Predicting and Modeling Recovery Dynamics Post-Acute Kidney Injury

Background: AKI affects 10%–25% of hospitalized patients and is associated with significant morbidity, mortality, and long-term adverse outcomes. Recovery patterns vary greatly, from full reversal to progression toward chronic kidney disease. Predicting short-term AKI states and understanding their dynamic trajectories could help optimize clinical interventions. Methods: This retrospective study used data from four healthcare systems in the Greater Plains Collaborative, spanning 2009–2022. A total of 94,531 inpatient encounters (54% male, 80% White patients) from 75,312 adults with admission eGFR ≥15 mL/min/1.73 m 2 and without prior dialysis or kidney failure were included. We developed CatBoost models, a gradient-boosting decision-tree algorithm, to predict 7-day AKI progression and reversal, then performed multistate modeling to estimate transition intensities and covariate effects on AKI state changes. Results: The models achieved strong performance across outcomes and subgroups: AUROC 0.79–0.89 and accuracy 0.7–0.79 for reversal; AUROC 0.91–0.93 and accuracy 0.83–0.87 for progression. Serum creatinine, systolic blood pressure (SBP), and albumin were key predictors across both outcomes. Low SBP (≤120 mmHg) predicted increased likelihood of progression, whereas high SBP (≥140 mmHg) predicted faster but asymmetric recovery with reduced chances of subsequent reversal. Multi-state analysis highlighted the dynamic and transient nature of AKI recovery, with nearly half of AKI-1 patients (instantaneous hazard rate=0.46) transitioning to “no AKI” peaking on the first day post-onset. Conclusions: This study presents a two-stage analytical framework linking short-term prediction with multi-state modelling to characterize early recovery and progression patterns after hospital-acquired AKI. The approach highlights a small set of routinely measured variables, such as serum creatinine trajectories and blood-pressure trends, that consistently track these dynamics across health systems. While the results are hypothesis-generating and require external, prospective validation, they lay groundwork for future studies on refining risk stratification and exploring targeted interventions in AKI care.