Search

Background Timely prediction of AKI in children can allow for targeted interventions, but the wealth of data in the electronic health record poses unique modeling challenges. Methods We retrospectively reviewed the electronic medical records of all children younger than 18 years old who had at least two creatinine values measured during a hospital admission from January 2014 through January 2018. We divided the study population into derivation, and internal and external validation cohorts, and used five feature selection techniques to select 10 of 720 potentially predictive variables from the electronic health records. Model performance was assessed by the area under the receiver operating characteristic curve in the validation cohorts. The primary outcome was development of AKI (per the Kidney Disease Improving Global Outcomes creatinine definition) within a moving 48-hour window. Secondary outcomes included severe AKI (stage 2 or 3), inpatient mortality, and length of stay. Results Among 8473 encounters studied, AKI occurred in 516 (10.2%), 207 (9%), and 27 (2.5%) encounters in the derivation, and internal and external validation cohorts, respectively. The highest-performing model used a machine learning-based genetic algorithm, with an overall receiver operating characteristic curve in the internal validation cohort of 0.76 [95% confidence interval (CI), 0.72 to 0.79] for AKI, 0.79 (95% CI, 0.74 to 0.83) for severe AKI, and 0.81 (95% CI, 0.77 to 0.86) for neonatal AKI. To translate this prediction model into a clinical risk-stratification tool, we identified high- and low-risk threshold points. Conclusions Using various machine learning algorithms, we identified and validated a time-updated prediction model of ten readily available electronic health record variables to accurately predict imminent AKI in hospitalized children.

Objective To determine whether surge conditions were associated with increased mortality. Design Multicenter cohort study. Setting U.S. ICUs participating in STOP-COVID. Patients Consecutive adults with COVID-19 admitted to participating ICUs between March 4 and July 1, 2020. Interventions None Measurements and Main Results The main outcome was 28-day in-hospital mortality. To assess the association between admission to an ICU during a surge period and mortality, we used two different strategies: (1) an inverse probability weighted difference-in-differences model limited to appropriately matched surge and non-surge patients and (2) a meta-regression of 50 multivariable difference-in-differences models (each based on sets of randomly matched surge- and non-surge hospitals). In the first analysis, we considered a single surge period for the cohort (March 23 – May 6). In the second, each surge hospital had its own surge period (which was compared to the same time periods in matched non-surge hospitals). Our cohort consisted of 4342 ICU patients (average age 60.8 [sd 14.8], 63.5% men) in 53 U.S. hospitals. Of these, 13 hospitals encountered surge conditions. In analysis 1, the increase in mortality seen during surge was not statistically significant (odds ratio [95% CI]: 1.30 [0.47-3.58], p = .6). In analysis 2, surge was associated with an increased odds of death (odds ratio 1.39 [95% CI, 1.34-1.43], p Conclusions Admission to an ICU with COVID-19 in a hospital that is experiencing surge conditions may be associated with an increased odds of death. Given the high incidence of COVID-19, such increases would translate into substantial excess mortality.

Background Hispanic persons living in the United States (U.S.) are at higher risk of infection and death from coronavirus disease 2019 (COVID-19) compared with non-Hispanic persons. Whether this disparity exists among critically ill patients with COVID-19 is unknown. Objective To evaluate ethnic disparities in mortality among critically ill adults with COVID-19 enrolled in the Study of the Treatment and Outcomes in Critically Ill Patients with COVID-19 (STOP-COVID). Methods Multicenter cohort study of adults with laboratory-confirmed COVID-19 admitted to intensive care units (ICU) at 67 U.S. hospitals from March 4 to May 9, 2020. Multilevel logistic regression was used to evaluate 28-day mortality across racial/ethnic groups. Results A total of 2153 patients were included (994 [46.2%] Hispanic and 1159 [53.8%] non-Hispanic White). The median (IQR) age was 62 (51–71) years (non-Hispanic White, 66 [57–74] years; Hispanic, 56 [46–67] years), and 1462 (67.9%) were men. Compared with non-Hispanic White patients, Hispanic patients were younger; were less likely to have hypertension, chronic obstructive pulmonary disease, coronary artery disease, or heart failure; and had longer duration of symptoms prior to ICU admission. During median (IQR) follow-up of 14 (7–24) days, 785 patients (36.5%) died. In analyses adjusted for age, sex, clinical characteristics, and hospital size, Hispanic patients had higher odds of death compared with non-Hispanic White patients (OR, 1.44; 95% CI, 1.12–1.84). Conclusions Among critically ill adults with COVID-19, Hispanic patients were more likely to die than non-Hispanic White patients, even though they were younger and had lower comorbidity burden. This finding highlights the need to provide earlier access to care to Hispanic individuals with COVID-19, especially given our finding of longer duration of symptoms prior to ICU admission among Hispanic patients. In addition, there is a critical need to address ongoing disparities in post hospital discharge care for patients with COVID-19.

Variation in hospital mortality has been described for coronavirus disease 2019 (COVID-19), but the factors that explain these differences remain unclear.Our objective was to utilize a large, nationally representative dataset of critically ill adults with COVID-19 to determine which factors explain mortality variability.In this multicenter cohort study, we examined adults hospitalized in intensive care units with COVID-19 at 70 United States hospitals between March and June 2020. The primary outcome was 28-day mortality. We examined patient-level and hospital-level variables. Mixed-effects logistic regression was used to identify factors associated with interhospital variation. The median odds ratio (OR) was calculated to compare outcomes in higher- vs. lower-mortality hospitals. A gradient boosted machine algorithm was developed for individual-level mortality models.A total of 4,019 patients were included, 1537 (38%) of whom died by 28 days. Mortality varied considerably across hospitals (0-82%). After adjustment for patient- and hospital-level domains, interhospital variation was attenuated (OR decline from 2.06 [95% CI, 1.73-2.37] to 1.22 [95% CI, 1.00-1.38]), with the greatest changes occurring with adjustment for acute physiology, socioeconomic status, and strain. For individual patients, the relative contribution of each domain to mortality risk was: acute physiology (49%), demographics and comorbidities (20%), socioeconomic status (12%), strain (9%), hospital quality (8%), and treatments (3%).There is considerable interhospital variation in mortality for critically ill patients with COVID-19, which is mostly explained by hospital-level socioeconomic status, strain, and acute physiologic differences. Individual mortality is driven mostly by patient-level factors. This article is open access and distributed under the terms of the Creative Commons Attribution Non-Commercial No Derivatives License 4.0 (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Rationale and objective While COVID-19 infection has been associated with acute kidney injury (AKI), it is unclear whether this association is independent of traditional risk factors such as hypotension, nephrotoxin exposure, and inflammation. We tested the independent association of COVID-19 with AKI. Study Design Multicenter, observational, cohort study. Setting and participants Patients admitted to one of six hospitals within the Yale-New Haven Health System between 3/10/2020 and 8/31/2020 and tested for SARS-CoV-2 via nasopharyngeal PCR test. Exposure Positive test for SARS-CoV-2. Outcome AKI by Kidney Disease: Improving Global Outcomes criteria. Analytic approach Evaluated the association of COVID-19 with AKI after controlling for time-invariant factors at admission (e.g., demographics, comorbidities) and time-varying factors updated continuously during hospitalization (e.g., vital signs, medications, laboratory results, respiratory failure) using time-updated Cox proportional hazard models. Results Of the 22,122 patients hospitalized between, 2,600 tested positive and 19,522 tested negative for SARS-CoV-2. Compared to patients who tested negative, patients with COVID-19 had more AKI [30.6% vs. 18.2%, absolute risk difference 12.5 (95% CI, 10.6, 14.3)%] and dialysis-requiring AKI (8.5% vs. 3.6%) and lower recovery from AKI (58% vs. 69.8%]. Compared to patients who tested negative, patients with COVID-19 had higher inflammatory markers (C-reactive protein, ferritin), and greater use of vasopressors and diuretics. Compared to patients who tested negative, patients with COVID-19 had higher rate of AKI in univariable analysis (HR, 1.84 [1.73, 1.95]). In fully adjusted model controlling for demographics, comorbidities, vital signs, medications, and laboratory results, COVID-19 remained associated with a high rate of AKI (adjusted HR, 1.40 [1.29-1.53]). Limitations Possibility of residual confounding. Conclusions COVID-19 is associated with high rates of AKI not fully explained by adjustment for known risk factors. This suggests the presence of mechanisms of AKI not accounted for in this analysis, which may include a direct effect of COVID-19 on the kidney or other unmeasured mediators. Future studies should evaluate the possible unique pathways by which COVID-19 may cause AKI., One-third of patients hospitalized with COVID-19 experience acute kidney injury (AKI), which is higher than in other hospitalized patients. Patients with COVID-19 carry many well-known risk factors for AKI including severe lung disease requiring mechanical ventilation, shock and significant inflammation. Whether higher rates of AKI in COVID-19 are above what could be expected in patients with similar risk factors is unknown. We compared AKI rates between those with and without COVID-19 after controlling for risk factors for AKI both before and during hospitalization. We found that COVID-19 was independently associated with high rates of AKI. This indicates that some of the AKI risk in patients with COVID-19 is unexplained by traditional AKI risk factors and is unique to this disease.

Summary: Many US states published crisis standards of care (CSC) guidelines for allocating scarce critical care resources during the COVID-19 pandemic. However, the performance of these guidelines in maximizing their population benefit has not been well tested. In 2,272 adults with COVID-19 requiring mechanical ventilation drawn from the Study of the Treatment and Outcomes in Critically Ill Patients with COVID-19 (STOP-COVID) multicenter cohort, we test the following three approaches to CSC algorithms: Sequential Organ Failure Assessment (SOFA) scores grouped into ranges, SOFA score ranges plus comorbidities, and a hypothetical approach using raw SOFA scores not grouped into ranges. We find that area under receiver operating characteristic (AUROC) curves for all three algorithms demonstrate only modest discrimination for 28-day mortality. Adding comorbidity scoring modestly improves algorithm performance over SOFA scores alone. The algorithm incorporating comorbidities has modestly worse predictive performance for Black compared to white patients. CSC algorithms should be empirically examined to refine approaches to the allocation of scarce resources during pandemics and to avoid potential exacerbation of racial inequities.

Objectives Therapies for patients with respiratory failure from coronavirus disease 2019 are urgently needed. Early implementation of prone positioning ventilation improves survival in patients with acute respiratory distress syndrome, but studies examining the effect of proning on survival in patients with coronavirus disease 2019 are lacking. Our objective was to estimate the effect of early proning initiation on survival in patients with coronavirus disease 2019-associated respiratory failure. Design Data were derived from the Study of the Treatment and Outcomes in Critically Ill Patients with coronavirus disease 2019, a multicenter cohort study of critically ill adults with coronavirus disease 2019 admitted to 68 U.S. hospitals. Using these data, we emulated a target trial of prone positioning ventilation by categorizing mechanically ventilated hypoxemic (ratio of PaO2 over the corresponding FIO2 ≤ 200 mm Hg) patients as having been initiated on proning or not within 2 days of ICU admission. We fit an inverse probability-weighted Cox model to estimate the mortality hazard ratio for early proning versus no early proning. Patients were followed until death, hospital discharge, or end of follow-up. Setting ICUs at 68 U.S. sites. Patients Critically ill adults with laboratory-confirmed coronavirus disease 2019 receiving invasive mechanical ventilation with ratio of PaO2 over the corresponding FIO2 less than or equal to 200 mm Hg. Interventions None. Measurements and main results Among 2,338 eligible patients, 702 (30.0%) were proned within the first 2 days of ICU admission. After inverse probability weighting, baseline and severity of illness characteristics were well-balanced between groups. A total of 1,017 (43.5%) of the 2,338 patients were discharged alive, 1,101 (47.1%) died, and 220 (9.4%) were still hospitalized at last follow-up. Patients proned within the first 2 days of ICU admission had a lower adjusted risk of death compared with nonproned patients (hazard ratio, 0.84; 95% CI, 0.73-0.97). Conclusions In-hospital mortality was lower in mechanically ventilated hypoxemic patients with coronavirus disease 2019 treated with early proning compared with patients whose treatment did not include early proning.

Hypercoagulability may be a key mechanism of death in patients with COVID-19. This cohort study evaluated the incidence of venous thromboembolism and major bleeding in critically ill patients with COVID-19 and examined the observational effect of early therapeutic anticoagulation on survival., Visual Abstract. Early Anticoagulation in COVID-19 Hypercoagulability may be a key mechanism of death in patients with COVID-19. This cohort study evaluated the incidence of venous thromboembolism and major bleeding in critically ill patients with COVID-19 and examined the observational effect of early therapeutic anticoagulation on survival. Visual Abstract. Early Anticoagulation in COVID-19 Hypercoagulability may be a key mechanism of death in patients with COVID-19. This cohort study evaluated the incidence of venous thromboembolism and major bleeding in critically ill patients with COVID-19 and examined the observational effect of early therapeutic anticoagulation on survival., Background: Hypercoagulability may be a key mechanism of death in patients with coronavirus disease 2019 (COVID-19). Objective: To evaluate the incidence of venous thromboembolism (VTE) and major bleeding in critically ill patients with COVID-19 and examine the observational effect of early therapeutic anticoagulation on survival. Design: In a multicenter cohort study of 3239 critically ill adults with COVID-19, the incidence of VTE and major bleeding within 14 days after intensive care unit (ICU) admission was evaluated. A target trial emulation in which patients were categorized according to receipt or no receipt of therapeutic anticoagulation in the first 2 days of ICU admission was done to examine the observational effect of early therapeutic anticoagulation on survival. A Cox model with inverse probability weighting to adjust for confounding was used. Setting: 67 hospitals in the United States. Participants: Adults with COVID-19 admitted to a participating ICU. Measurements: Time to death, censored at hospital discharge, or date of last follow-up. Results: Among the 3239 patients included, the median age was 61 years (interquartile range, 53 to 71 years), and 2088 (64.5%) were men. A total of 204 patients (6.3%) developed VTE, and 90 patients (2.8%) developed a major bleeding event. Independent predictors of VTE were male sex and higher D-dimer level on ICU admission. Among the 2809 patients included in the target trial emulation, 384 (11.9%) received early therapeutic anticoagulation. In the primary analysis, during a median follow-up of 27 days, patients who received early therapeutic anticoagulation had a similar risk for death as those who did not (hazard ratio, 1.12 [95% CI, 0.92 to 1.35]). Limitation: Observational design. Conclusion: Among critically ill adults with COVID-19, early therapeutic anticoagulation did not affect survival in the target trial emulation. Primary Funding Source: None.

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 .

Background AKI is a common sequela of coronavirus disease 2019 (COVID-19). However, few studies have focused on AKI treated with RRT (AKI-RRT). Methods We conducted a multicenter cohort study of 3099 critically ill adults with COVID-19 admitted to intensive care units (ICUs) at 67 hospitals across the United States. We used multivariable logistic regression to identify patient-and hospital-level risk factors for AKI-RRT and to examine risk factors for 28-day mortality among such patients. Results A total of 637 of 3099 patients (20.6%) developed AKI-RRT within 14 days of ICU admission, 350 of whom (54.9%) died within 28 days of ICU admission. Patient-level risk factors for AKI-RRT included CKD, men, non-White race, hypertension, diabetes mellitus, higher body mass index, higher d-dimer, and greater severity of hypoxemia on ICU admission. Predictors of 28-day mortality in patients with AKI-RRT were older age, severe oliguria, and admission to a hospital with fewer ICU beds or one with greater regional density of COVID-19. At the end of a median follow-up of 17 days (range, 1-123 days), 403 of the 637 patients (63.3%) with AKI-RRT had died, 216 (33.9%) were discharged, and 18 (2.8%) remained hospitalized. Of the 216 patients discharged, 73 (33.8%) remained RRT dependent at discharge, and 39 (18.1%) remained RRT dependent 60 days after ICU admission. Conclusions AKI-RRT is common among critically ill patients with COVID-19 and is associated with a hospital mortality rate of >60%. Among those who survive to discharge, one in three still depends on RRT at discharge, and one in six remains RRT dependent 60 days after ICU admission.

RATIONALE & OBJECTIVE: Acute kidney injury (AKI) is diagnosed based on changes in serum creatinine concentration, a late marker of this syndrome. Algorithms that predict elevated risk for AKI are of great interest, but no studies have incorporated such an algorithm into the electronic health record to assist with clinical care. We describe the experience of implementing such an algorithm. STUDY DESIGN: Prospective observational cohort study. SETTING & PARTICIPANTS: 2,856 hospitalized adults in a single urban tertiary-care hospital with an algorithm-predicted risk for AKI in the next 24 hours >15%. Alerts were also used to target a convenience sample of 100 patients for measurement of 16 urine and 6 blood biomarkers. EXPOSURE: Clinical characteristics at the time of pre-AKI alert. OUTCOME: AKI within 24 hours of pre-AKI alert (AKI(24)). ANALYTICAL APPROACH: Descriptive statistics and univariable associations. RESULTS: At enrollment, mean predicted probability of AKI(24) was 19.1%; 18.9% of patients went on to develop AKI(24). Outcomes were generally poor among this population, with 29% inpatient mortality among those who developed AKI(24) and 14% among those who did not (P < 0.001). Systolic blood pressure < 100 mm Hg (28% of patients with AKI(24) vs 18% without), heart rate > 100 beats/min (32% of patients with AKI(24) vs 24% without), and oxygen saturation < 92% (15% of patients with AKI(24) vs 6% without) were all more common among those who developed AKI(24). Of all biomarkers measured, only hyaline casts on urine microscopy (72% of patients with AKI(24) vs 25% without) and fractional excretion of urea nitrogen (20% [IQR, 12%−36%] among patients with AKI(24) vs 34% [IQR, 25%−44%] without) differed between those who did and did not develop AKI(24). LIMITATIONS: Single-center study, reliance on serum creatinine level for AKI diagnosis, small number of patients undergoing biomarker evaluation. CONCLUSIONS: A real-time AKI risk model was successfully integrated into the EHR.

Background and objectives Electronic 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, & measurements This 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. Results The 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. Conclusions Uplift modeling, which accounts for treatment effect, can successfully target electronic alerts for AKI to those most likely to benefit, whereas purely prognostic targeting cannot.

Background Acute kidney injury (AKI) is an adverse event that carries significant morbidity. Given that interventions after AKI occurrence have poor performance, there is substantial interest in prediction of AKI prior to its diagnosis. However, integration of real-time prognostic modeling into the electronic health record (EHR) has been challenging, as complex models increase the risk of error and complicate deployment. Our goal in this study was to create an implementable predictive model to accurately predict AKI in hospitalized patients and could be easily integrated within an existing EHR system. Methods and findings We performed a retrospective analysis looking at data of 169,859 hospitalized adults admitted to one of three study hospitals in the United States (in New Haven and Bridgeport, Connecticut) from December 2012 to February 2016. Demographics, medical comorbidities, hospital procedures, medications, and laboratory data were used to develop a model to predict AKI within 24 hours of a given observation. Outcomes of AKI severity, requirement for renal replacement therapy, and mortality were also measured and predicted. Models were trained using discrete-time logistic regression in a subset of Hospital 1, internally validated in the remainder of Hospital 1, and externally validated in Hospital 2 and Hospital 3. Model performance was assessed via the area under the receiver-operator characteristic (ROC) curve (AUC). The training set cohort contained 60,701 patients, and the internal validation set contained 30,599 patients. External validation data sets contained 43,534 and 35,025 patients. Patients in the overall cohort were generally older (median age ranging from 61 to 68 across hospitals); 44%–49% were male, 16%–20% were black, and 23%–29% were admitted to surgical wards. In the training set and external validation set, 19.1% and 18.9% of patients, respectively, developed AKI. The full model, including all covariates, had good ability to predict imminent AKI for the validation set, sustained AKI, dialysis, and death with AUCs of 0.74 (95% CI 0.73–0.74), 0.77 (95% CI 0.76–0.78), 0.79 (95% CI 0.73–0.85), and 0.69 (95% CI 0.67–0.72), respectively. A simple model using only readily available, time-updated laboratory values had very similar predictive performance to the complete model. The main limitation of this study is that it is observational in nature; thus, we are unable to conclude a causal relationship between covariates and AKI and do not provide an optimal treatment strategy for those predicted to develop AKI. Conclusions In this study, we observed that a simple model using readily available laboratory data could be developed to predict imminent AKI with good discrimination. This model may lend itself well to integration into the EHR without sacrificing the performance seen in more complex models., Michael Simonov and colleagues present a model for predicting acute kidney disease using electronic data records., Author summary Why was this study done? Acute kidney injury (AKI) is an adverse event associated with significant morbidity and healthcare costs. Treatments for AKI are generally poor and largely supportive; thus, there has been a focus on early identification and prevention of AKI. There has been growing interest in harnessing electronic health data for the prediction of AKI in hospitalized patients. What did the researchers do and find? We developed a mathematical model that predicts which patients would develop AKI for 169,859 patients observed at three hospitals in the US (specifically in New Haven and Bridgeport, Connecticut) between 2012 and 2016. The model included several elements about the patients, including demographics, medical history, and bloodwork. The model was able to provide a good prediction for patients who would develop AKI and was also able to predict with fair discrimination whether the patient would need dialysis or whether they would die in the hospital. What do these findings mean? This model could be readily implemented on an electronic health record (EHR) to alert or caution healthcare providers of their patient’s risk for developing AKI and provide guided decision support to best help prevent this adverse event. In the future, there could be a study evaluating different interventions randomized to individual patients at high risk for developing AKI as per the model. This strategy could develop novel therapies for the prevention of AKI.

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.