Background <p>In critically ill elderly patients, malnutrition is a common comorbidity. The Geriatric Nutritional Risk Index (GNRI) is a straightforward tool for evaluating the nutritional status of elderly individuals. The association between GNRI score and unfavorable health outcomes has been established. However, no studies have yet elucidated the relationship between GNRI score and sepsis-related acute kidney injury (S-AKI).</p> Methods <p>We sourced patient data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. All patients were divided into four groups based on their GNRI score using quartile analysis. The main objective of this study was to investigate the 28-day mortality rate. Secondary study outcomes were the incidence of severe AKI, length of stay in the intensive care unit, and days in the hospital. To evaluate the association between GNRI score and study outcomes, we used a Cox proportional hazards regression model and restricted cubic splines. Kaplan–Meier curves were used to compare the outcomes in each group.</p> Results <p>A total of 4515 elderly patients with S-AKI were included in this study. Patients were categorized into four groups according to GNRI quartile: Q1 (&lt; 78.92), Q2 (78.92–84.88), Q3 (84.88–90.84), and Q4 (&gt; 90.84). Overall 28-day mortality was 29.5%. Patients with a low GNRI were predominantly women, and had a low body mass index. After controlling for confounding factors, GNRI score emerged as an independent predictor of 28-day mortality among elderly patients with S-AKI (Q4 vs. Q1: hazard ratio 0.74, 95% confidence interval 0.63–0.87; <i>p</i> &lt; 0.001). Restricted cubic spline analysis revealed a linear relationship between GNRI and 28-day mortality (p for non-linearity = 0.207), and this association remained consistent across all subgroup analyses.</p> Conclusions <p>The GNRI is an important nutritional assessment tool, and is useful in predicting the prognosis of critically ill elderly patients with S- AKI.</p>