ABSTRACT
Objective:To construct and evaluate a decision tree based on biomarkers for predicting severe acute kidney injury (AKI) in critical patients.Methods:A prospectively study was conducted. Critical patients who had been admitted to the department of critical care medicine of Xiaolan Hospital of Southern Medical University from January 2017 to June 2018 were enrolled. The clinical data of the patients were recorded, and the biomarkers, including serum cystatin C (sCys C) and urinary N-acetyl-β-D-glucosaminidase (uNAG) were established immediately after admission to intensive care unit (ICU), and the end points were recorded. The test cohort was established with patient data from January to December 2017. The decision tree classification and regression tree (CART) algorithm was used, and the best cut-off values of biomarkers were used as the decision node to construct a biomarker decision tree model for predicting severe AKI. The accuracy of the decision tree model was evaluated by the overall accuracy and the receiver operating characteristic (ROC) curve. The validation cohort, established on patient data from January to June 2018, was used to further validate the accuracy and predictive ability of the decision tree.Results:In test cohort, 263 patients were enrolled, of whom 57 developed severe AKI [defined as phase 2 and 3 of Kidney Disease: Improving Global Outcomes (KDIGO) criterion]. Compared with patients without severe AKI, severe AKI patients were older [years old: 64 (49, 74) vs. 52 (41, 66)], acute physiology and chronic health evaluation Ⅱ (APACHEⅡ) score were higher [23 (19, 27) vs. 15 (11, 20)], the incidence of hypertension, diabetes and other basic diseases and sepsis were higher (64.9% vs. 40.3%, 28.1% vs. 10.7%, 63.2% vs. 29.6%), the levels of sCys C and uNAG were higher [sCys C (mg/L): 1.38 (1.12, 2.02) vs. 0.79 (0.67, 0.98), uNAG (U/mmol Cr): 5.91 (2.43, 10.68) vs. 2.72 (1.60, 3.90)], hospital mortality and 90-day mortality were higher (21.1% vs. 4.4%, 52.6% vs. 13.1%), the length of ICU stay was longer [days: 6.0 (4.0, 9.5) vs. 3.0 (1.0, 6.0)], and renal replacement therapy requirement was higher (22.8% vs. 1.9%), with statistically significant differences (all P < 0.05). ROC curve analysis showed that the areas under ROC curve (AUC) of sCys C and uNAG in predicting severe AKI were 0.857 [95% confidence interval (95% CI) was 0.809-0.897) ] and 0.735 (95% CI was 0.678-0.788), and the best cut-off values were 1.05 mg/L and 5.39 U/mmol Cr, respectively. The structure of the biomarker decision tree model constructed by biomarkers were intuitive. The overall accuracy in predicting severe AKI was 86.0%, and AUC was 0.905 (95% CI was 0.863-0.937), the sensitivity was 0.912, and the specificity was 0.796. In validation cohort of 130 patients, this decision tree yielded an excellent AUC of 0.909 (95% CI was 0.846-0.952), the sensitivity was 0.906, and the specificity was 0.816, with an overall accuracy of 81.0%. Conclusion:The decision tree model based on biomarkers for predicting severe AKI in critical patients is highly accurate, intuitive and executable, which is helpful for clinical judgment and decision.
ABSTRACT
Objective@#To investigate the influence of serum creatinine (sCr) at different time-points on prognosis of critically ill patients with acute kidney injury (AKI).@*Methods@#This study was retrospectively analyzed the clinical data of critical patients with AKI who admitted to the mixed ICU of Xiaolan Hospital of Southern Medical University during March 2015 and January 2016. According to the clinical prognosis, the patients were divided into the renal replacement therapy (RRT) group and non-renal replacement therapy (non-RRT) group, 28-day renal loss group and renal recover group, hospital death group and survival group. Serum Cr at different time-points and clinical data were collected. The receiver operating characteristic (ROC) curve and the area under curve (AUC) were used to evaluate the capability of sCr at different time-points in predicting clinical prognosis.@*Results@#During the study, 85 AKI patients were enrolled. The in-hospital mortality was 20%, RRT rate was 15.3%, and renal lose at 28 days after ICU admission was 31.8%. The levels of sCr out of ICU (o-sCr) and the peak of sCr were significantly higher in the RRT group than the non-RRT group (P<0.01). The o-sCr and p-sCr predicted RRT during the hospital stay with a higher AUC value (0.806 vs 0.833) than b-sCr and a-sCr. The levels of b-sCr, a-sCr, o-sCr, and p-sCr were all significantly higher in the28-day renal loss group than the kidney recover group (P<0.01). The levels of o-sCr and p-sCr were significantly higher in the hospital death group than the survival group (P<0.05). The o-sCr predicted renal lose at 28 days and hospital death with the highest AUC value of 0.850 and 0.797, respectively.@*Conclusions@#It cannot be ignored to monitor dynamically the level of sCr at different time-points in critical patients with AKI, which can predict the clinical prognosis such as hospital death, RRT and renal lose at 28 days after ICU admission.
ABSTRACT
Objective To investigate the influence of serum creatinine (sCr) at different time-points on prognosis of critically ill patients with acute kidney injury (AKI).Methods This study was retrospectively analyzed the clinical data of critical patients with AKI who admitted to the mixed ICU of Xiaolan Hospital of Southern Medical University during March 2015 and January 2016. According to the clinical prognosis, the patients were divided into the renal replacement therapy (RRT) group and non-renal replacement therapy (non-RRT) group, 28-day renal loss group and renal recover group, hospital death group and survival group. Serum Cr at different time-points and clinical data were collected. The receiver operating characteristic (ROC) curve and the area under curve (AUC) were used to evaluate the capability of sCr at different time-points in predicting clinical prognosis.Results During the study, 85 AKI patients were enrolled. The in-hospital mortality was 20％, RRT rate was 15.3％, and renal lose at 28 days after ICU admission was 31.8％. The levels of sCr out of ICU (o-sCr) and the peak of sCr were significantly higher in the RRT group than the non-RRT group (P<0.01). The o-sCr and p-sCr predicted RRT during the hospital stay with a higher AUC value (0.806vs 0.833) than b-sCr and a-sCr. The levels of b-sCr, a-sCr, o-sCr, and p-sCr were all significantly higher in the28-day renal loss group than the kidney recover group (P<0.01). The levels of o-sCr and p-sCr were significantly higher in the hospital death group than the survival group (P<0.05). The o-sCr predicted renal lose at 28 days and hospital death with the highest AUC value of 0.850 and 0.797, respectively.Conclusions It cannot be ignored to monitor dynamically the level of sCr at different time-points in critical patients with AKI, which can predict the clinical prognosis such as hospital death, RRT and renal lose at 28 days after ICU admission.
ABSTRACT
Objective To investigate the clinical value of serum cystatin C (sCysC) and APACHE Ⅱ score in predicting diagosis and prognosis of acute kidney injury(AKI) in patients with sepsis. Methods In this study, we prospectively enrolled 138 adult patients with sepsis who had been admitted to the mixed ICU of Xiaolan Hospital of Southern Medical University during March 2015 to January 2016. According to the Kidney Disease Improving Global Outcomes (KDIGO) criterion, the patients were divided into non-AKI group and AKI group (including mild AKI and severe AKI). The receiver operating characteristic(ROC) curve and the area under curve(AUC) were used to evaluate these indexes' capability of detecting septic AKI and its prognosis. Results In this study,72 patients (52.2％) developed AKI. The levels of sCysC and APACHE Ⅱ score were significantly higher in AKI than in non-AKI (P<0.05). In total, 33 patients (23.9％) developed severe AKI. The levels of sCysC and APACHE Ⅱscore were significantly higher in severe AKI than in non-AKI and mild AKI (P<0.05) . Combination of sCysC and APACHE Ⅱ score predicted AKI and severe AKI after ICU admission with a higherAUC value (0.880&0.930) than each biomarker alone. In this cohort, in-hospital mortality was 19.6％and renal replacement therapy rate was 9.4％,which were strikingly higher in AKI group than non AKI group (P<0.05). Conclusions sCysC is a novel indexes for predicting AKI and its prognosis in patients with sepsis. Combinating with APACHE Ⅱ score can further improve its predictive performance of AKI detection and short-term prognosis.