University (FAH-HMU). There were four kinds of feature-selection approaches involved, taken together. Nine types of machine-learning algorithm were fine-tuned by means of Bayesian optimization and then compared. To explain what can be predicted by the last model chosen, the method adopted was Shapley additive explanations. Regarding the derivation of possible indicators from among candidates found while developing the model itself, a two-stage Delphi consultation followed about their clinical value, whether nurses could use them, and whether they fit easily with existing ways of working. It involved 15,767 patients from the eICU database, 12,842 subjects from MIMIC-IV, and 932 people from the FAH-HMU group. Here too, the best results were found for the Extreme Gradient Boosting algorithm: the area under the receiver operating characteristic curve was 0.798 (internal validation), 0.738 (MIMIC-IV), and 0.727 (institutional sample). There was also good calibration, and decision-curve analysis provided additional reasons to advocate using this method for early risk stratification. All fifteen experts answered both Delphi questionnaires, and the authority coefficient value was 0.87. Delphi consensus retained nine objective indicators and added capillary refill time as an additional nurse’s bedside observation item. On this basis, three kinds of pathways according to high-, moderate-, and low-risk levels were set forth, along with specific requirements for monitoring, reevaluation, and escalation, respectively. It produces a nursing response scheme consisting of multicohort-validated and explainable risk prediction combined with expert consensus on the levels of nursing activity required. Thus, a certain structure exists regarding what needs to happen in terms of early detection of SA-AKI risk, bedside monitoring, and risk-based nursing care in intensive-care practice.

Yang Ding, Minerva Bravo De Ala, Ying Zhang. Nursing-Oriented Risk Prediction and Response to Sepsis-Associated Acute Kidney Injury Using Interpretable Machine Learning and Delphi Consensus. International Journal of World Medicine (2026), Vol. 7, Issue 1: 66-81. https://doi.org/10.38007/IJWM.2026.070107.

[1] Hoste, E. A. J., Bagshaw, S. M., Bellomo, R., Cely, C. M., Colman, R., Cruz, D. N., Edipidis, K., Forni, L. G., Gomersall, C. D., Govil, D., Honoré, P. M., Joannes-Boyau, O., Joannidis, M., Korhonen, A.-M., Lavrentieva, A., Mehta, R. L., Palevsky, P., Roessler, E., Ronco, C., … Kellum, J. A. (2015). Epidemiology of acute kidney injury in critically ill patients: The multinational AKI-EPI study. Intensive Care Medicine, 41(8), 1411–1423. https://doi.org/10.1007/s00134-015-3934-7

[2] Susantitaphong, P., Cruz, D. N., Cerda, J., Abulfaraj, M., Alqahtani, F., Koulouridis, I., & Jaber, B. L. (2013). World incidence of AKI: A meta-analysis. Clinical Journal of the American Society of Nephrology, 8(9), 1482–1493. https://doi.org/10.2215/CJN.00710113

[3] Peerapornratana, S., Manrique-Caballero, C. L., Gómez, H., & Kellum, J. A. (2019). Acute kidney injury from sepsis: Current concepts, epidemiology, pathophysiology, prevention and treatment. Kidney International, 96(5), 1083–1099. https://doi.org/10.1016/j.kint.2019.05.026

[4] Poston, J. T., & Koyner, J. L. (2019). Sepsis associated acute kidney injury. BMJ, 364, k4891. https://doi.org/10.1136/bmj.k4891

[5] Kidney Disease: Improving Global Outcomes (KDIGO) Acute Kidney Injury Work Group. (2012). KDIGO clinical practice guideline for acute kidney injury. Kidney International Supplements, 2(1), 1–138. https://doi.org/10.1038/kisup.2012.1

[6] Vincent, J. L., Moreno, R., Takala, J., Willatts, S., De Mendonça, A., Bruining, H., Reinhart, C. K., Suter, P. M., & Thijs, L. G. (1996). The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure. Intensive Care Medicine, 22(7), 707–710. https://doi.org/10.1007/BF01709751

[7] Knaus, W. A., Draper, E. A., Wagner, D. P., & Zimmerman, J. E. (1985). APACHE II: A severity of disease classification system. Critical Care Medicine, 13(10), 818–829. https://doi.org/10.1097/00003246-198510000-00009

[8] Le Gall, J. R., Lemeshow, S., & Saulnier, F. (1993). A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. JAMA, 270(24), 2957–2963. https://doi.org/10.1001/jama.1993.03510240069035

[9] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM. https://doi.org/10.1145/2939672.2939785

[10] Tomašev, N., Glorot, X., Rae, J. W., Zielinski, M., Askham, H., Saraiva, A., Mottram, A., Meyer, C., Ravuri, S., Protsyuk, I., Connell, A., Ouyang, C., Karthikesalingam, A., Nielson, C., Kohlberg, E., Mohamed, S., Clancy, B., Fontana, V., McNamee, C., … Hassabis, D. (2019). A clinically applicable approach to continuous prediction of future acute kidney injury. Nature, 572(7767), 116–119. https://doi.org/10.1038/s41586-019-1390-1

[11] Flechet, M., Güiza, F., Schetz, M., Wouters, P., Vanhorebeek, I., Derese, I., Gunst, J., Spriet, I., Van den Berghe, G., & Meyfroidt, G. (2017). AKI predictor, an online prognostic calculator for acute kidney injury in adult critically ill patients: Development, validation, and comparison to serum neutrophil gelatinase-associated lipocalin. Intensive Care Medicine, 43(6), 764–773. https://doi.org/10.1007/s00134-017-4678-3

[12] Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, 30 (pp. 4765–4774).

[13] Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S. I. (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2(1), 56–67. https://doi.org/10.1038/s42256-019-0138-9

[14] Li, J., Zhu, M., & Yan, L. (2024). Predictive models of sepsis-associated acute kidney injury based on machine learning: A scoping review. Renal Failure, 46(2), 2380748. https://doi.org/10.1080/0886022X.2024.2380748

[15] Sendak, M. P., D’Arcy, J., Kashyap, S., Gao, M., Nichols, M., Corey, K., Ratliff, W., & Balu, S. (2020). A path for translation of machine learning products into healthcare delivery. EMJ Innovations, 4(1), 38–45. https://doi.org/10.33590/emjinnov/19-00172

[16] Pollard, T. J., Johnson, A. E. W., Raffa, J. D., Celi, L. A., Mark, R. G., & Badawi, O. (2018). The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Scientific Data, 5, 180178. https://doi.org/10.1038/sdata.2018.178

[17] Johnson, A. E. W., Bulgarelli, L., Shen, L., Gayles, A., Shammout, A., Horng, S., Pollard, T. J., Hao, S., Moody, B., Gow, B., Lehman, L.-W. H., Celi, L. A., & Mark, R. G. (2023). MIMIC-IV, a freely accessible electronic health record dataset. Scientific Data, 10, 1. https://doi.org/10.1038/s41597-022-01899-x

[18] Singer, M., Deutschman, C. S., Seymour, C. W., Shankar-Hari, M., Annane, D., Bauer, M., Bellomo, R., Bernard, G. R., Chiche, J.-D., Coopersmith, C. M., Hotchkiss, R. S., Levy, M. M., Marshall, J. C., Martin, G. S., Opal, S. M., Rubenfeld, G. D., van der Poll, T., Vincent, J.-L., & Angus, D. C. (2016). The Third International Consensus Definitions for Sepsis and Septic Shock. JAMA, 315(8), 801–810. https://doi.org/10.1001/jama.2016.0287

[19] Elixhauser, A., Steiner, C., Harris, D. R., & Coffey, R. M. (1998). Comorbidity measures for use with administrative data. Medical Care, 36(1), 8–27. https://doi.org/10.1097/00005650-199801000-00004

[20] van Buuren, S., & Groothuis-Oudshoorn, K. (2011). mice: Multivariate imputation by chained equations in R. Journal of Statistical Software, 45(3), 1–67. https://doi.org/10.18637/jss.v045.i03

[21] Stekhoven, D. J., & Bühlmann, P. (2012). MissForest: Non-parametric missing value imputation for mixed-type data. Bioinformatics, 28(1), 112–118. https://doi.org/10.1093/bioinformatics/btr597

[22] Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B, 58(1), 267–288.  https://doi.org/10.1111/j.2517-6161.1996.tb02080.x

[23] Kursa, M. B., & Rudnicki, W. R. (2010). Feature selection with the Boruta package. Journal of Statistical Software, 36(11), 1–13. https://doi.org/10.18637/jss.v036.i11

[24] Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002). Gene selection for cancer classification using support vector machines. Machine Learning, 46, 389–422. https://doi.org/10.1023/A:1012487302797

[25] Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems, 30 (pp. 3146–3154).

[26] Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. In Advances in Neural Information Processing Systems, 31 (pp. 6639–6649).

[27] Lou, Y., Caruana, R., Gehrke, J., & Hooker, G. (2013). Accurate intelligible models with pairwise interactions. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 623–631). https://doi.org/10.1145/2487575.2487579

[28] Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 2623–2631). https://doi.org/10.1145/3292500.3330701

[29] Vickers, A. J., & Elkin, E. B. (2006). Decision curve analysis: A novel method for evaluating prediction models. Medical Decision Making, 26(6), 565–574. https://doi.org/10.1177/0272989X06295361

[30] Dalkey, N., & Helmer, O. (1963). An experimental application of the Delphi method to the use of experts. Management Science, 9(3), 458–467. https://doi.org/10.1287/mnsc.9.3.458

[31] Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K. I. (2020). An overview of clinical decision support systems: Benefits, risks, and strategies for success. npj Digital Medicine, 3, 17. https://doi.org/10.1038/s41746-020-0221-y

[32] Hasson, F., Keeney, S., & McKenna, H. (2000). Research guidelines for the Delphi survey technique. Journal of Advanced Nursing, 32(4), 1008–1015. https://doi.org/10.1046/j.1365- 2648.2000.t01-1-01567.x

[33] Sendelbach, S., & Funk, M. (2013). Alarm fatigue: A patient safety concern. AACN Advanced Critical Care, 24(4), 378–386. https://doi.org/10.1097/NCI.0b013e3182a903f9

[34] Hernández, G., Ospina-Tascón, G. A., Damiani, L. P., Estenssoro, E., Dubin, A., Hurtado, J., Friedman, G., Castro, R., Alegría, L., Teboul, J. L., Cecconi, M., & Bakker, J. (2019). Effect of a resuscitation strategy targeting peripheral perfusion status vs serum lactate levels on 28-day mortality among patients with septic shock: The ANDROMEDA-SHOCK randomized clinical trial. JAMA, 321(7), 654–664. https://doi.org/10.1001/jama.2019.0071

[35] Topol, E. J. (2019). High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine, 25(1), 44–56. https://doi.org/10.1038/s41591-018-0300-7

[36] Mebrahtu, T. F., Skyrme, S., Randell, R., Keenan, A. M., Bloor, K., Yang, H., Andre, D., Ledward, A., King, H., & Thompson, C. (2021). Effects of computerised clinical decision support systems (CDSS) on nursing and allied health professional performance and patient outcomes: A systematic review of experimental and observational studies. BMJ Open, 11(12), e053886. https://doi.org/10.1136/bmjopen-2021-053886