Approaches to Predicting Outcomes in Patients with Acute Kidney Injury.
ABSTRACT: Despite recognition that Acute Kidney Injury (AKI) leads to substantial increases in morbidity, mortality, and length of stay, accurate prognostication of these clinical events remains difficult. It remains unclear which approaches to variable selection and model building are most robust. We used data from a randomized trial of AKI alerting to develop time-updated prognostic models using stepwise regression compared to more advanced variable selection techniques. We randomly split data into training and validation cohorts. Outcomes of interest were death within 7 days, dialysis within 7 days, and length of stay. Data elements eligible for model-building included lab values, medications and dosages, procedures, and demographics. We assessed model discrimination using the area under the receiver operator characteristic curve and r-squared values. 2241 individuals were available for analysis. Both modeling techniques created viable models with very good discrimination ability, with AUCs exceeding 0.85 for dialysis and 0.8 for death prediction. Model performance was similar across model building strategies, though the strategy employing more advanced variable selection was more parsimonious. Very good to excellent prediction of outcome events is feasible in patients with AKI. More advanced techniques may lead to more parsimonious models, which may facilitate adoption in other settings.
Project description:Variable selection is an important step in building a multivariate regression model for which several methods and statistical packages are available. A comprehensive approach for variable selection in complex multivariate regression analyses within HIV cohorts is explored by utilizing both epidemiological and biostatistical procedures.Three different methods for variable selection were illustrated in a study comparing survival time between subjects in the Department of Defense's National History Study and the Atlanta Veterans Affairs Medical Center's HIV Atlanta VA Cohort Study. The first two methods were stepwise selection procedures, based either on significance tests (Score test), or on information theory (Akaike Information Criterion), while the third method employed a Bayesian argument (Bayesian Model Averaging).All three methods resulted in a similar parsimonious survival model. Three of the covariates previously used in the multivariate model were not included in the final model suggested by the three approaches. When comparing the parsimonious model to the previously published model, there was evidence of less variance in the main survival estimates.The variable selection approaches considered in this study allowed building a model based on significance tests, on an information criterion, and on averaging models using their posterior probabilities. A parsimonious model that balanced these three approaches was found to provide a better fit than the previously reported model.
Project description:Acute kidney injury (AKI) is a frequent complication of cardiac surgery. We sought prognostic combinations of postoperative biomarkers measured within 6 h of surgery, potentially in combination with cardiopulmonary bypass time (to account for the degree of insult to the kidney). We used data from a large cohort of patients and adapted methods for developing biomarker combinations to account for the multicenter design of the study.The primary endpoint was sustained mild AKI, defined as an increase of 50% or more in serum creatinine over preoperative levels lasting at least 2 days during the hospital stay. Severe AKI (secondary endpoint) was defined as a serum creatinine increase of 100% or more or dialysis during hospitalization. Data were from a cohort of 1219 adults undergoing cardiac surgery at 6 medical centers; among these, 117 developed sustained mild AKI and 60 developed severe AKI. We considered cardiopulmonary bypass time and 22 biomarkers as candidate predictors. We adapted Bayesian model averaging methods to develop center-adjusted combinations for sustained mild AKI by (1) maximizing the posterior model probability and (2) retaining predictors with posterior variable probabilities above 0.5. We used resampling-based methods to avoid optimistic bias in evaluating the biomarker combinations.The maximum posterior model probability combination included plasma N-terminal-pro-B-type natriuretic peptide, plasma heart-type fatty acid binding protein, and change in serum creatinine from before to 0-6 h after surgery; the median probability combination additionally included plasma interleukin-6. The center-adjusted, optimism-corrected AUCs for these combinations were 0.80 (95% CI: 0.78, 0.87) and 0.81 (0.78, 0.87), respectively, for predicting sustained mild AKI, and 0.81 (0.76, 0.90) and 0.83 (0.76, 0.90), respectively, for predicting severe AKI. For these data, the Bayesian model averaging methods yielded combinations with prognostic capacity comparable to that achieved by standard frequentist methods but with more parsimonious models.Pending external validation, the identified combinations could be used to identify individuals at high risk of AKI immediately after cardiac surgery and could facilitate clinical trials of renoprotective agents.
Project description:BACKGROUND:The current acute kidney injury (AKI) risk prediction model for patients undergoing percutaneous coronary intervention (PCI) from the American College of Cardiology (ACC) National Cardiovascular Data Registry (NCDR) employed regression techniques. This study aimed to evaluate whether models using machine learning techniques could significantly improve AKI risk prediction after PCI. METHODS AND FINDINGS:We used the same cohort and candidate variables used to develop the current NCDR CathPCI Registry AKI model, including 947,091 patients who underwent PCI procedures between June 1, 2009, and June 30, 2011. The mean age of these patients was 64.8 years, and 32.8% were women, with a total of 69,826 (7.4%) AKI events. We replicated the current AKI model as the baseline model and compared it with a series of new models. Temporal validation was performed using data from 970,869 patients undergoing PCIs between July 1, 2016, and March 31, 2017, with a mean age of 65.7 years; 31.9% were women, and 72,954 (7.5%) had AKI events. Each model was derived by implementing one of two strategies for preprocessing candidate variables (preselecting and transforming candidate variables or using all candidate variables in their original forms), one of three variable-selection methods (stepwise backward selection, lasso regularization, or permutation-based selection), and one of two methods to model the relationship between variables and outcome (logistic regression or gradient descent boosting). The cohort was divided into different training (70%) and test (30%) sets using 100 different random splits, and the performance of the models was evaluated internally in the test sets. The best model, according to the internal evaluation, was derived by using all available candidate variables in their original form, permutation-based variable selection, and gradient descent boosting. Compared with the baseline model that uses 11 variables, the best model used 13 variables and achieved a significantly better area under the receiver operating characteristic curve (AUC) of 0.752 (95% confidence interval [CI] 0.749-0.754) versus 0.711 (95% CI 0.708-0.714), a significantly better Brier score of 0.0617 (95% CI 0.0615-0.0618) versus 0.0636 (95% CI 0.0634-0.0638), and a better calibration slope of observed versus predicted rate of 1.008 (95% CI 0.988-1.028) versus 1.036 (95% CI 1.015-1.056). The best model also had a significantly wider predictive range (25.3% versus 21.6%, p < 0.001) and was more accurate in stratifying AKI risk for patients. Evaluated on a more contemporary CathPCI cohort (July 1, 2015-March 31, 2017), the best model consistently achieved significantly better performance than the baseline model in AUC (0.785 versus 0.753), Brier score (0.0610 versus 0.0627), calibration slope (1.003 versus 1.062), and predictive range (29.4% versus 26.2%). The current study does not address implementation for risk calculation at the point of care, and potential challenges include the availability and accessibility of the predictors. CONCLUSIONS:Machine learning techniques and data-driven approaches resulted in improved prediction of AKI risk after PCI. The results support the potential of these techniques for improving risk prediction models and identification of patients who may benefit from risk-mitigation strategies.
Project description:<h4>Introduction</h4>After dialysis-requiring acute kidney injury (AKI-D), recovery of sufficient kidney function to discontinue dialysis is an important clinical and patient-oriented outcome. Predicting the probability of recovery in individual patients is a common dilemma.<h4>Methods</h4>This cohort study examined all adult members of Kaiser Permanente Northern California who experienced AKI-D between January 2009 and September 2015 and had predicted inpatient mortality of <20%. Candidate predictors included demographic characteristics, comorbidities, laboratory values, and medication use. We used logistic regression and classification and regression tree (CART) approaches to develop and cross-validate prediction models for recovery.<h4>Results</h4>Among 2214 patients with AKI-D, mean age was 67.1 years, 40.8% were women, and 54.0% were white; 40.9% of patients recovered. Patients who recovered were younger, had higher baseline estimated glomerular filtration rates (eGFR) and preadmission hemoglobin levels, and were less likely to have prior heart failure or chronic liver disease. Stepwise logistic regression applied to bootstrapped samples identified baseline eGFR, preadmission hemoglobin level, chronic liver disease, and age as the predictors most commonly associated with coming off dialysis within 90 days. Our final logistic regression model including these predictors had a correlation coefficient between observed and predicted probabilities of 0.97, with a c-index of 0.64. An alternate CART approach did not outperform the logistic regression model (c-index 0.61).<h4>Conclusion</h4>We developed and cross-validated a parsimonious prediction model for recovery after AKI-D with excellent calibration using routinely available clinical data. However, the model's modest discrimination limits its clinical utility. Further research is needed to develop better prediction tools.
Project description:OBJECTIVE:To focus on the potential beneficial effects of the pleiotropic effects of dipeptidyl peptidase-4 inhibitors (DPP4is) on attenuating progression of diabetic kidney disease in reducing the long-term effect of the acute kidney injury (AKI) to chronic kidney disease (CKD) transition. PATIENTS AND METHODS:Data from the National Health Insurance Research Database from January 1, 1999, to July 31, 2011, were analyzed, and patients with diabetes weaning from dialysis-requiring AKI were identified. Cox proportional hazards models and inverse-weighted estimates of the probability of treatment were used to adjust for treatment selection bias. The outcomes were incident end-stage renal disease (ESRD) and mortality, major adverse cardiovascular events, and hospitalized heart failure. RESULTS:Of a total of 6165 patients with diabetes weaning from dialysis-requiring AKI identified, 5635 (91.4%) patients were DPP4i nonusers and 530 (8.6%) patients were DPP4i users. Compared with DPP4i nonusers, DPP4i users had a lower risk of ESRD (hazard ratio, 0.81; 95% CI, 0.70-0.94; P=.04) and all-cause mortality (hazard ratio, 0.28; 95% CI, 0.23-0.34; P<.001) after adjustments for CKD, advanced CKD, and angiotensin-converting enzyme inhibitor or angiotensin II receptor blocker use. In contrast, the risk of major adverse cardiovascular events and hospitalized heart failure did not differ significantly between groups. CONCLUSION:Dipeptidyl peptidase-4 inhibitor users had a lower risk of ESRD and mortality than did nonusers among patients with diabetes after weaning from dialysis-requiring AKI. Therefore, a prospective study of AKI to CKD transitions after episodes of AKI is needed to optimally target DPP4i interventions.
Project description:<h4>Background</h4>Profound alterations in immune responses associated with uremia and exacerbated by dialysis increase the risk of active tuberculosis (TB). Evidence of the long-term risk and outcome of active TB after acute kidney injury (AKI) is limited.<h4>Methods</h4>This population-based-cohort study used claim records retrieved from the Taiwan National Health Insurance database. We retrieved records of all hospitalized patients, more than 18 years, who underwent dialysis for acute kidney injury (AKI) during 1999-2008 and validated using the NSARF data. Time-dependent Cox proportional hazards model to adjust for the ongoing effect of end-stage renal disease (ESRD) was conducted to predict long-term de novo active TB after discharge from index hospitalization.<h4>Results</h4>Out of 2,909 AKI dialysis patients surviving 90 days after index discharge, 686 did not require dialysis after hospital discharge. The control group included 11,636 hospital patients without AKI, dialysis, or history of TB. The relative risk of active TB in AKI dialysis patients, relative to the general population, after a mean follow-up period of 3.6 years was 7.71. Patients who did (hazard ratio [HR], 3.84; p<0.001) and did not (HR, 6.39; p<0.001) recover from AKI requiring dialysis had significantly higher incidence of TB than patients without AKI. The external validated data also showed nonrecovery subgroup (HR = 4.37; p = 0.049) had high risk of developing active TB compared with non-AKI. Additionally, active TB was associated with long-term all-cause mortality after AKI requiring dialysis (HR, 1.34; p = 0.032).<h4>Conclusions</h4>AKI requiring dialysis seems to independently increase the long-term risk of active TB, even among those who weaned from dialysis at discharge. These results raise concerns that the increasing global burden of AKI will in turn increase the incidence of active TB.
Project description:BACKGROUND: Prolonged mechanical ventilation (PMV) is increasingly common worldwide, consuming enormous healthcare resources. Factors that modify PMV outcome are still obscure. METHODS: We selected patients without preceding mechanical ventilation within the one past year and who developed PMV during index admission in Taiwan's National Health Insurance (NHI) system during 1998-2007 for comparison of mortality and resource use. They were divided into three groups: (1) patients with end-stage renal diseases (ESRD) before the index admission for PMV onset; (2) patients with dialysis-requiring acute kidney injury (AKI-dialysis) during the hospitalization course; and (3) patients without AKI or with non dialysis-requiring AKI during the hospitalization course (non-AKI). We used a random-effects logistic regression model to identify factors associated with mortality. RESULTS: Compared with the other two groups, patients with AKI-dialysis had significantly longer mechanical ventilation, more frequent use of vasopressors, longer intensive care unit/hospital stay and higher inpatient expenditures during the index admission. Relative to non-AKI patients, patients with AKI-dialysis had an elevated mortality hazard; the adjusted relative risk ratios were 1.51 (95% confidence interval [CI]:1.46-1.56), 1.27 (95% CI: 1.23-1.32), and 1.10 (95% CI: 1.08-1.12) for mortality rates at discharge, 3 months, and 4 years after PMV, respectively. Patients with AKI-dialysis also consumed significantly higher total in-patient expenditure than the other two patient groups (p<0.001). CONCLUSIONS: Among patients that need PMV care during an admission, the presence of de novo AKI requiring dialysis significantly increased short and long term mortality, and demand for health care resources.
Project description:Clinical prediction models are used frequently in clinical practice to identify patients who are at risk of developing an adverse outcome so that preventive measures can be initiated. A prediction model can be developed in a number of ways; however, an appropriate variable selection strategy needs to be followed in all cases. Our purpose is to introduce readers to the concept of variable selection in prediction modelling, including the importance of variable selection and variable reduction strategies. We will discuss the various variable selection techniques that can be applied during prediction model building (backward elimination, forward selection, stepwise selection and all possible subset selection), and the stopping rule/selection criteria in variable selection (p values, Akaike information criterion, Bayesian information criterion and Mallows' Cp statistic). This paper focuses on the importance of including appropriate variables, following the proper steps, and adopting the proper methods when selecting variables for prediction models.
Project description:Urinary liver-type fatty acid-binding protein (L-FABP) is a proximal tubular injury candidate biomarker for early detection of acute kidney injury (AKI), with variable performance characteristics depending on clinical settings.Meta-analysis of diagnostic test studies assessing the performance of urinary L-FABP in AKI.Literature search in MEDLINE, EMBASE, Scopus, Google Scholar, Cochrane Central Register of Controlled Trials, and ClinicalTrials.gov using search terms "liver-type fatty acid-binding protein" and "L-FABP."Studies of humans investigating the performance characteristics of urinary L-FABP for the early diagnosis of AKI and AKI-related outcomes, including dialysis requirement and mortality.Urinary L-FABP.Diagnosis of AKI, dialysis requirement, and in-hospital death.15 prospective cohort and 2 case-control studies were identified. Only 7 cohort studies could be meta-analyzed. The estimated sensitivity of urinary L-FABP level for the diagnosis of AKI was 74.5% (95% CI, 60.4%-84.8%), and specificity was 77.6% (95% CI, 61.5%-88.2%). The estimated sensitivity of urinary L-FABP level for predicting dialysis requirement was 69.1% (95% CI, 34.6%-90.5%), and specificity was 42.7% (95% CI, 3.1%-94.5%); for in-hospital mortality, sensitivity and specificity were 93.2% (95% CI, 66.2%-99.0%) and 78.8% (95% CI, 27.0%-97.4%), respectively.Paucity and low quality of studies, different clinical settings, and variable definitions of AKI.Although urinary L-FABP may be a promising biomarker for early detection of AKI and prediction of dialysis requirement and in-hospital mortality, its potential value needs to be validated in large studies and across a broader spectrum of clinical settings.
Project description:Off-pump coronary artery bypass grafting (CABG) has been advocated to cause less inflammation, morbidity, and mortality than the more traditional on-pump technique. This meta-analysis compares these two surgical techniques with respect to causing acute kidney injury (AKI).This study searched for randomized controlled trials in MEDLINE and abstracts from the proceedings of scientific meetings through February 2010. Included were trials comparing off-pump to on-pump CABG that reported the incidence of AKI, as defined by a mixture of criteria including biochemical parameter/urine output/dialysis requirement. Mortality was evaluated among the studies that reported kidney-related outcomes. For primary and subgroup analyses, fixed-effect meta-analyses of odds ratios (OR) were performed.In 22 identified trials (4819 patients), the weighted incidence of AKI in the on-pump CABG group was 4.0% (95% confidence interval [CI] 1.8%, 8.5%), dialysis requirement 2.4% (95% CI 1.6%, 3.7%), and mortality 2.6% (95% CI 1.6%, 4.0%). By meta-analysis, off-pump CABG was associated with a 40% lower odds of postoperative AKI (OR 0.60; 95% CI 0.43, 0.84; P = 0.003) and a nonsignificant 33% lower odds for dialysis requirement (OR 0.67; 95% CI 0.40, 1.12; P = 0.12). Within the selected trials, off-pump CABG was not associated with a significant decrease in mortality.Off-pump CABG may be associated with a lower incidence of postoperative AKI but may not affect dialysis requirement, a serious complication of cardiac surgery. However, the different definitions of AKI used in individual trials and methodological concerns preclude definitive conclusions.