Dataset Information

Electronic health records accurately predict renal replacement therapy in acute kidney injury.

ABSTRACT: BACKGROUND:Electronic health records (EHR) detect the onset of acute kidney injury (AKI) in hospitalized patients, and may identify those at highest risk of mortality and renal replacement therapy (RRT), for earlier targeted intervention. METHODS:Prospective observational study to derive prediction models for hospital mortality and RRT, in inpatients aged ?18?years with AKI detected by EHR over 1 year in a tertiary institution, fulfilling modified KDIGO criterion based on serial serum creatinine (sCr) measures. RESULTS:We studied 3333 patients with AKI, of 77,873 unique patient admissions, giving an AKI incidence of 4%. KDIGO AKI stages at detection were 1(74%), 2(15%), 3(10%); corresponding peak AKI staging in hospital were 61, 20, 19%. 392 patients (12%) died, and 174 (5%) received RRT. Multivariate logistic regression identified AKI onset in ICU, haematological malignancy, higher delta sCr (sCr rise from AKI detection till peak), higher serum potassium and baseline eGFR, as independent predictors of both mortality and RRT. Additionally, older age, higher serum urea, pneumonia and intraabdominal infections, acute cardiac diseases, solid organ malignancy, cerebrovascular disease, current need for RRT and admission under a medical specialty predicted mortality. The AUROC for RRT prediction was 0.94, averaging 0.93 after 10-fold cross-validation. Corresponding AUROC for mortality prediction was 0.9 and 0.9 after validation. Decision tree analysis for RRT prediction achieved a balanced accuracy of 70.4%, and identified delta-sCr???148??mol/L as the key factor that predicted RRT. CONCLUSION:Case fatality was high with significant renal deterioration following hospital-wide AKI. EHR clinical model was highly accurate for both RRT prediction and for mortality; allowing excellent risk-stratification with potential for real-time deployment.

SUBMITTER: Low S

PROVIDER: S-EPMC6357378 | biostudies-literature | 2019 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Electronic health records accurately predict renal replacement therapy in acute kidney injury.

Low Sanmay S Vathsala Anantharaman A Murali Tanusya Murali TM Pang Long L MacLaren Graeme G Ng Wan-Ying WY Haroon Sabrina S Mukhopadhyay Amartya A Lim Shir-Lynn SL Tan Bee-Hong BH Lau Titus T Chua Horng-Ruey HR

BMC nephrology 20190131 1

<h4>Background</h4>Electronic health records (EHR) detect the onset of acute kidney injury (AKI) in hospitalized patients, and may identify those at highest risk of mortality and renal replacement therapy (RRT), for earlier targeted intervention.<h4>Methods</h4>Prospective observational study to derive prediction models for hospital mortality and RRT, in inpatients aged ≥18 years with AKI detected by EHR over 1 year in a tertiary institution, fulfilling modified KDIGO criterion based on serial s ...[more]

PMID: 30704418

Similar Datasets

Project description:Recent data indicate AKI is very common among hospitalized Chinese patients and continuous renal replacement therapy (CRRT) is increasingly offered for treatment. However, only anecdotal information regarding CRRT's use in relation to other modalities and the specific manner in which it is prescribed exists currently. This report summarizes the results of a comprehensive physician survey designed to characterize contemporary dialytic management of AKI patients in China, especially with respect to the utilization of CRRT. The survey queried both nephrologists and critical care physicians across a wide spectrum of hospitals about factors influencing initial RRT modality selection, especially patient clinical characteristics and willingness to receive RRT, treatment location, and institutional capabilities. For patients initially treated with CRRT, data related to indication, timing of treatment initiation, dose, anticoagulation technique, and duration of therapy were also collected. Among AKI patients considered RRT candidates, the survey indicated 15.1% (95% CI, 12.3%-17.9%) did not actually receive dialysis at Chinese hospitals. The finding was largely attributed to prohibitively high therapy costs in the view of patients or their families. The survey confirmed the dichotomy in RRT delivery in China, occurring both in the nephrology department (with nephrologists responsible) and the intensive care unit (with critical care physicians responsible). For all patients who were offered and received RRT, the survey participants reported 63.9% (56.4%-71.3%) were treated initially with CRRT and 24.8% (19.2%-30.3%) with intermittent hemodialysis (HD) (P<0.001). The mean percentage of patients considered hemodynamically unstable at RRT initiation was 36.2% (31.3%-41.1%), although this figure was two-fold higher in patients treated initially with CRRT (43.1%; 35.8%-50.4%) in comparison to those initially treated with HD (22.4%; 16.4%-28.4%)(P<0.001). An overwhelming majority of intensive care patients were treated initially with CRRT (86.6%; 79.8-93.4%) while it was the initial modality in only 44.6% (33.5-55.7%) of patients treated in a nephrology department (P<0.001). Approximately 70% of respondents overall reported prescribing a CRRT dose in the range of 20-30 mL/kg/hr while approximately 20% of prescriptions fell above this range. Daily prescribed therapy duration demonstrated a marked divergence from values reported in the literature and standard clinical practice. Overall, the most common average prescribed value (50% of respondents) fell in the 10-20 hr range, with only 18% in the 20-24 hr range. Moreover, 32% of respondents reported an average prescribed value of less than 10 hrs per day. While the percentages for the 10-20 hrs range were essentially the same for nephrology and ICU programs, a daily duration of less than 10 hrs was much more common in nephrology programs (48.0%; 38.3%-57.9%) versus ICU programs (16%; 10.0%-24.6%)(P<0.001). Our analysis demonstrates both similarities and differences between RRT practices for AKI in China and those in the developed world. While some differences are driven by non-medical factors, future studies should explore these issues further as Chinese RRT practices are harmonized with those in the rest of the world.

Project description:IntroductionThe optimal dialysis dose for the treatment of acute kidney injury (AKI) is controversial. We sought to evaluate the relationship between renal replacement therapy (RRT) dose and outcome.MethodsWe performed a prospective multicentre observational study in 30 intensive care units (ICUs) in eight countries from June 2005 to December 2007. Delivered RRT dose was calculated in patients treated exclusively with either continuous RRT (CRRT) or intermittent RRT (IRRT) during their ICU stay. Dose was categorised into more-intensive (CRRT >or= 35 ml/kg/hour, IRRT >or= 6 sessions/week) or less-intensive (CRRT < 35 ml/kg/hour, IRRT < 6 sessions/week). The main outcome measures were ICU mortality, ICU length of stay and duration of mechanical ventilation.ResultsOf 15,200 critically ill patients admitted during the study period, 553 AKI patients were treated with RRT, including 338 who received CRRT only and 87 who received IRRT only. For CRRT, the median delivered dose was 27.1 ml/kg/hour (interquartile range (IQR) = 22.1 to 33.9). For IRRT, the median dose was 7 sessions/week (IQR = 5 to 7). Only 22% of CRRT patients and 64% of IRRT patients received a more-intensive dose. Crude ICU mortality among CRRT patients were 60.8% vs. 52.5% (more-intensive vs. less-intensive groups, respectively). In IRRT, this was 23.6 vs. 19.4%, respectively. On multivariable analysis, there was no significant association between RRT dose and ICU mortality (Odds ratio (OR) more-intensive vs. less-intensive: CRRT OR = 1.21, 95% confidence interval (CI) = 0.66 to 2.21; IRRT OR = 1.50, 95% CI = 0.48 to 4.67). Among survivors, shorter ICU stay and duration of mechanical ventilation were observed in the more-intensive RRT groups (more-intensive vs. less-intensive for all: CRRT (median): 15 (IQR = 8 to 26) vs. 19.5 (IQR = 12 to 33.5) ICU days, P = 0.063; 7 (IQR = 4 to 17) vs. 14 (IQR = 5 to 24) ventilation days, P = 0.031; IRRT: 8 (IQR = 5.5 to 14) vs. 18 (IQR = 13 to 35) ICU days, P = 0.008; 2.5 (IQR = 0 to 10) vs. 12 (IQR = 3 to 24) ventilation days, P = 0.026).ConclusionsAfter adjustment for multiple variables, these data provide no evidence for a survival benefit afforded by higher dose RRT. However, more-intensive RRT was associated with a favourable effect on ICU stay and duration of mechanical ventilation among survivors. This result warrants further exploration.Trial registrationCochrane Renal Group (CRG110600093).

Dataset Information

Electronic health records accurately predict renal replacement therapy in acute kidney injury.

Publications

Electronic health records accurately predict renal replacement therapy in acute kidney injury.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets