Dataset Information

Predicting acute kidney injury among burn patients in the 21st century: a classification and regression tree analysis.

ABSTRACT: Historically, acute kidney injury (AKI) carried a deadly prognosis in the burn population. The aim of this study is to provide a modern description of AKI in the burn population and to develop a prediction tool for identifying patients at risk for late AKI. A large multi-institutional database, the Glue Grant's Trauma-Related Database, was used to characterize AKI in a cohort of critically ill burn patients. The authors defined AKI according to the RIFLE criteria and categorized AKI as early, late, or progressive. They then used Classification and Regression Tree (CART) analysis to create a decision tree with data obtained from the first 48 hours of admission to predict which subset of patients would develop late AKI. The accuracy of this decision tree was tested in a separate, single-institution cohort of burn patients who met the same criteria for entry into the Glue Grant study. Of the 220 total patients analyzed from the Glue Grant cohort, 49 (22.2%) developed early AKI, 39 (17.7%) developed late AKI, and 16 (7.2%) developed progressive AKI. The group with progressive AKI was statistically older, with more comorbidities and with the worst survival when compared with those with early or late AKI. Using CART analysis, a decision tree was developed with an overall accuracy of 80% for the development of late AKI for the Glue Grant dataset. The authors then tested this decision tree on a smaller dataset from our own institution to validate this tool and found it to be 73% accurate. AKI is common in severe burns with notable differences between early, late, and progressive AKI. In addition, CART analysis provided a predictive model for early identification of patients at highest risk for developing late AKI with proven clinical accuracy.

SUBMITTER: Schneider DF

PROVIDER: S-EPMC3310938 | biostudies-literature | 2012 Mar-Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting acute kidney injury among burn patients in the 21st century: a classification and regression tree analysis.

Schneider David F DF Dobrowolsky Adrian A Shakir Irshad A IA Sinacore James M JM Mosier Michael J MJ Gamelli Richard L RL

Journal of burn care & research : official publication of the American Burn Association 20120301 2

Historically, acute kidney injury (AKI) carried a deadly prognosis in the burn population. The aim of this study is to provide a modern description of AKI in the burn population and to develop a prediction tool for identifying patients at risk for late AKI. A large multi-institutional database, the Glue Grant's Trauma-Related Database, was used to characterize AKI in a cohort of critically ill burn patients. The authors defined AKI according to the RIFLE criteria and categorized AKI as early, la ...[more]

PMID: 22370901

Similar Datasets

Project description:There is no good science in bad models. Cell culture is especially prone to artifacts. A number of novel cell culture technologies have become more broadly available in the 21st century, which allow overcoming limitations of traditional culture and are more physiologically relevant. These include the use of stem-cell derived human cells, cocultures of different cell types, scaffolds and extracellular matrices, perfusion platforms (such as microfluidics), 3D culture, organ-on-chip technologies, tissue architecture, and organ functionality. The physiological relevance of such models is further enhanced by the measurement of biomarkers (e.g., key events of pathways), organ specific functionality, and more comprehensive assessment cell responses by high-content methods. These approaches are still rarely combined to create microphysiological systems. The complexity of the combination of these technologies can generate results closer to the in vivo situation but increases the number of parameters to control, bringing some new challenges. In fact, we do not argue that all cell culture needs to be that sophisticated. The efforts taken are determined by the purpose of our experiments and tests. If only a very specific molecular target to cell response is of interest, a very simple model, which reflects this, might be much more suited to allow standardization and high-throughput. However, the less defined the end point of interest and cellular response are, the better we should approximate organ- or tissue-like culture conditions to make physiological responses more probable. Besides these technologic advances, important progress in the quality assurance and reporting on cell cultures as well as the validation of cellular test systems brings the utility of cell cultures to a new level. The advancement and broader implementation of Good Cell Culture Practice (GCCP) is key here. In toxicology, this is a major prerequisite for meaningful and reliable results, ultimately supporting risk assessment and product development decisions.

Project description:Background/aimAssessing prognosis for acetaminophen-induced acute liver failure (APAP-ALF) patients often presents significant challenges. King's College (KCC) has been validated on hospital admission, but little has been published on later phases of illness. We aimed to improve determinations of prognosis both at the time of and following admission for APAP-ALF using Classification and Regression Tree (CART) models.MethodsCART models were applied to US ALFSG registry data to predict 21-day death or liver transplant early (on admission) and post-admission (days 3-7) for 803 APAP-ALF patients enrolled 01/1998-09/2013. Accuracy in prediction of outcome (AC), sensitivity (SN), specificity (SP), and area under receiver-operating curve (AUROC) were compared between 3 models: KCC (INR, creatinine, coma grade, pH), CART analysis using only KCC variables (KCC-CART) and a CART model using new variables (NEW-CART).ResultsTraditional KCC yielded 69% AC, 90% SP, 27% SN, and 0.58 AUROC on admission, with similar performance post-admission. KCC-CART at admission offered predictive 66% AC, 65% SP, 67% SN, and 0.74 AUROC. Post-admission, KCC-CART had predictive 82% AC, 86% SP, 46% SN and 0.81 AUROC. NEW-CART models using MELD (Model for end stage liver disease), lactate and mechanical ventilation on admission yielded predictive 72% AC, 71% SP, 77% SN and AUROC 0.79. For later stages, NEW-CART (MELD, lactate, coma grade) offered predictive AC 86%, SP 91%, SN 46%, AUROC 0.73.ConclusionCARTs offer simple prognostic models for APAP-ALF patients, which have higher AUROC and SN than KCC, with similar AC and negligibly worse SP. Admission and post-admission predictions were developed.Key points• Prognostication in acetaminophen-induced acute liver failure (APAP-ALF) is challenging beyond admission • Little has been published regarding the use of King's College Criteria (KCC) beyond admission and KCC has shown limited sensitivity in subsequent studies • Classification and Regression Tree (CART) methodology allows the development of predictive models using binary splits and offers an intuitive method for predicting outcome, using processes familiar to clinicians • Data from the ALFSG registry suggested that CART prognosis models for the APAP population offer improved sensitivity and model performance over traditional regression-based KCC, while maintaining similar accuracy and negligibly worse specificity • KCC-CART models offered modest improvement over traditional KCC, with NEW-CART models performing better than KCC-CART particularly at late time points.

Project description:It has been suggested that fluid accumulation may delay recognition of acute kidney injury. We sought to determine the impact of fluid balance on the incidence of nondialysis requiring acute kidney injury in patients with acute lung injury and to describe associated outcomes, including mortality.Analysis of the Fluid and Catheter Treatment Trial, a factorial randomized clinical trial of conservative vs. liberal fluid management and of management guided by a central venous vs. pulmonary artery catheter.Acute Respiratory Distress Syndrome Network hospitals.One thousand patients.None.The incidence of acute kidney injury, defined as an absolute rise in creatinine of ?0.3 mg/dL or a relative change of >50% over 48 hrs, was examined before and after adjustment of serum creatinine for fluid balance. The incidence of acute kidney injury before adjustment for fluid balance was greater in those managed with the conservative fluid protocol (57% vs. 51%, p = .04). After adjustment for fluid balance, the incidence of acute kidney injury was greater in those managed with the liberal fluid protocol (66% vs. 58%, p = .007). Patients who met acute kidney injury criteria after adjustment of creatinine for fluid balance (but not before) had a mortality rate that was significantly greater than those who did not meet acute kidney injury criteria both before and after adjustment for fluid balance (31% vs. 12%, p < .001) and those who had acute kidney injury before but not after adjustment for fluid balance (31% vs. 11%, p = .005). The mortality of those patients meeting acute kidney injury criteria after but not before adjustment for fluid balance was similar to patients with acute kidney injury both before and after adjustment for fluid balance (31% vs. 38%, p = .18).Fluid management influences serum creatinine and therefore the diagnosis of acute kidney injury using creatinine-based definitions. Patients with "unrecognized" acute kidney injury that is identified after adjusting for positive fluid balance have higher mortality rates, and patients who have acute kidney injury before but not after adjusting for fluid balance have lower mortality rates. Future studies of acute kidney injury should consider potential differences in serum creatinine caused by changes in fluid balance and the impact of these differences on diagnosis and prognosis.

Dataset Information

Predicting acute kidney injury among burn patients in the 21st century: a classification and regression tree analysis.

Publications

Predicting acute kidney injury among burn patients in the 21st century: a classification and regression tree analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets