©Author(s) (or their employer(s)) 2026. No commercial re-use. See Permissions. Published by Baishideng Publishing Group Inc.
World J Crit Care Med. Mar 9, 2026; 15(1): 114318
Published online Mar 9, 2026. doi: 10.5492/wjccm.v15.i1.114318
Published online Mar 9, 2026. doi: 10.5492/wjccm.v15.i1.114318
Predicting acute kidney injury in septic shock patients using inflammatory indices in the intensive care unit
Jackson Rajendran, Maria Jose Lorenzo-Capps, Eunseuk Lee, Veera Jayasree Latha Bommu, George Altarcha, Bryan Gregory, Department of Internal Medicine, Rutgers Health - RWJBH, Toms River, NJ 08701, United States
Song-Peng Ang, Department of Cardiology, University of Arizona, Tucson, AZ 85719, United States
Carlos Valladares, Department of Internal Medicine, Rutgers Health - RWJBH Community Medical Center, Rutgers Health - RWJBH, Toms River, NJ 08753, United States
Svitlana Pominov, Pulmonary Critical Care Medicine, Rutgers Health - RWJBH, Toms River, NJ 08755, United States
Jia Ee Chia, Department of Internal Medicine, Institution Texas Tech University Health Science Center, El Paso, TX 79912, United States
Jose Iglesias, Department of Internal Medicine, Hackensack Meridian School of Medicine, Nutley, NJ 07110, United States
Author contributions: Rajendran J, Ang SP, and Iglesias J analyzed data and wrote the manuscript; Rajendran J and Iglesias J designed the study; Lorenzo-Capps MJ, Valladares C, Bommu VL, Pominov S, and Gregory B researched references and wrote the manuscript; Lee E and Altarcha G did the graphic representation; Chia JE worked on the references; all of the authors read and approved the final version of the manuscript to be published.
Institutional review board statement: This study used de-identified data from the publicly available eICU Collaborative Research Database. The use of this database is certified as meeting safe harbor standards under HIPAA, and therefore is exempt from institutional review board approval.
Informed consent statement: Informed consent was not required as the dataset comprises fully de-identified patient information, and no individual can be identified directly or through identifiers linked to the subjects.
Conflict-of-interest statement: All authors declare no conflict of interest in publishing the manuscript.
STROBE statement: The authors have read the STROBE Statement – checklist of items, and the manuscript was prepared and revised according to the STROBE Statement – checklist of items.
Data sharing statement: The data underlying this article are available from the eICU Collaborative Research Database, a publicly accessible repository. Access to the data requires registration, training in research with human subjects, and a data use agreement governing use and collaborative research.
Corresponding author: Jose Iglesias, FASN, Department of Internal Medicine, Hackensack Meridian School of Medicine, 123 Metro Blvd, Nutley, NJ 07110, United States.
Received: September 16, 2025
Revised: November 17, 2025
Accepted: January 28, 2026
Published online: March 9, 2026
Processing time: 165 Days and 11.8 Hours
Revised: November 17, 2025
Accepted: January 28, 2026
Published online: March 9, 2026
Processing time: 165 Days and 11.8 Hours
Core Tip
Core Tip: Composite inflammatory markers are elevated in patients who develop acute kidney injury. However, due to heterogeneity of septic shock, multicollinearity and nonlinear relationships, these markers alone offer limited incremental predictive value. Neural network models further expounded the contribution of both clinical factors and the combined inflammatory/metabolic dimension to accurate acute kidney injury prediction, capturing complex interactions and non-linear relationships not evident in traditional regression models. Implementation of supervised and unsupervised machine learning together may offer further insights.