Dataset Information

Acute kidney injury detection using refined and physiological-feature augmented urine output.

ABSTRACT: Acute kidney injury (AKI) is common in the intensive care unit, where it is associated with increased mortality. AKI is often defined using creatinine and urine output criteria. The creatinine-based definition is more reliable but less expedient, whereas the urine output based definition is rapid but less reliable. Our goal is to examine the urine output criterion and augment it with physiological features for better agreement with creatinine-based definitions of AKI. The objectives are threefold: (1) to characterize the baseline agreement of urine output and creatinine definitions of AKI; (2) to refine the urine output criteria to identify the thresholds that best agree with the creatinine-based definition; and (3) to build generalized estimating equation (GEE) and generalized linear mixed-effects (GLME) models with static and time-varying features to improve the accuracy of a near-real-time marker for AKI. We performed a retrospective observational study using data from two independent critical care databases, MIMIC-III and eICU, for critically ill patients who developed AKI in intensive care units. We found that the conventional urine output criterion (6 hr, 0.5 ml/kg/h) has specificity and sensitivity of 0.49 and 0.54 for MIMIC-III database; and specificity and sensitivity of 0.38 and 0.56 for eICU. Secondly, urine output thresholds of 12 hours and 0.6 ml/kg/h have specificity and sensitivity of 0.58 and 0.48 for MIMIC-III; and urine output thresholds of 10 hours and 0.6 ml/kg/h have specificity and sensitivity of 0.49 and 0.48 for eICU. Thirdly, the GEE model of four hours duration augmented with static and time-varying features can achieve a specificity and sensitivity of 0.66 and 0.61 for MIMIC-III; and specificity and sensitivity of 0.66 and 0.64 for eICU. The GLME model of four hours duration augmented with static and time-varying features can achieve a specificity and sensitivity of 0.71 and 0.55 for MIMIC-III; and specificity and sensitivity of 0.66 and 0.60 for eICU. The GEE model has greater performance than the GLME model, however, the GLME model is more reflective of the variables as fixed effects or random effects. The significant improvement in performance, relative to current definitions, when augmenting with patient features, suggest the need of incorporating these features when detecting disease onset and modeling at window-level rather than patient-level.

SUBMITTER: Alkhairy S

PROVIDER: S-EPMC8486770 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAutomated data analysis and processing has the potential to assist, improve and guide decision making in medical practice. However, by now it has not yet been fully integrated in a clinical setting. Herein we present the first results of applying algorithm-based detection to the diagnosis of postoperative acute kidney injury (AKI) comprising patient data from a cardiac surgical intensive care unit (ICU).MethodsFirst, we generated a well-defined study population of cardiac surgical ICU patients by implementing an application programming interface (API) to extract, clean and select relevant data from the archived digital patient management system. Health records of N = 21,045 adult patients admitted to the ICU following cardiac surgery between 2012 and 2022 were analyzed. Secondly, we developed a software functionality to detect the incidence of AKI according to Kidney Disease: Improving Global Outcomes (KDIGO) criteria, including urine output. Incidence, severity, and temporal evolution of AKI were assessed.ResultsWith the use of our automated data analyzing model the overall incidence of postoperative AKI was 65.4% (N = 13,755). Divided by stages, AKI 2 was the most frequent maximum disease stage with 30.5% of patients (stage 1 in 17.6%, stage 3 in 17.2%). We observed considerable temporal divergence between first detections and maximum AKI stages: 51% of patients developed AKI stage 2 or 3 after a previously identified lower stage. Length of ICU stay was significantly prolonged in AKI patients (8.8 vs. 6.6 days, p < 0.001) and increased for higher AKI stages up to 10.1 days on average. In terms of AKI criteria, urine output proved to be most relevant, contributing to detection in 87.3% (N = 12,004) of cases.ConclusionThe incidence of postoperative AKI following cardiac surgery is strikingly high with 65.4% when using full KDIGO-criteria including urine output. Automated data analysis demonstrated reliable early detection of AKI with progressive deterioration of renal function in the majority of patients, therefore allowing for potential earlier therapeutic intervention for preventing or lessening disease progression, reducing the length of ICU stay, and ultimately improving overall patient outcomes.

Project description:Background: The relationship between urine output (UO) and severe-stage progression in the early phase of acute kidney injury (AKI) remains unclear. This study aimed to investigate the relationship between early-phase UO6-12h [UO within 6 h after diagnosis of stage 1 AKI by Kidney Disease: Improving Global Outcomes (KDIGO) UO criteria] and severe-stage progression of AKI and to identify a reference value of early-phase UO6-12h for guiding initial therapy in critical care. Methods: Adult patients with UO < 0.5 ml/kg/h for the first 6 h after intensive care unit (ICU) admission (meeting stage 1 AKI by UO) and UO6-12h ≥ 0.5 ml/kg/h were identified from the Medical Information Mart for Intensive Care (MIMIC) III database. The primary outcome was progression to stage 2/3 AKI by UO. After other variables were adjusted through multivariate analysis, generalized additive model (GAM) was used to visualize the relationship between early-phase UO6-12h and progression to stage 2/3 AKI by UO. A two-piecewise linear regression model was employed to identify the inflection point of early-phase UO6-12h above which progression risk significantly leveled off. Sensitivity and subgroup analyses were performed to assess the robustness of our findings. Results: Of 2,984 individuals, 1,870 (62.7%) with KDIGO stage 1 UO criteria progressed to stage 2/3 AKI. In the multivariate analysis, early-phase UO6-12h showed a significant association with progression to stage 2/3 AKI by UO (odds ratio, 0.40; 95% confidence interval, 0.34-0.46; p < 0.001). There was a non-linear relationship between early-phase UO6-12h and progression of AKI. Early-phase UO6-12h of 1.1 ml/kg/h was identified as the inflection point, above which progression risk significantly leveled off (p = 0.780). Patients with early-phase UO6-12h ≥ 1.1 ml/kg/h had significantly shorter length of ICU stay (3.82 vs. 4.17 days, p < 0.001) and hospital stay (9.28 vs. 10.43 days, p < 0.001) and lower 30-day mortality (11.05 vs. 18.42%, p < 0.001). The robustness of our findings was confirmed by sensitivity and subgroup analyses. Conclusions: Among early-stage AKI patients in critical care, there was a non-linear relationship between early-phase UO6-12h and progression of AKI. Early-phase UO6-12h of 1.1 ml/kg/h was the inflection point above which progression risk significantly leveled off.

Project description:Background and objectivesThe current threshold used for oliguria in the definition of neonatal AKI has been empirically defined as 1 ml/kg per hour. Urine output criteria are generally poorly documented, resulting in uncertainty in the most accurate threshold to identify AKI in very preterm infants with known tubular immaturity.Design, setting, participants, & measurementsWe conducted a bicentric study including 473 very preterm infants (240/7-296/7 weeks of gestation) born between January 2014 and December 2018 with urine output measurements every 3 hours during the first 7 days of life and two serum creatinine measurements during the first 10 days of life. AKI was defined using the neonatal Kidney Disease Improving Global Outcomes (KDIGO) definition. We tested whether higher urine output thresholds (1.5 or 2 ml/kg per hour) in modified AKI definitions may better discriminate neonatal mortality compared with the current definition.ResultsEarly-onset AKI was developed by 101 of 473 (21%) very preterm infants. AKI was diagnosed on the basis of urine output criteria alone (no rise in creatinine) for 27 of 101 (27%) participants. Early-onset AKI was associated with higher risk of death before discharge (adjusted odds ratio, 3.9; 95% confidence interval, 1.9 to 7.8), and the AKI neonatal KDIGO score showed good discriminative performance for neonatal mortality, with an area under the receiver operating characteristic (ROC) curve of 0.68 (95% confidence interval, 0.61 to 0.75). Modified AKI definitions that included higher urine output thresholds showed significantly improved discriminative performance, with areas under the ROC curve of 0.73 (95% confidence interval, 0.66 to 0.80) for the 1.5-ml/kg per hour threshold and 0.75 (95% confidence interval, 0.68 to 0.81) for the 2-ml/kg per hour threshold.ConclusionsEarly-onset AKI was diagnosed on the basis of urine output exclusively for a quarter of the cases. Furthermore, modified AKI definitions that included higher urine output improved the discriminative performance for predicting mortality.

Project description:IntroductionThe current definition of acute kidney injury (AKI) includes increased serum creatinine (sCr) concentration and decreased urinary output (UO). Recent studies suggest that the standard UO threshold of 0.5 ml/kg/h may be suboptimal. This study aimed to develop and validate a novel UO-based AKI classification system that improves mortality prediction and patient stratification.MethodsData were obtained from the MIMIC-IV and eICU databases. The development process included (1) evaluating UO as a continuous variable over 3-, 6-, 12-, and 24-h periods; (2) identifying 3 optimal UO cutoff points for each time window (stages 1, 2, and 3); (3) comparing sensitivity and specificity to develop a unified staging system; (4) assessing average versus persistent reduced UO hourly; (5) comparing the new UO-AKI system to the KDIGO UO-AKI system; (6) integrating sCr criteria with both systems and comparing them; and (7) validating the new classification with an independent cohort. In all these steps, the outcome was hospital mortality. Another analyzed outcome was 90-day mortality. The analyses included ROC curve analysis, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and logistic and Cox regression analyses.ResultsFrom the MIMIC-IV database, 35,845 patients were included in the development cohort. After comparing the sensitivity and specificity of 12 different lowest UO thresholds across four time frames, 3 cutoff points were selected to compose the proposed UO-AKI classification: stage 1 (0.2-0.3 mL/kg/h), stage 2 (0.1-0.2 mL/kg/h), and stage 3 (< 0.1 mL/kg/h) over 6 h. The proposed classification had better discrimination when the average was used than when the persistent method was used. The adjusted odds ratio demonstrated a significant stepwise increase in hospital mortality with advancing UO-AKI stage. The proposed classification combined or not with the sCr criterion outperformed the KDIGO criteria in terms of predictive accuracy-AUC-ROC 0.75 (0.74-0.76) vs. 0.69 (0.68-0.70); NRI: 25.4% (95% CI: 23.3-27.6); and IDI: 4.0% (95% CI: 3.6-4.5). External validation with the eICU database confirmed the superior performance of the new classification system.ConclusionThe proposed UO-AKI classification enhances mortality prediction and patient stratification in critically ill patients, offering a more accurate and practical approach than the current KDIGO criteria.

Project description:BackgroundContinuous renal replacement therapy (CCRT) is a frequently used modality for the support of intensive care patients with acute kidney injury (AKI). Nevertheless, there are no objective criteria for the discontinuation of CRRT. The purpose of this study was to investigate whether urine neutrophil gelatinase-associated lipocalin (uNGAL) alone or in combination with urine output could be used as a diagnostic test for renal function recovery in ICU patients on CRRT.MethodsThis was a single-centre prospective observational study including patients with acute kidney failure needing CRRT. Sixty-nine patients were enrolled, and 54 completed the study. Of the 54 patients, 22 recovered renal function (REC), defined as dialysis independency at 72 h from discontinuation, while 32 patients did not (NREC). Urine NGAL was measured at 0, 6, 12, and 24 h after CRRT discontinuation. The cumulated urine output was measured for 24 h prior to discontinuation and at 6, 12, and 24 h after discontinuation. Missing uNGAL values were calculated by interpolation. The Youden's index was used to calculate cut-off values in order to define uNGAL and urine output single variable and 2-variable diagnostic tests with the optimum prediction of successful CRRT discontinuation.ResultsBaseline characteristics at CRRT initiation were similar between groups. Compared to the NREC group, the REC group had significantly higher urine output (p < 0.0001) and lower uNGAL (p < 0.001) at all time points, except for uNGAL at 24 h (p < 0.24). The best uNGAL predictor for successful CRRT discontinuation was uNGAL at 6 h after discontinuation (predictive value 80%). The best single predictor was cumulated urine output 24 h before discontinuation (predictive value 85%). The combinations of uNGAL at 6 h (cut-off 1650 μg/L) with cumulated urine output 24 h prior to discontinuation (cut-off 210 ml) proved to be the superior tests (using either "or" or "and"), with predictive values of 93% (successful CRRT discontinuation) and 92% (dialysis dependency).ConclusionsWith a predictive value of 93%, the combination of uNGAL at 6 h after and the cumulated urine output 24 h prior to CRRT cessation proved to be the best diagnostic test for successful CRRT discontinuation in ICU patients.Clinical trial registrationN/A.

Project description:BackgroundThe study of novel urinary biomarkers of acute kidney injury has expanded exponentially. Effective interpretation of data and meaningful comparisons between studies require awareness of factors that can adversely affect measurement. We examined how variations in short-term storage and processing might affect the measurement of urine biomarkers.Study designCross-sectional prospective.Setting & participantsHospitalized patients from 2 sites: Yale New Haven Hospital (n=50) and University of California, San Francisco Medical Center (n=36).PredictorsWe tested the impact of 3 urine processing conditions on these biomarkers: (1) centrifugation and storage at 4°C for 48 hours before freezing at -80°C, (2) centrifugation and storage at 25°C for 48 hours before freezing at -80°C, and (3) uncentrifuged samples immediately frozen at -80°C.OutcomesUrine concentrations of 5 biomarkers: neutrophil gelatinase-associated lipocalin (NGAL), interleukin 18 (IL-18), kidney injury molecule 1 (KIM-1), liver-type fatty acid-binding protein (L-FABP), and cystatin C.MeasurementsWe measured urine biomarkers by established enzyme-linked immunosorbent assay methods. Biomarker values were log-transformed, and agreement with a reference standard of immediate centrifugation and storage at -80°C was compared using concordance correlation coefficients (CCCs).ResultsNeither storing samples at 4°C for 48 hours nor centrifugation had a significant effect on measured levels, with CCCs higher than 0.9 for all biomarkers tested. For samples stored at 25°C for 48 hours, excellent CCC values (>0.9) also were noted between the test sample and the reference standard for NGAL, cystatin C, L-FABP and KIM-1. However, the CCC for IL-18 between samples stored at 25°C for 48 hours and the reference standard was 0.81 (95% CI, 0.66-0.96).LimitationsNo comparisons to fresh, unfrozen samples; no evaluation of the effect of protease inhibitors.ConclusionsAll candidate markers tested using the specified assays showed high stability with both short-term storage at 4°C and without centrifugation prior to freezing. For optimal fidelity, urine for IL-18 measurement should not be stored at 25°C before long-term storage or analysis.

Dataset Information

Acute kidney injury detection using refined and physiological-feature augmented urine output.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets