Dataset Information

Electronic health record alerts for acute kidney injury: multicenter, randomized clinical trial.

ABSTRACT:

Objective

To determine whether electronic health record alerts for acute kidney injury would improve patient outcomes of mortality, dialysis, and progression of acute kidney injury.

Design

Double blinded, multicenter, parallel, randomized controlled trial.

Setting

Six hospitals (four teaching and two non-teaching) in the Yale New Haven Health System in Connecticut and Rhode Island, US, ranging from small community hospitals to large tertiary care centers.

Participants

6030 adult inpatients with acute kidney injury, as defined by the Kidney Disease: Improving Global Outcomes (KDIGO) creatinine criteria.

Interventions

An electronic health record based "pop-up" alert for acute kidney injury with an associated acute kidney injury order set upon provider opening of the patient's medical record.

Main outcome measures

A composite of progression of acute kidney injury, receipt of dialysis, or death within 14 days of randomization. Prespecified secondary outcomes included outcomes at each hospital and frequency of various care practices for acute kidney injury.

Results

6030 patients were randomized over 22 months. The primary outcome occurred in 653 (21.3%) of 3059 patients with an alert and in 622 (20.9%) of 2971 patients receiving usual care (relative risk 1.02, 95% confidence interval 0.93 to 1.13, P=0.67). Analysis by each hospital showed worse outcomes in the two non-teaching hospitals (n=765, 13%), where alerts were associated with a higher risk of the primary outcome (relative risk 1.49, 95% confidence interval 1.12 to 1.98, P=0.006). More deaths occurred at these centers (15.6% in the alert group v 8.6% in the usual care group, P=0.003). Certain acute kidney injury care practices were increased in the alert group but did not appear to mediate these outcomes.

Conclusions

Alerts did not reduce the risk of our primary outcome among patients in hospital with acute kidney injury. The heterogeneity of effect across clinical centers should lead to a re-evaluation of existing alerting systems for acute kidney injury.

Trial registration

ClinicalTrials.gov NCT02753751.

SUBMITTER: Wilson FP

PROVIDER: S-EPMC8034420 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAcute kidney injury is common in hospitalized patients, increases morbidity and mortality, and is under-recognized. To improve provider recognition, we previously developed an electronic alert system for acute kidney injury. To test the hypothesis that this electronic acute kidney injury alert could improve patient outcome, we designed a randomized controlled trial to test the effectiveness of this alert in hospitalized patients. The study design presented several methodologic, ethical, and statistical challenges.PurposeTo highlight the challenges faced and the solutions employed in the design and implementation of a clinical trial to determine whether the provision of an early electronic alert for acute kidney injury would improve outcomes in hospitalized patients. Challenges included how to randomize the delivery of the alert system and the ethical framework for waiving informed consent. Other methodologic challenges included the selection and statistical evaluation of our study outcome, a ranked-composite of a continuous covariate (creatinine) and two dichotomous outcomes (dialysis and death), and the use of the medical record as a source of trial data.MethodsWe have designed a randomized trial to assess the effectiveness of an electronic alert system for acute kidney injury. With broad inclusion criteria, and a waiver of informed consent, we enroll and randomize virtually every patient with acute kidney injury in our hospital.ResultsAs of 31 March 2014, we have enrolled 2373 patients of 2400 targeted. Pre-alert data demonstrated a strong association between severity of acute kidney injury and inpatient mortality with a range of 6.4% in those with mild, stage 1 acute kidney injury, to 29% among those with stage 3 acute kidney injury (p < 0.001). We judged that informed consent would undermine the scientific validity of the study and present harms that are out of proportion to the very low risk intervention.ConclusionOur study demonstrates the feasibility of designing an ethical randomized controlled trial of an early electronic alert for acute kidney injury without obtaining informed consent from individual participants. Our study outcome may serve as a model for other studies of acute kidney injury, insofar as our paradigm accounts for the effect that early death and dialysis have on assessment of acute kidney injury severity as defined by maximum achieved serum creatinine.

Project description:BACKGROUND:Acute kidney injury often goes unrecognised in its early stages when effective treatment options might be available. We aimed to determine whether an automated electronic alert for acute kidney injury would reduce the severity of such injury and improve clinical outcomes in patients in hospital. METHODS:In this investigator-masked, parallel-group, randomised controlled trial, patients were recruited from the hospital of the University of Pennsylvania in Philadelphia, PA, USA. Eligible participants were adults aged 18 years or older who were in hospital with stage 1 or greater acute kidney injury as defined by Kidney Disease Improving Global Outcomes creatinine-based criteria. Exclusion criteria were initial hospital creatinine 4·0 mg/dL (to convert to ?mol/L, multiply by 88·4) or greater, fewer than two creatinine values measured, inability to determine the covering provider, admission to hospice or the observation unit, previous randomisation, or end-stage renal disease. Patients were randomly assigned (1:1) via a computer-generated sequence to receive an acute kidney injury alert (a text-based alert sent to the covering provider and unit pharmacist indicating new acute kidney injury) or usual care, stratified by medical versus surgical admission and intensive care unit versus non-intensive care unit location in blocks of 4-8 participants. The primary outcome was a composite of relative maximum change in creatinine, dialysis, and death at 7 days after randomisation. All analyses were by intention to treat. This study is registered with ClinicalTrials.gov, number NCT01862419. FINDINGS:Between Sept 17, 2013, and April 14, 2014, 23,664 patients were screened. 1201 eligible participants were assigned to the acute kidney injury alert group and 1192 were assigned to the usual care group. Composite relative maximum change in creatinine, dialysis, and death at 7 days did not differ between the alert group and the usual care group (p=0·88), or within any of the four randomisation strata (all p>0·05). At 7 days after randomisation, median maximum relative change in creatinine concentrations was 0·0% (IQR 0·0-18·4) in the alert group and 0·6% (0·0-17·5) in the usual care group (p=0·81); 87 (7·2%) patients in the alert group and 70 (5·9%) patients in usual care group had received dialysis (odds ratio 1·25 [95% CI 0·90-1·74]; p=0·18); and 71 (5·9%) patients in the alert group and 61 (5·1%) patients in the usual care group had died (1·16 [0·81-1·68]; p=0·40). INTERPRETATION:An electronic alert system for acute kidney injury did not improve clinical outcomes among patients in hospital. FUNDING:Penn Center for Healthcare Improvement and Patient Safety.

Project description:IntroductionAcute kidney injury (AKI) is common among hospitalised patients and under-recognised by providers and yet carries a significant risk of morbidity and mortality. Electronic alerts for AKI have become more common despite a lack of strong evidence of their benefits. We designed a multicentre, randomised, controlled trial to evaluate the effectiveness of AKI alerts. Our aim is to highlight several challenges faced in the design of this trial, which uses electronic screening, enrolment, randomisation, intervention and data collection.Methods and analysisThe design and implementation of an electronic alert system for AKI was a reiterative process involving several challenges and limitations set by the confines of the electronic medical record system. The trial will electronically identify and randomise 6030 adults with AKI at six hospitals over a 1.5-2 year period to usual care versus an electronic alert containing an AKI-specific order set. Our primary outcome will be a composite of AKI progression, inpatient dialysis and inpatient death within 14 days of randomisation. During a 1-month pilot in the medical intensive care unit of Yale New Haven Hospital, we have demonstrated feasibility of automating enrolment and data collection. Feedback from providers exposed to the alerts was used to continually improve alert clarity, user friendliness and alert specificity through refined inclusion and exclusion criteria.Ethics and disseminationThis study has been approved by the appropriate ethics committees for each of our study sites. Our study qualified for a waiver of informed consent as it presents no more than minimal risk and cannot be feasibly conducted in the absence of a waiver. We are committed to open dissemination of our data through clinicaltrials.gov and submission of results to the NIH data sharing repository. Results of our trial will be submitted for publication in a peer-reviewed journal.Trial registration numberNCT02753751; Pre-results.

Project description:Background and objectivesElectronic alerts for heterogenous conditions such as AKI may not provide benefit for all eligible patients and can lead to alert fatigue, suggesting that personalized alert targeting may be useful. Uplift-based alert targeting may be superior to purely prognostic-targeting of interventions because uplift models assess marginal treatment effect rather than likelihood of outcome.Design, setting, participants, & measurementsThis is a secondary analysis of a clinical trial of 2278 adult patients with AKI randomized to an automated, electronic alert system versus usual care. We used three uplift algorithms and one purely prognostic algorithm, trained in 70% of the data, and evaluated the effect of targeting alerts to patients with higher scores in the held-out 30% of the data. The performance of the targeting strategy was assessed as the interaction between the model prediction of likelihood to benefit from alerts and randomization status. The outcome of interest was maximum relative change in creatinine from the time of randomization to 3 days after randomization.ResultsThe three uplift score algorithms all gave rise to a significant interaction term, suggesting that a strategy of targeting individuals with higher uplift scores would lead to a beneficial effect of AKI alerting, in contrast to the null effect seen in the overall study. The prognostic model did not successfully stratify patients with regards to benefit of the intervention. Among individuals in the high uplift group, alerting was associated with a median reduction in change in creatinine of -5.3% (P=0.03). In the low uplift group, alerting was associated with a median increase in change in creatinine of +5.3% (P=0.005). Older individuals, women, and those with a lower randomization creatinine were more likely to receive high uplift scores, suggesting that alerts may benefit those with more slowly developing AKI.ConclusionsUplift modeling, which accounts for treatment effect, can successfully target electronic alerts for AKI to those most likely to benefit, whereas purely prognostic targeting cannot.

Project description:BackgroundA major problem in treating acute kidney injury (AKI) is that clinical criteria for recognition are markers of established kidney damage or impaired function; treatment before such damage manifests is desirable. Clinicians could intervene during what may be a crucial stage for preventing permanent kidney injury if patients with incipient AKI and those at high risk of developing AKI could be identified.ObjectiveIn this study, we evaluate a machine learning algorithm for early detection and prediction of AKI.DesignWe used a machine learning technique, boosted ensembles of decision trees, to train an AKI prediction tool on retrospective data taken from more than 300 000 inpatient encounters.SettingData were collected from inpatient wards at Stanford Medical Center and intensive care unit patients at Beth Israel Deaconess Medical Center.PatientsPatients older than the age of 18 whose hospital stays lasted between 5 and 1000 hours and who had at least one documented measurement of heart rate, respiratory rate, temperature, serum creatinine (SCr), and Glasgow Coma Scale (GCS).MeasurementsWe tested the algorithm's ability to detect AKI at onset and to predict AKI 12, 24, 48, and 72 hours before onset.MethodsWe tested AKI detection and prediction using the National Health Service (NHS) England AKI Algorithm as a gold standard. We additionally tested the algorithm's ability to detect AKI as defined by the Kidney Disease: Improving Global Outcomes (KDIGO) guidelines. We compared the algorithm's 3-fold cross-validation performance to the Sequential Organ Failure Assessment (SOFA) score for AKI identification in terms of area under the receiver operating characteristic (AUROC).ResultsThe algorithm demonstrated high AUROC for detecting and predicting NHS-defined AKI at all tested time points. The algorithm achieves AUROC of 0.872 (95% confidence interval [CI], 0.867-0.878) for AKI detection at time of onset. For prediction 12 hours before onset, the algorithm achieves an AUROC of 0.800 (95% CI, 0.792-0.809). For 24-hour predictions, the algorithm achieves AUROC of 0.795 (95% CI, 0.785-0.804). For 48-hour and 72-hour predictions, the algorithm achieves AUROC values of 0.761 (95% CI, 0.753-0.768) and 0.728 (95% CI, 0.719-0.737), respectively.LimitationsBecause of the retrospective nature of this study, we cannot draw any conclusions about the impact the algorithm's predictions will have on patient outcomes in a clinical setting.ConclusionsThe results of these experiments suggest that a machine learning-based AKI prediction tool may offer important prognostic capabilities for determining which patients are likely to suffer AKI, potentially allowing clinicians to intervene before kidney damage manifests.