Background: Acute kidney injury (AKI) is common in intensive care and is frequently recognized late. We aimed to develop an interpretable, dynamic early warning score (EWS) to predict incident AKI within the next 24 h in ICU adult patients and to test its transportability temporally and geographically. Methods: We performed a retrospective cohort multi-center study using hospitalized ICU patients from MIMIC-IV and eICU-CRD databases. The outcome was incident AKI (KDIGO stage 1–3). Gradient-boosted trees (XGBoost) were trained with 10-fold cross-validation. Predictors were prespecified from the literature and finalized as 61 routinely available EHR predictors selected using SHAP ranking (spanning demographics/comorbidities, laboratory markers, vital-sign dynamics, and ICU therapies/procedures). Prespecified validations included (i) temporal validation in the COVID-19 era and (ii) geographic validation in eICU Northeast hospitals. Results: The development cohort included 51,833 ICU stays; temporal and geographic cohorts included 3346 and 2993 stays, respectively. Discrimination was high in internal validation (AUC 0.88, 95% CI 0.84–0.90) and remained robust temporally (AUC 0.84, 0.80–0.87) and geographically (AUC 0.82, 0.81–0.84). At a prespecified threshold, sensitivity/specificity were 0.76/0.79 (temporal) and 0.73/0.86 (geographic). Decision-curve analysis showed net benefit across clinically relevant thresholds. Key predictors reflected physiologic trajectories (e.g., mean arterial pressure dynamics), urine output, renal/metabolic markers (e.g., creatinine and BUN trends), and oxygenation dynamics (SpO₂). Conclusions: A routinely updated, explainable EHR-based EWS can predict ICU AKI up to 24 h in advance with stable performance across a pandemic-era temporal shift and external geographic validation.

Background: Iron deficiency (ID) is prevalent in congestive heart failure (CHF), worsening outcomes. While European guidelines recommend screening using ferritin and transferrin-saturation (TSAT), inconsistent diagnostic criteria, especially regarding functional deficiency (ferritin 100–299 μg/L + TSAT < 20%) and hyperferritinemia, limit prognostic accuracy. This study evaluated iron status definitions, including guideline criteria and a combined Ferritin-TSAT model, for predicting 365-day mortality in hospitalised CHF patients. Methods: This retrospective analysis used MIMIC-IV data from 1839 CHF patients. Iron status within 24 h of admission was categorised using: (1) Guideline ID vs. non-ID; (2) Ferritin categories; (3) TSAT categories; (4) Combined Ferritin-TSAT model (Low: guideline ID; Intermediate: ferritin 100–299 + TSAT ≥ 20%; High: ferritin ≥ 300 μg/L). Adjusted Cox models assessed mortality associations. Results: Guidelines-defined iron deficiency (33.66% prevalence) independently associated with higher 1-year mortality (56.1% vs. 29.4%; adjusted HR 4.36, 95% CI 3.35–5.34). The combined Ferritin-TSAT model showed significant prognostic value, differentiating true iron deficiency (reference) from hyperferritinemia (adjusted HR 0.50 vs. iron deficiency) and intermediate group (adjusted HR 0.36 vs. ID), indicating varying risk relative to the most deficient group. This combined model better distinguished hyperferritinemic and iron-replete subgroups than the binary guideline definition. Conclusions: Iron status, including deficiency and hyperferritinemia, independently predicts 1-year mortality in CHF. While guideline iron deficiency is a strong predictor, a combined Ferritin-TSAT classification offers finer risk stratification by identifying distinct phenotypes (true deficiency, hyperferritinemia, intermediate). Nuanced iron status assessment could improve prognostic evaluation and guide personalised therapies (e.g., IV iron for deficiency, investigation for hyperferritinemia) to enhance CHF outcomes.