Search

Abstract Renal recovery following dialysis-requiring acute kidney injury (AKI-D) is a vital clinical outcome in critical care, yet it remains an understudied area. This retrospective cohort study, conducted in a medical center in Taiwan from 2015 to 2020, enrolled patients with AKI-D during intensive care unit stays. We aimed to develop and temporally test models for predicting dialysis liberation before hospital discharge using machine learning algorithms and explore early predictors. The dataset comprised 90 routinely collected variables within the first three days of dialysis initiation. Out of 1,381 patients who received acute dialysis, 27.3% experienced renal recovery. The cohort was divided into the training group (N = 1135) and temporal testing group (N = 251). The models demonstrated good performance, with an area under the receiver operating characteristic curve of 0.85 (95% CI, 0.81–0.88) and an area under the precision-recall curve of 0.69 (95% CI, 0.62–0.76) for the XGBoost model. Key predictors included urine volume, Charlson comorbidity index, vital sign derivatives (trend of respiratory rate and SpO2), and lactate levels. We successfully developed early prediction models for renal recovery by integrating early changes in vital signs and inputs/outputs, which have the potential to aid clinical decision-making in the ICU.

Abstract Background Several biomarkers have been proposed to predict the occurrence of acute kidney injury (AKI); however, their efficacy varies between different trials. The aim of this study was to compare the predictive performance of different candidate biomarkers for AKI. Methods In this systematic review, we searched PubMed, Medline, Embase, and the Cochrane Library for papers published up to August 15, 2022. We selected all studies of adults (> 18 years) that reported the predictive performance of damage biomarkers (neutrophil gelatinase-associated lipocalin (NGAL), kidney injury molecule-1 (KIM-1), liver-type fatty acid-binding protein (L-FABP)), inflammatory biomarker (interleukin-18 (IL-18)), and stress biomarker (tissue inhibitor of metalloproteinases-2 × insulin-like growth factor-binding protein-7 (TIMP-2 × IGFBP-7)) for the occurrence of AKI. We performed pairwise meta-analyses to calculate odds ratios (ORs) and 95% confidence intervals (CIs) individually. Hierarchical summary receiver operating characteristic curves (HSROCs) were used to summarize the pooled test performance, and the Grading of Recommendations, Assessment, Development and Evaluations criteria were used to appraise the quality of evidence. Results We identified 242 published relevant studies from 1,803 screened abstracts, of which 110 studies with 38,725 patients were included in this meta-analysis. Urinary NGAL/creatinine (diagnostic odds ratio [DOR] 16.2, 95% CI 10.1–25.9), urinary NGAL (DOR 13.8, 95% CI 10.2–18.8), and serum NGAL (DOR 12.6, 95% CI 9.3–17.3) had the best diagnostic accuracy for the risk of AKI. In subgroup analyses, urinary NGAL, urinary NGAL/creatinine, and serum NGAL had better diagnostic accuracy for AKI than urinary IL-18 in non-critically ill patients. However, all of the biomarkers had similar diagnostic accuracy in critically ill patients. In the setting of medical and non-sepsis patients, urinary NGAL had better predictive performance than urinary IL-18, urinary L-FABP, and urinary TIMP-2 × IGFBP-7: 0.3. In the surgical patients, urinary NGAL/creatinine and urinary KIM-1 had the best diagnostic accuracy. The HSROC values of urinary NGAL/creatinine, urinary NGAL, and serum NGAL were 91.4%, 85.2%, and 84.7%, respectively. Conclusions Biomarkers containing NGAL had the best predictive accuracy for the occurrence of AKI, regardless of whether or not the values were adjusted by urinary creatinine, and especially in medically treated patients. However, the predictive performance of urinary NGAL was limited in surgical patients, and urinary NGAL/creatinine seemed to be the most accurate biomarkers in these patients. All of the biomarkers had similar predictive performance in critically ill patients. Trial registration CRD42020207883 , October 06, 2020.

IntroductionEarly fluid balance has been found to affect short-term mortality in critically ill patients; however, there is little knowledge regarding the association between early cumulative fluid balance (CFB) and long-term mortality. This study aims to determine the distinct association between CFB day 1–3 (CFB 1–3) and day 4–7 (CFB 4–7) and long-term mortality in critically ill patients.Patients and MethodsThis study was conducted at Taichung Veterans General Hospital, a tertiary care referral center in central Taiwan, by linking the hospital critical care data warehouse 2015–2019 and death registry data of the Taiwanese National Health Research Database. The patients followed up until deceased or the end of the study on 31 December 2019. We use the log-rank test to examine the association between CFB 1–3 and CFB 4–7 with long-term mortality and multivariable Cox regression to identify independent predictors during index admission for long-term mortality in critically ill patients.ResultsA total of 4,610 patients were evaluated. The mean age was 66.4 ± 16.4 years, where 63.8% were men. In patients without shock, a positive CFB 4–7, but not CFB 1–3, was associated with 1-year mortality, while a positive CFB 1–3 and CFB 4–7 had a consistent and excess hazard of 1-year mortality among critically ill patients with shock. The multivariate Cox proportional hazard regression model identified that CFB 1–3 and CFB 4–7 (with per 1-liter increment, HR: 1.047 and 1.094; 95% CI 1.037–1.058 and 1.080–1.108, respectively) were independently associated with high long-term mortality in critically ill patients after adjustment of relevant covariates, including disease severity and the presence of shock.ConclusionsWe found that the fluid balance in the first week, especially on days 4–7, appears to be an early predictor for long-term mortality in critically ill patients. More studies are needed to validate our findings and elucidate underlying mechanisms.