Abstract
Purpose
Acute kidney injury (AKI) recovery prediction remains challenging. The purpose of the present study is to develop and validate prediction models for AKI recovery at hospital discharge in critically ill patients with ICU-acquired AKI stage 3 (AKI-3).
Methods
Models were developed and validated in a development cohort (n = 229) and a matched validation cohort (n = 244) from the multicenter EPaNIC database to create prediction models with the least absolute shrinkage and selection operator (Lasso) machine-learning algorithm. We evaluated the discrimination and calibration of the models and compared their performance with plasma neutrophil gelatinase-associated lipocalin (NGAL) measured on first AKI-3 day (NGAL_AKI3) and reference model that only based on age.
Results
Complete recovery and complete or partial recovery occurred in 33.20% and 51.23% of the validation cohort patients respectively. The prediction model for complete recovery based on age, need for renal replacement therapy (RRT), diagnostic group (cardiac/surgical/trauma/others), and sepsis on admission had an area under the receiver operating characteristics curve (AUROC) of 0.53. The prediction model for complete or partial recovery based on age, need for RRT, platelet count, urea, and white blood cell count had an AUROC of 0.61. NGAL_AKI3 showed AUROCs of 0.55 and 0.53 respectively. In cardiac patients, the models had higher AUROCs of 0.60 and 0.71 than NGAL_AKI3’s AUROCs of 0.52 and 0.54. The developed models demonstrated a better performance over the reference models (only based on age) for cardiac surgery patients, but not for patients with sepsis and for a general ICU population.
Conclusion
Models to predict AKI recovery upon hospital discharge in critically ill patients with AKI-3 showed poor performance in the general ICU population, similar to the biomarker NGAL. In cardiac surgery patients, discrimination was acceptable, and better than NGAL. These findings demonstrate the difficulty of predicting non-reversible AKI early.
Similar content being viewed by others
Availability of data and material
The data for the current study are not publicly available due to no prior agreement with the local ethical committee. Upon reasonable request, amendment can be requested to the corresponding author to share the necessary data.
Code availability
All analyses and modeling were done in python 3.7.4 with the open-source scikit-learn library 0.23.1.
References
Chertow GM, Burdick E, Honour M, et al. Acute kidney injury, mortality, length of stay, and costs in hospitalized patients. J Am Soc Nephrol. 2005;16:3365–70. https://doi.org/10.1681/ASN.2004090740.
Lysak N, Bihorac A, Hobson C. Mortality and cost of acute and chronic kidney disease after cardiac surgery. Curr Opin Anaesthesiol. 2017;30:113–7.
Silver SA, Chertow GM. The Economic Consequences of Acute Kidney Injury. Nephron. 2017;137:297–301.
Dasta JF, Kane-Gill S. Review of the literature on the costs associated with acute kidney injury. J Pharm Pract. 2019;32:292–302.
Alshaikh HN, Katz NM, Gani F, et al. Financial impact of acute kidney injury after cardiac operations in the United States. Ann Thorac Surg. 2018;105:469–75. https://doi.org/10.1016/j.athoracsur.2017.10.053.
Jiang L, Zhu Y, Luo X, et al. Epidemiology of acute kidney injury in intensive care units in Beijing: the multi-center BAKIT study. BMC Nephrol. 2019;20:468. https://doi.org/10.1186/s12882-019-1660-z.
Gammelager H, Christiansen CF, Johansen MB, et al. One-year mortality among Danish intensive care patients with acute kidney injury: a cohort study. Crit Care. 2012;16:R124. https://doi.org/10.1186/cc11420.
Fujii T, Uchino S, Takinami M, Bellomo R. Validation of the kidney disease improving global outcomes criteria for AKI and comparison of three criteria in hospitalized patients. Clin J Am Soc Nephrol. 2014;9:848–54. https://doi.org/10.2215/CJN.09530913.
Koeze J, Keus F, Dieperink W, et al. Incidence, timing and outcome of AKI in critically ill patients varies with the definition used and the addition of urine output criteria. BMC Nephrol. 2017;18:70. https://doi.org/10.1186/s12882-017-0487-8.
Ronco C, Bellomo R, Kellum JA. Acute kidney injury. Lancet. 2019;394:1949–64.
Khwaja A. KDIGO clinical practice guidelines for acute kidney injury. Nephron - Clin Pract. 2012;120:c179–84.
Gaudry S, Hajage D, Benichou N, et al. Delayed versus early initiation of renal replacement therapy for severe acute kidney injury: a systematic review and individual patient data meta-analysis of randomised clinical trials. Lancet (London, England). 2020;395:1506–15. https://doi.org/10.1016/S0140-6736(20)30531-6.
Srisawat N, Murugan R, Lee M, et al. Plasma neutrophil gelatinase-associated lipocalin predicts recovery from acute kidney injury following community-acquired pneumonia. Kidney Int. 2011;80:545–52. https://doi.org/10.1038/ki.2011.160.
Dewitte A, Joannès-Boyau O, Sidobre C, et al. Kinetic eGFR and novel AKI biomarkers to predict renal recovery. Clin J Am Soc Nephrol. 2015;10:1900–10. https://doi.org/10.2215/CJN.12651214.
Fiorentino M, Tohme FA, Murugan R, Kellum JA. Plasma Biomarkers in Predicting Renal Recovery from Acute Kidney Injury in Critically Ill Patients. Blood Purif. 2019;48:253–61. https://doi.org/10.1159/000500423.
Srisawat N, Wen X, Lee MJ, et al. Urinary biomarkers and renal recovery in critically ill patients with renal support. Clin J Am Soc Nephrol. 2011;6:1815–23. https://doi.org/10.2215/CJN.11261210.
Pike F, Murugan R, Keener C, et al. Biomarker enhanced risk prediction for adverse outcomes in critically Ill patients receiving RRT. Clin J Am Soc Nephrol. 2015;10:1332–9. https://doi.org/10.2215/CJN.09911014.
Flechet M, Güiza F, Schetz M, et al. AKIpredictor, 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 Med. 2017;43:764–73. https://doi.org/10.1007/s00134-017-4678-3.
Malhotra R, Kashani KB, Macedo E, et al. A risk prediction score for acute kidney injury in the intensive care unit. Nephrol Dial Transplant. 2017;32:814–22. https://doi.org/10.1093/ndt/gfx026.
Chiofolo C, Chbat N, Ghosh E, et al. Automated continuous acute kidney injury prediction and surveillance: a random forest model. Mayo Clin Proc. 2019;94:783–92. https://doi.org/10.1016/j.mayocp.2019.02.009.
Zimmerman LP, Reyfman PA, Smith ADR, et al. Early prediction of acute kidney injury following ICU admission using a multivariate panel of physiological measurements. BMC Med Inform Decis Mak. 2019;19:16. https://doi.org/10.1186/s12911-019-0733-z.
Tomašev N, Glorot X, Rae JW, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019;572:116–9. https://doi.org/10.1038/s41586-019-1390-1.
Li Y, Yao L, Mao C, et al (2019) Early Prediction of Acute Kidney Injury in Critical Care Setting Using Clinical Notes. In: Proceedings—2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. pp 683–686
Chen Y, Feng F, Li M, et al. Development of a risk stratification-based model for prediction of acute kidney injury in critically ill patients. Med (United States). 2019;98:e16867. https://doi.org/10.1097/MD.0000000000016867.
Parreco J, Soe-Lin H, Parks JJ, et al. Comparing machine learning algorithms for predicting acute kidney injury. Am Surg. 2019;85:725–9. https://doi.org/10.1177/000313481908500731.
Dharan KS, John GT, Antonisamy B, et al. Prediction of mortality in acute renal failure in the tropics. Ren Fail. 2005;27:289–96. https://doi.org/10.1081/JDI-200056612.
Chertow GM, Soroko SH, Paganini EP, et al. Mortality after acute renal failure: Models for prognostic stratification and risk adjustment. Kidney Int. 2006;70:1120–6. https://doi.org/10.1038/sj.ki.5001579.
Demirjian S, Chertow GM, Zhang JH, et al. Model to predict mortality in critically ill adults with acute kidney injury. Clin J Am Soc Nephrol. 2011;6:2114–20. https://doi.org/10.2215/CJN.02900311.
da Hora PR, Ramos JGR, Mendonça EJB, et al. A clinical score to predict mortality in septic acute kidney injury patients requiring continuous renal replacement therapy: the HELENICC score. BMC Anesthesiol. 2017;17:21. https://doi.org/10.1186/s12871-017-0312-8.
Kim Y, Park N, Kim J, et al. Development of a new mortality scoring system for acute kidney injury with continuous renal replacement therapy. Nephrology. 2019;24:1233–40. https://doi.org/10.1111/nep.13661.
Kang MW, Kim J, Kim DK, et al. Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy. Crit Care. 2020;24:42. https://doi.org/10.1186/s13054-020-2752-7.
Lin K, Hu Y, Kong G. Predicting in-hospital mortality of patients with acute kidney injury in the ICU using random forest model. Int J Med Inform. 2019;125:55–61. https://doi.org/10.1016/j.ijmedinf.2019.02.002.
Xu Z, Luo Y, Adekkanattu P, et al (2019) Stratified mortality prediction of patients with acute kidney injury in critical care. In: Studies in Health Technology and Informatics. IOS Press, pp 462–466
Itenov TS, Berthelsen RE, Jensen JU, et al. Predicting recovery from acute kidney injury in critically ill patients: development and validation of a prediction model. Crit Care Resusc. 2018;20:54–60.
Lee BJ, Hsu C, yuan, Parikh R, et al. Predicting Renal Recovery After Dialysis-Requiring Acute Kidney Injury. Kidney Int Reports. 2019;4:571–81. https://doi.org/10.1016/j.ekir.2019.01.015.
Thiele RH, Isbell JM, Rosner MH. AKI associated with cardiac surgery. Clin J Am Soc Nephrol. 2015;10:500–14.
Peerapornratana S, Manrique-Caballero CL, Gómez H, Kellum JA. Acute kidney injury from sepsis: current concepts, epidemiology, pathophysiology, prevention and treatment. Kidney Int. 2019;96:1083–99.
Kellum JA. How can we define recovery after acute kidney injury? Considerations from epidemiology and clinical trial design. Nephron - Clin Pract. 2014;127:81–8. https://doi.org/10.1159/000363681.
Casaer MP, Mesotten D, Hermans G, et al. Early versus late parenteral nutrition in Critically Ill adults. N Engl J Med. 2011;365:506–17. https://doi.org/10.1056/NEJMoa1102662.
Witten IH, Frank E, Hall MA. The explorer. In: Witten IH, Frank E, Hall MA, editors. Data mining: practical machine learning tools and techniques. 3rd ed. Boston: Morgan Kaufmann; 2011. p. 407–94.
Strobl C, Boulesteix AL, Zeileis A, Hothorn T. Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics. 2007;8:25. https://doi.org/10.1186/1471-2105-8-25.
Bone RC, Balk RA, Cerra FB, et al (1992) Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. In: Chest. pp 1644–1655
Steyerberg EW. Evaluation of performance. In: Clinical prediction models: a practical approach to development, validation, and updating. New York: Springer; 2009. p. 255–80.
Kellum JA, Sileanu FE, Bihorac A, et al. Recovery after acute kidney injury. Am J Respir Crit Care Med. 2017;195:784–91. https://doi.org/10.1164/rccm.201604-0799OC.
Fan H, Zhao Y, Zhu JH, et al. Thrombocytopenia as a predictor of severe acute kidney injury in patients with heat stroke. Ren Fail. 2015;37:877–81. https://doi.org/10.3109/0886022X.2015.1022851.
Kertai MD, Zhou S, Karhausen JA, et al. Platelet counts, acute kidney injury, and mortality after coronary artery bypass grafting surgery. Anesthesiology. 2016;124:339–52. https://doi.org/10.1097/ALN.0000000000000959.
Koo CH, Eun Jung D, Park YS, et al. Neutrophil, Lymphocyte, and Platelet Counts and Acute Kidney Injury After Cardiovascular Surgery. J Cardiothorac Vasc Anesth. 2018;32:212–22. https://doi.org/10.1053/j.jvca.2017.08.033.
Griffin BR, Jovanovich A, You Z, et al. Effects of baseline thrombocytopenia and platelet decrease following renal replacement therapy initiation in patients with severe acute kidney injury. Crit Care Med. 2019;47:e325–31. https://doi.org/10.1097/CCM.0000000000003598.
Wu M, Luan YY, Lu JF, et al. Platelet count as a new biomarker for acute kidney injury induced by hemorrhagic shock. Platelets. 2020;31:94–102. https://doi.org/10.1080/09537104.2019.1581921.
Li DH, Wald R, Blum D, et al. Predicting mortality among critically ill patients with acute kidney injury treated with renal replacement therapy: Development and validation of new prediction models. J Crit Care. 2020;56:113–9. https://doi.org/10.1016/j.jcrc.2019.12.015.
Han SS, Ahn SY, Ryu J, et al. U-shape relationship of white blood cells with acute kidney injury and mortality in critically Ill patients. Tohoku J Exp Med. 2014;232:177–85. https://doi.org/10.1620/tjem.232.177.
Uchino S, Kellum JA, Bellomo R, et al. Acute renal failure in critically ill patients: a multinational, multicenter study. J Am Med Assoc. 2005;294:813–8. https://doi.org/10.1001/jama.294.7.813.
Bagshaw SM. Epidemiology of renal recovery after acute renal failure. Curr Opin Crit Care. 2006;12:544–50.
Bagshaw SM, Laupland KB, Doig CJ, et al. Prognosis for long-term survival and renal recovery in critically ill patients with severe acute renal failure: a population-based study. Crit Care. 2005;9:R700. https://doi.org/10.1186/cc3879.
Bagshaw SM, Bennett M, Haase M, et al. Plasma and urine neutrophil gelatinase-associated lipocalin in septic versus non-septic acute kidney injury in critical illness. Intensive Care Med. 2010;36:452–61. https://doi.org/10.1007/s00134-009-1724-9.
Czempik P, Cieśla D, Knapik P, Krzych Ł. Mortality of patients with acute kidney injury requiring renal replacement therapy. Adv Clin Exp Med. 2018;27:327–33. https://doi.org/10.17219/acem/65066.
Ohnuma T, Uchino S. Prediction models and their external validation studies for mortality of patients with acute kidney injury: A systematic review. PLoS ONE. 2017;12: e0169341. https://doi.org/10.1371/journal.pone.0169341.
Beaubien-Souligny W, Wald R. Predicting outcomes in acute kidney injury survivors: searching for the crystal ball. Kidney Int Reports. 2019;4:520–1.
Moons KGM, Altman DG, Reitsma JB, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015;162:W1–73. https://doi.org/10.7326/M14-0698.
Acknowledgements
The authors would like to thank the members of the EPaNIC research group for helpfully providing the EPaNIC database, which was used to develop the AKI recovery prediction models.
Funding
C-YH receives a grant from the Taiwan-KU Leuven scholarship. JG holds a postdoctoral research fellowship supported by the University Hospitals Leuven. GDV receives a clinical fellowship grant of the Flanders Research Foundation (1701719 N). GM received a grant of the Flanders Research Foundation as senior clinical investigator. This work was supported by the Methusalem program of the Flemish government (through the University of Leuven to GVdB, METH/08/07 and to GVdB and IV, METH14/06).
Author information
Authors and Affiliations
Contributions
Conceptualization: FG and GM. Data curation: C-YH, FG, PW, JG, MC, IV, ID, and GVdB. Formal analysis: C-YH. Funding acquisition: IV and GVdB. Investigation: C-YH, FG, and GM. Methodology: C-YH, FG, and GM. Project administration: FG and GM. Resources: FG, PW, JG, MC, IV, ID, GVdB, and GM. Software: C-YH. Supervision: FG and GM. Validation: C-YH, FG, and GM. Visualization: C-YH, FG, and GM. Writing—original draft preparation: C-YH, FG, GDV, and GM. writing—review and editing: C-YH, FG, PW, JG, MC, IV, GDV, GVdB, and GM.
Corresponding author
Ethics declarations
Conflict of interest
All the authors declared no competing interests that are relevant to the content of this article.
Ethical approval
EPaNIC data collection has ethical committee (EC) approval from the institutional review board of the participating centers and by the Belgian authorities.
Informed consent
Written informed consent was obtained from all patients participating in the EPaNIC study or their designated representatives.
Consent to participate
Informed consent was obtained from all individual participants included in the EPaNIC study or their designated representatives.
Consent for publication
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Huang, CY., Güiza, F., De Vlieger, G. et al. Development and validation of clinical prediction models for acute kidney injury recovery at hospital discharge in critically ill adults. J Clin Monit Comput 37, 113–125 (2023). https://doi.org/10.1007/s10877-022-00865-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10877-022-00865-7