(1) Background: Inflammation plays an important role in the onset and progression of acute kidney injury (AKI). Despite this, evidence regarding the prognostic effect of the monocyte-to-lymphocyte ratio (MLR), a novel systemic inflammation marker, among patients with AKI is scarce. This study sets out to investigate the prognostic potential of both baseline and early changes in MLR for short-term mortality among critically ill patients with AKI. (2) Method: Eligible patients with AKI from the Medical Information Mart for Intensive Care IV database were retrospectively analyzed. MLR cutoff values were determined using maximally selected rank statistics and tertiles. The clinical outcomes were 30-day and 90-day mortality in the intensive care unit. A restricted cubic splines model and Cox proportional hazards models were utilized to evaluate the association between the baseline MLR and short-term mortality. Then, the trends in MLR over time were compared between the 30-day survivors and non-survivors using a generalized additive mixed model (GAMM). (3) Result: A total of 15,986 patients were enrolled. Multivariable Cox regression analysis identified baseline MLR ≥ 0.48 as an independent risk factor predicting 30-day mortality (HR 1.33, 95%CI 1.24, 1.45, p < 0.001) and 90-day mortality (HR 1.34, 95%CI 1.23, 1.52, p < 0.001) after adjusting for potential confounders. Similar trends were observed for 30-day and 90-day mortality when tertiles were used to group patients. The restricted cubic splines model revealed a non-linear association between MLR and 30-day and 90-day mortality (both p for non-linear < 0.001, both p for overall < 0.001). The area under the curve of 0.64 for MLR was higher than that of monocytes (0.55) and lymphocytes (0.61). In the subgroup analyses, despite the noted significant interactions, the direction of the observed association between MLR and 30-day mortality was consistent across most prespecified subgroups, except for shock and black ethnicity. The GAMM results highlighted that, as time went on, MLR in the 30-day survival group consistently declined, whereas MLR in the non-survival group rose within 15 days post-ICU admission. The difference between the two groups persisted significantly even after adjusting for confounders (p = 0.006). (4) Conclusion: A higher baseline MLR was identified as an independent risk factor predicting 30-day and 90-day mortality. The early increase in MLR was associated with high 30-day mortality, suggesting that dynamic monitoring of MLR could potentially better predict survival in critically ill patients with AKI.

	Year	Citations

About