Impact of Electronic Acute Kidney Injury (AKI) Alerts With Automated Nephrologist Consultation on Detection and Severity of AKI: A Quality Improvement Study

Severe acute kidney injury in COVID-19 patients is associated with in-hospital mortality

Although the lungs are major targets for COVID-19 invasion, other organs-such as the kidneys-are also affected. However, the renal complications of COVID-19 are not yet well explored. This study aimed to identify the incidence of acute kidney injury (AKI) in patients with COVID-19 and to evaluate its impact on patient outcomes. This retrospective study included 704 patients with COVID-19 who were hospitalized at two hospitals in Daegu, Korea from February 19 to March 31, 2020. AKI was defined according to the serum creatinine criteria in the Kidney Disease: Improving Global Outcomes (KDIGO) guidelines. The final date of follow-up was May 1, 2020. Of the 704 patients, 28 (4.0%) developed AKI. Of the 28 patients with AKI, 15 (53.6%) were found to have AKI stage 1, 3 (10.7%) had AKI stage 2, and 10 (35.7%) had AKI stage 3. Among these patients, 12 (42.9%) recovered from AKI. In the patients with AKI, the rates of admission to intensive care unit (ICU), administration of mechanical ventilator (MV), and in-hospital mortality were significantly higher than in patients without AKI. Multivariable analysis revealed that old age (Hazard ratio [HR] = 4.668, 95% confidence interval [CI] = 1.250-17.430, p = 0.022), high neutrophil-to-lymphocyte ratio (HR = 1.167, 95% CI = 1.078-1.264, p < 0.001), elevated creatinine kinase (HR = 1.002, 95% CI = 1.001-1.004, p = 0.007), and severe AKI (HR = 12.199, 95% CI = 4.235-35.141, p < 0.001) were independent risk factors for in-hospital mortality. The Kaplan-Meier curves showed that the cumulative survival rate was lowest in the AKI stage 3 group (p < 0.001). In conclusion, the incidence of AKI in patients with COVID-19 was 4.0%. Severe AKI was associated with in-hospital death.

Sustainable Development Goals relevant to kidney health: an update on progress

Globally, more than 5 million people die annually from lack of access to critical treatments for kidney disease — by 2040, chronic kidney disease is projected to be the fifth leading cause of death worldwide. Kidney diseases are particularly challenging to tackle because they are pathologically diverse and are often asymptomatic. As such, kidney disease is often diagnosed late, and the global burden of kidney disease continues to be underappreciated. When kidney disease is not detected and treated early, patient care requires specialized resources that drive up cost, place many people at risk of catastrophic health expenditure and pose high opportunity costs for health systems. Prevention of kidney disease is highly cost-effective but requires a multisectoral holistic approach. Each Sustainable Development Goal (SDG) has the potential to impact kidney disease risk or improve early diagnosis and treatment, and thus reduce the need for high-cost care. All countries have agreed to strive to achieve the SDGs, but progress is disjointed and uneven among and within countries. The six SDG Transformations framework can be used to examine SDGs with relevance to kidney health that require attention and reveal inter-linkages among the SDGs that should accelerate progress.

Working towards sustainable development is essential to tackle the rise in the global burden of non-communicable diseases, including kidney disease. Five years after the Sustainable Development Goal agenda was set, this Review examines the progress thus far, highlighting future challenges and opportunities, and explores the implications for kidney disease.

Each Sustainable Development Goal (SDG) has the potential to improve kidney health and prevent kidney disease by improving the general health and well-being of individuals and societies, and by protecting the environment.

Achievement of each SDG is interrelated to the achievement of multiple other SDGs; therefore, a multisectoral approach is required.

The global burden of kidney disease has been relatively underestimated because of a lack of data.

Structural violence and the social determinants of health have an important impact on kidney disease risk.

Kidney disease is the leading global cause of catastrophic health expenditure, in part because of the high costs of kidney replacement therapy.

Achievement of universal health coverage is the minimum requirement to ensure sustainable and affordable access to early detection and quality treatment of kidney disease and/or its risk factors, which should translate to a reduction in the burden of kidney failure in the future.

Predicting acute kidney injury in critically ill patients using comorbid conditions utilizing machine learning

Background

Acute kidney injury (AKI) carries a poor prognosis. Its incidence is increasing in the intensive care unit (ICU). Our purpose in this study is to develop and externally validate a model for predicting AKI in the ICU using patient data present prior to ICU admission.

Methods

We used data of 98 472 adult ICU admissions at Mayo Clinic between 1 January 2005 and 31 December 2017 and 51 801 encounters from Medical Information Mart for Intensive Care III (MIMIC-III) cohort. A gradient-boosting model was trained on 80% of the Mayo Clinic cohort using a set of features to predict AKI acquired in the ICU.

Results

AKI was identified in 39 307 (39.9%) encounters in the Mayo Clinic cohort. Patients who developed AKI in the ICU were older and had higher ICU and in-hospital mortality compared to patients without AKI. A 30-feature model yielded an area under the receiver operating curve of 0.690 [95% confidence interval (CI) 0.682–0.697] in the Mayo Clinic cohort set and 0.656 (95% CI 0.648–0.664) in the MIMIC-III cohort.

Conclusions

Using machine learning, AKI among ICU patients can be predicted using information available prior to admission. This model is independent of ICU information, making it valuable for stratifying patients at admission.

Acute Kidney Injury in Asia: Disease Burden

Acute kidney injury (AKI) is a common and critical clinical disorder with non-negligible morbidity and mortality and remains a large public health problem. Asia, as the world's largest and most populous continent, is crucial in eliminating unsatisfactory outcomes of AKI. The diversities in climate, customs, and economic status lead to various clinical features of AKI across Asia. In this review, we focus on the epidemiologic data and clinical features of AKI in different Asian countries and clinical settings, and we show the huge medical and economic burden of AKI in Asian countries. Drugs and sepsis are the most common etiologies for AKI, however, an adequate surveillance system has not been well established. There is significant undertreatment of AKI in many regions, and medical resources for renal replacement therapy are not universally available. Although substantial improvement has been achieved, health care for AKI still needs improvement, especially in developing regions.

Controversies in acute kidney injury: conclusions from a Kidney Disease: Improving Global Outcomes (KDIGO) Conference

In 2012, Kidney Disease: Improving Global Outcomes (KDIGO) published a guideline on the classification and management of acute kidney injury (AKI). The guideline was derived from evidence available through February 2011. Since then, new evidence has emerged that has important implications for clinical practice in diagnosing and managing AKI. In April of 2019, KDIGO held a controversies conference entitled Acute Kidney Injury with the following goals: determine best practices and areas of uncertainty in treating AKI; review key relevant literature published since the 2012 KDIGO AKI guideline; address ongoing controversial issues; identify new topics or issues to be revisited for the next iteration of the KDIGO AKI guideline; and outline research needed to improve AKI management. Here, we present the findings of this conference and describe key areas that future guidelines may address.

The impact of biomarkers of acute kidney injury on individual patient care

Acute kidney injury (AKI) remains a common clinical syndrome associated with increased morbidity and mortality. In the last several years there have been several advances in the identification of patients at increased risk for AKI through the use of traditional and newer functional and damage biomarkers of AKI. This article will specifically focus on the impact of biomarkers of AKI on individual patient care, focusing predominantly on the markers with the most expansive breadth of study in patients and reported literature evidence. Several studies have demonstrated that close monitoring of widely available biomarkers such as serum creatinine and urine output is strongly associated with improved patient outcomes. An integrated approach to these biomarkers used in context with patient risk factors (identifiable using electronic health record monitoring) and with tests of renal reserve may guide implementation and targeting of care bundles to optimize patient care. Besides traditional functional markers, biochemical injury biomarkers have been increasingly utilized in clinical trials both as a measure of kidney injury as well as a trigger to initiate other treatment options (e.g. care bundles and novel therapies). As the novel measures are becoming globally available, the clinical implementation of hospital-based real-time biomarker measurements involves a multidisciplinary approach. This literature review discusses the data evidence supporting both the strengths and limitations in the clinical implementation of biomarkers based on the authors' collective clinical experiences and opinions.

Acute kidney injury prediction models: current concepts and future strategies

PURPOSE OF REVIEW

Acute kidney injury (AKI) is a critical condition associated with poor patient outcomes. We aimed to review the current concepts and future strategies regarding AKI risk prediction models.

RECENT FINDINGS

Recent studies have shown that AKI occurs frequently in patients with common risk factors and certain medical conditions. Prediction models for AKI risk have been reported in medical fields such as critical care medicine, surgery, nephrotoxic agent exposure, and others. However, practical, generalizable, externally validated, and robust AKI prediction models remain relatively rare. Further efforts to develop AKI prediction models based on comprehensive clinical data, artificial intelligence, improved delivery of care, and novel biomarkers may help improve patient outcomes through precise AKI risk prediction.

SUMMARY

This brief review provides insights for current concepts for AKI prediction model development. In addition, by overviewing the recent AKI prediction models in various medical fields, future strategies to construct advanced AKI prediction models are suggested.

The Effects of Intensive Versus Routine Treatment in Patients with Acute Kidney Injury

BACKGROUND

In patients with acute kidney injury (AKI), specialized treatment-initiated in response to an early-warning system- may be beneficial compared with routine treatment.

METHOD

To explore effect estimators in a pilot trial (DRKS00010530), patients with AKI on regular wards of a university hospital were treated either in the usual way (control group) or more intensively (intervention group). The subjects were allotted randomly to the two treatment groups. The more intensive treatment consisted of an early warning system for a rise in the serum creatinine concentration, immediate consultation of a specialist, and the issuance of a patient kidney passport. The primary endpoint was recovery of renal function after AKI during the index hospitalization. Renal complications and process indicators were the secondary endpoints.

RESULTS

The proportion of patients whose renal function returned to baseline after AKI was 50% in the intervention group (N = 26) and 42% in the control group (N = 26) (odds ratio 1.4, 95% confidence interval [0.5; 4.0], p = 0.58). The calculated glomerular filtration rate went down, from hospital admission to discharge, by 3 mL/min/1.73 m2 (1st-3rd quartile: [6; -20]) in the intervention group and by 13 mL/min/1.73 m2 in the control group (1st-3rd quartile: [0; -25]; p = 0.09). Complications of AKI such as hyperkalemia, pulmonary edema, and renal acidosis were rarer in the intervention group (15% versus 39%; p = 0.03). In the intervention group, compared with the control group, the cause of AKI was identified more frequently (27% versus 4%; p = 0.05); drugs with relevance to the kidney were discontinued more frequently (65% versus 31%; p = 0.01); and the diagnosis of AKI was more frequently documented in the patient's chart (58% versus 37%; p = 0.03).

CONCLUSION

Specialized consultations supported by an early warning system for AKI seem to be beneficial for patients. The findings of this pilot trial should be verified in larger-scale randomized controlled trials.

Early prediction of pediatric acute kidney injury from the emergency department: A pilot study

BACKGROUND

Identifying acute kidney injury (AKI) early can inform medical decisions key to mitigation of injury. An AKI risk stratification tool, the renal angina index (RAI), has proven better than creatinine changes alone at predicting AKI in critically ill children.

OBJECTIVE

To derive and test performance of an "acute" RAI (aRAI) in the Emergency Department (ED) for prediction of inpatient AKI and to evaluate the added yield of urinary AKI biomarkers.

METHODS

Study of pediatric ED patients with sepsis admitted and followed for 72 h. The primary outcome was inpatient AKI defined by a creatinine >1.5× baseline, 24-72 h after admission. Patients were denoted renal angina positive (RA+) for an aRAI score above a population derived cut-off. Test characteristics evaluated predictive performance of the aRAI compared to changes in creatinine and incorporation of 4 urinary biomarkers in the context of renal angina were assessed.

RESULTS

118 eligible subjects were enrolled. Mean age was 7.8 ± 6.4 years, 16% required intensive care admission. In the ED, 27% had a +RAI (22% had a >50% creatinine increase). The aRAI had an AUC of 0.92 (0.86-0.98) for prediction of inpatient AKI. For AKI prediction, RA+ demonstrated a sensitivity of 94% (69-99) and a negative predictive value of 99% (92-100) (versus sensitivity 59% (33-82) and NPV 93% (89-96) for creatinine ≥2× baseline). Biomarker analysis revealed a higher AUC for aRAI alone than any individual biomarker.

CONCLUSIONS

This pilot study finds the aRAI to be a sensitive ED-based tool for ruling out the development of in-hospital AKI.

Intraoperative Arterial Pressure Variability and Postoperative Acute Kidney Injury

BACKGROUND AND OBJECTIVES

High BP variability may cause AKI because of inappropriate kidney perfusion. This study aimed to investigate the association between intraoperative BP variability and postoperative AKI in patients who underwent noncardiac surgery.

DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS

We performed a cohort study of adults undergoing noncardiac surgery in hospitals in South Korea. We studied three cohorts using the following recording windows for intraoperative BP: discovery cohort, 1-minute intervals; first validation cohort, 5-minute intervals; and second validation cohort, 2-second intervals. We calculated four variability parameters (SD, coefficient of variation, variation independent of mean, and average real variability) based on the measured mean arterial pressure values. The primary outcomes were postoperative AKI (defined by the Kidney Disease Improving Global Outcomes serum creatinine cutoffs) and critical AKI (consisting of stage 2 or higher AKI and post-AKI death or dialysis within 90 days).

RESULTS

In the three cohorts, 45,520, 29,704, and 7435 patients were analyzed, each with 2230 (443 critical), 1552 (444 critical), and 300 (91 critical) postoperative AKI events, respectively. In the discovery cohort, all variability parameters were significantly associated with risk of AKI, even after adjusting for intraoperative hypotension. For example, average real variability was associated with higher risks of postoperative AKI (adjusted odds ratio, 1.13 per 1 SD increment; 95% CI, 1.07 to 1.19) and critical AKI (adjusted odds ratio, 1.13 per 1 SD increment; 95% CI, 1.02 to 1.26). Associations were evident predominantly among patients who also experienced intraoperative hypotension. In the validation analysis with 5-minute-interval BP records, all four variability parameters were associated with the risk of postoperative AKI or critical AKI. In the validation cohort with 2-second-interval BP records, average real variability was the only significant variability parameter.

CONCLUSIONS

Higher intraoperative BP variability is associated with higher risks of postoperative AKI after noncardiac surgery, independent of hypotension and other clinical characteristics.

Acute kidney injury risk-based screening in pediatric inpatients: a pragmatic randomized trial

BACKGROUND

Pediatric acute kidney injury (AKI) is common and associated with increased morbidity, mortality, and length of stay. We performed a pragmatic randomized trial testing the hypothesis that AKI risk alerts increase AKI screening.

METHODS

All intensive care and ward admissions of children aged 28 days through 21 years without chronic kidney disease from 12/6/2016 to 11/1/2017 were included. The intervention alert displayed if calculated AKI risk was > 50% and no serum creatinine (SCr) was ordered within 24 h. The primary outcome was SCr testing within 48 h of AKI risk > 50%.

RESULTS

Among intensive care admissions, 973/1909 (51%) were randomized to the intervention. Among those at risk, more SCr tests were ordered for the intervention group than for controls (418/606, 69% vs. 361/597, 60%, p = 0.002). AKI incidence and severity were the same in intervention and control groups. Among ward admissions, 5492/10997 (50%) were randomized to the intervention, and there were no differences between groups in SCr testing, AKI incidence, or severity of AKI.

CONCLUSIONS

Alerts based on real-time prediction of AKI risk increased screening rates in intensive care but not pediatric ward settings. Pragmatic clinical trials provide the opportunity to assess clinical decision support and potentially eliminate ineffective alerts.

Acute kidney injury electronic alerts: mixed methods Normalisation Process Theory evaluation of their implementation into secondary care in England

OBJECTIVE

Around one in five emergency hospital admissions are affected by acute kidney injury (AKI). To address poor quality of care in relation to AKI, electronic alerts (e-alerts) are mandated across primary and secondary care in England and Wales. Evidence of the benefit of AKI e-alerts remains conflicting, with at least some uncertainty explained by poor or unclear implementation. The objective of this study was to identify factors relating to implementation, using Normalisation Process Theory (NPT), which promote or inhibit use of AKI e-alerts in secondary care.

DESIGN

Mixed methods combining qualitative (observations, semi-structured interviews) and quantitative (survey) methods.

SETTING AND PARTICIPANTS

Three secondary care hospitals in North East England, representing two distinct AKI e-alerting systems. Observations (>44 hours) were conducted in Emergency Assessment Units (EAUs). Semi-structured interviews were conducted with clinicians (n=29) from EAUs, vascular or general surgery or care of the elderly. Qualitative data were supplemented by Normalization MeAsure Development (NoMAD) surveys (n=101).

ANALYSIS

Qualitative data were analysed using the NPT framework, with quantitative data analysed descriptively and using χ² and Wilcoxon signed-rank test for differences in current and future normalisation.

RESULTS

Participants reported familiarity with the AKI e-alerts but that the e-alerts would become more normalised in the future (p<0.001). No single NPT mechanism led to current (un)successful implementation of the e-alerts, but analysis of the underlying subconstructs identified several mechanisms indicative of successful normalisation (internalisation, legitimation) or unsuccessful normalisation (initiation, differentiation, skill set workability, systematisation).

CONCLUSIONS

Clinicians recognised the value and importance of AKI e-alerts in their practice, although this was not sufficient for the e-alerts to be routinely engaged with by clinicians. To further normalise the use of AKI e-alerts, there is a need for tailored training on use of the e-alerts and routine feedback to clinicians on the impact that e-alerts have on patient outcomes.

Baby NINJA (Nephrotoxic Injury Negated by Just-in-Time Action): Reduction of Nephrotoxic Medication-Associated Acute Kidney Injury in the Neonatal Intensive Care Unit

OBJECTIVE(S)

To test if acute kidney injury (AKI) is preventable in patients in the neonatal intensive care unit and if infants at high-risk of nephrotoxic medication-induced AKI can be identified using a systematic surveillance program previously used in the pediatric non-intensive care unit setting.

STUDY DESIGN

Quality improvement project that occurred between March 2015 and September 2017 in a single center, level IV neonatal intensive care unit. Infants were screened for high-risk nephrotoxic medication exposure (≥3 nephrotoxic medication within 24 hours or ≥4 calendar days of an intravenous [IV] aminoglycoside). If infants met criteria, a daily serum creatinine (SCr) was obtained until 2 days after end of exposure or end of AKI, whichever occurred last. The study was divided into 3 eras: pre-Nephrotoxic Injury Negated by Just-in-time Action (NINJA), initiation, and sustainability. Differences for 5 metrics across 3 eras were compared: SCr surveillance, high nephrotoxic medication exposure rate (per 1000 patient-days), AKI rate (per 1000 patient-days), nephrotoxin-AKI percentage, and AKI intensity (number of AKI days per 100 susceptible patient-days).

RESULTS

Comparing the initiation with sustainability era, there was a reduction in high nephrotoxic medication exposures from 16.4 to 9.6 per 1000 patient-days (P = .03), reduction in percentage of nephrotoxic medication-AKI from 30.9% to 11.0% (P < .001), and reduction in AKI intensity from 9.1 to 2.9 per 100 susceptible patient-days (P < .001) while maintaining a high SCr surveillance rate. This prevented 100 AKI episodes during the 18-month sustainability era.

CONCLUSION(S)

A systematic surveillance program to identify high-risk infants can prevent nephrotoxic-induced AKI and has the potential to prevent short and long-term consequences of AKI in critically ill infants.

Lab monitoring and acute care utilization during initiation of renin angiotensin aldosterone inhibitors or diuretics in chronic kidney disease

Renin angiotensin aldosterone system inhibitors (RAASi) and diuretics are among the most frequently prescribed anti-hypertensives. Individuals with chronic kidney disease (CKD) are particularly at risk for electrolyte disturbances and kidney injury but the appropriate use of lab monitoring following RAASi or diuretic initiation is uncertain in CKD.We describe the frequency and time interval of lab monitoring during initiation of RAASi and diuretics in CKD and assess whether close lab monitoring associates with one-year risk of emergency department (ED) visit or hospitalization.We evaluated an observational cohort of 8,217 individuals with stage 3-5 non-dialysis CKD newly prescribed a RAASi (52.3%) or diuretic (47.7%) from thirty-six primary care offices affiliated with Brigham and Women's Hospital and Massachusetts General Hospital between 2009 and 2011.Overall, 3306 (40.2%) individuals did not have pre-prescription labs done within 2 weeks, and 5957 (72.5%) did not have post-prescription labs done within 2 weeks which includes 524 (6.4%) individuals without post-prescription within 1 year. Close monitoring occurred in only 1547 (20.1%) and was more likely in individuals prescribed diuretics compared to RAASi (adjusted OR 1.39; 95%CI 1.20-1.62), with CKD stage 4,5 compared with stage 3 (adjusted OR 1.47; 95%CI 1.16-1.86) and with cardiovascular disease (adjusted OR 1.42; 95%CI 1.21-1.66). Close monitoring was not associated with decreased risk of ED visit or hospitalization.Close lab monitoring during initiation of RAASi or diuretics was more common in participants with cardiovascular disease and advanced CKD suggesting physicians selected high-risk individuals for close monitoring. As nearly 80% of individuals did not receive close lab monitoring there may be value in future research on electronic physician decision tools targeted at lab monitoring.

Acute Renal Failure of Nosocomial Origin

BACKGROUND

10-20% of hospitalized patients develop acute kidney injury (AKI)/acute renal failure during their hospital stay. The mortality of nosocomial AKI is approximately 30%.

METHODS

This review is based on relevant publications retrieved by a search in multiple databases (PubMed and Uptodate), archives, and pertinent medical journals.

RESULTS

The most common causes of nosocomial AKI are volume depletion, sepsis, heart diseases, polytrauma, liver diseases, and drug toxicity. AKI can also be of postrenal (obstructive) origin, or a result of renal diseases including glomeruloneph- ritis, vasculitis, tubulointerstitial nephritis, and cholesterol embolism. In about 13% of cases, nosocomial AKI develops on the basis of pre-existing chronic renal disease. Patients with AKI are at elevated risk of developing chronic renal disease and must be followed up appropriately after they are discharged from the hospital. Indispens- able elements of the evaluation of nosocomial AKI include renal ultrasonography, the exclusion of postrenal obstruction, urine chemistry, and microbiological urinaly- sis. Potentially nephrotoxic drugs and those that impair renal hemodynamics must be avoided to the greatest possible extent in patients with acute renal damage. Hypotension must be avoided as well.

CONCLUSION

Early, specific nephrological diagnosis and treatment are important components of the management of nosocomial AKI, particularly because causally directed treatment is available for some of the conditions that underlie it.

[Risk assessment of acute kidney injury in patients with acute cardiovascular disease without invasive intervention]

OBJECTIVE

To evaluate the prevalence, predictors, prognostic value of cardiorenal interrelations in patients with acute cardiovascular disease (CVD), and to develop an algorithm for stratification these patients at risk of acute kidney injury (AKI).

MATERIALS AND METHODS

566 patients (pts) were examined: 278 with acute decompensated heart failure (ADHF) and 288 with non-ST-elevation acute coronary syndrome (NSTE-ACS). The levels of electrolytes, glucose, urea, creatinine were evaluated, glomerular filtration rate (GFR) was determined according to the formula CKD-EPI. Chest x-ray, electrocardiography at admission and in dynamics, echocardiography at admission with assessment of systolic and diastolic myocardial functions were performed. Chronic kidney disease (CKD), AKI, ADHF, NSTE-ACS were diagnosed according to Russian and international Guidelines. Mann-Whitney test and multivariate logistic regression analysis were considered significant if p&lt;0.05.

RESULTS

Different variants of cardiorenal interrelations were revealed in 366 (64.7%) pts. CKD was diagnosed in 259 (45.8%), with more than half of the cases (61%) diagnosed for the first time at this hospitalization, 62 (11%) pts had signs of kidney damage of unknown duration (which did not allow to diagnose CKD). AKI occurred in 228 (40,3%) pts, more frequently in patients with ADHF vs with NSTE-ACS (43.5 and 37.2%). In all groups stage 1 of AKI was prevalent. In-hospital mortality was significantly higher in pts with AKI vs without AKI (14.9 vs 3.6%, p&lt;0.001). The risk of AKI was determined by kidney function and blood pressure levels at admission, and comorbidities.

CONCLUSION

Prevalence of cardiorenal interactions in patients with acute CVD (ADHF and NSTE-ACS) was 64.7%. Development of AKI was associated with poor prognosis in both groups. Renal function and blood pressure levels on admission are the main predictors of AKI.

A clinically applicable approach to continuous prediction of future acute kidney injury

The early prediction of deterioration could have an important role in supporting healthcare professionals, as an estimated 11% of deaths in hospital follow a failure to promptly recognize and treat deteriorating patients1. To achieve this goal requires predictions of patient risk that are continuously updated and accurate, and delivered at an individual level with sufficient context and enough time to act. Here we develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records2-17 and using acute kidney injury-a common and potentially life-threatening condition18-as an exemplar. Our model was developed on a large, longitudinal dataset of electronic health records that cover diverse clinical environments, comprising 703,782 adult patients across 172 inpatient and 1,062 outpatient sites. Our model predicts 55.8% of all inpatient episodes of acute kidney injury, and 90.2% of all acute kidney injuries that required subsequent administration of dialysis, with a lead time of up to 48 h and a ratio of 2 false alerts for every true alert. In addition to predicting future acute kidney injury, our model provides confidence assessments and a list of the clinical features that are most salient to each prediction, alongside predicted future trajectories for clinically relevant blood tests9. Although the recognition and prompt treatment of acute kidney injury is known to be challenging, our approach may offer opportunities for identifying patients at risk within a time window that enables early treatment.

Evaluation of a digitally-enabled care pathway for acute kidney injury management in hospital emergency admissions

We developed a digitally enabled care pathway for acute kidney injury (AKI) management incorporating a mobile detection application, specialist clinical response team and care protocol. Clinical outcome data were collected from adults with AKI on emergency admission before (May 2016 to January 2017) and after (May to September 2017) deployment at the intervention site and another not receiving the intervention. Changes in primary outcome (serum creatinine recovery to ≤120% baseline at hospital discharge) and secondary outcomes (30-day survival, renal replacement therapy, renal or intensive care unit (ICU) admission, worsening AKI stage and length of stay) were measured using interrupted time-series regression. Processes of care data (time to AKI recognition, time to treatment) were extracted from casenotes, and compared over two 9-month periods before and after implementation (January to September 2016 and 2017, respectively) using pre–post analysis. There was no step change in renal recovery or any of the secondary outcomes. Trends for creatinine recovery rates (estimated odds ratio (OR) = 1.04, 95% confidence interval (95% CI): 1.00–1.08, p = 0.038) and renal or ICU admission (OR = 0.95, 95% CI: 0.90–1.00, p = 0.044) improved significantly at the intervention site. However, difference-in-difference analyses between sites for creatinine recovery (estimated OR = 0.95, 95% CI: 0.90–1.00, p = 0.053) and renal or ICU admission (OR = 1.06, 95% CI: 0.98–1.16, p = 0.140) were not significant. Among process measures, time to AKI recognition and treatment of nephrotoxicity improved significantly (p < 0.001 and 0.047 respectively).

Implementation of a Digitally Enabled Care Pathway (Part 1): Impact on Clinical Outcomes and Associated Health Care Costs

Background

The development of acute kidney injury (AKI) in hospitalized patients is associated with adverse outcomes and increased health care costs. Simple automated e-alerts indicating its presence do not appear to improve outcomes, perhaps because of a lack of explicitly defined integration with a clinical response.

Objective

We sought to test this hypothesis by evaluating the impact of a digitally enabled intervention on clinical outcomes and health care costs associated with AKI in hospitalized patients.

Methods

We developed a care pathway comprising automated AKI detection, mobile clinician notification, in-app triage, and a protocolized specialist clinical response. We evaluated its impact by comparing data from pre- and postimplementation phases (May 2016 to January 2017 and May to September 2017, respectively) at the intervention site and another site not receiving the intervention. Clinical outcomes were analyzed using segmented regression analysis. The primary outcome was recovery of renal function to ≤120% of baseline by hospital discharge. Secondary clinical outcomes were mortality within 30 days of alert, progression of AKI stage, transfer to renal/intensive care units, hospital re-admission within 30 days of discharge, dependence on renal replacement therapy 30 days after discharge, and hospital-wide cardiac arrest rate. Time taken for specialist review of AKI alerts was measured. Impact on health care costs as defined by Patient-Level Information and Costing System data was evaluated using difference-in-differences (DID) analysis.

Results

The median time to AKI alert review by a specialist was 14.0 min (interquartile range 1.0-60.0 min). There was no impact on the primary outcome (estimated odds ratio [OR] 1.00, 95% CI 0.58-1.71; P=.99). Although the hospital-wide cardiac arrest rate fell significantly at the intervention site (OR 0.55, 95% CI 0.38-0.76; P<.001), DID analysis with the comparator site was not significant (OR 1.13, 95% CI 0.63-1.99; P=.69). There was no impact on other secondary clinical outcomes. Mean health care costs per patient were reduced by £2123 (95% CI −£4024 to −£222; P=.03), not including costs of providing the technology.

Conclusions

The digitally enabled clinical intervention to detect and treat AKI in hospitalized patients reduced health care costs and possibly reduced cardiac arrest rates. Its impact on other clinical outcomes and identification of the active components of the pathway requires clarification through evaluation across multiple sites.

A simple real-time model for predicting acute kidney injury in hospitalized patients in the US: A descriptive modeling study

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.

Schmidt-Ott K. The Incidence of Acute Kidney Injury and Associated Hospital Mortality

BACKGROUND

Studies from multiple countries have shown that acute kidney injury (AKI) in hospitalized patients is associated with mortality and morbidity. There are no reliable data at present on the incidence and mortality of AKI episodes among hospitalized patients in Germany. The utility of administrative codings of AKI for the identification of AKI episodes is also unclear.

METHODS

In an exploratory approach, we retrospectively analyzed all episodes of AKI over a period of 3.5 years (2014-2017) on the basis of routinely obtained serum creatinine measurements in 103 161 patients whose creatinine had been measured at least twice and who had been in the hospital for at least two days. We used the "Kidney Disease: Improving Global Outcomes" (KDIGO) criteria for AKI. In parallel, we assessed the administrative coding of discharge diagnoses of the same patients with codes from the International Classification of Diseases (ICD-10-GM).

RESULTS

Among 185 760 hospitalizations, stage 1 AKI occurred in 25 417 cases (13.7%), stage 2 in 8503 cases (4.6%), and stage 3 in 5881 cases (3.1%). AKI cases were associated with length of hospital stay, renal morbidity, and overall mortality, and this association was stage-dependent. The in-hospital mortality was 5.1% for patients with stage 1 AKI, 13.7% for patients with stage 2 AKI, and 24.8% for patients with stage 3 AKI. An administrative coding for acute kidney injury (N17) was present in only 28.8% (11 481) of the AKI cases that were identified by creatinine criteria. Like the AKI cases overall, those that were identified by creatinine criteria but were not coded as AKI had significantly higher mortality, and this association was stage-dependent.

CONCLUSION

AKI episodes are common among hospitalized patients and are associated with considerable morbidity and mortality, yet they are inadequately documented and probably often escape the attention of the treating physicians.

Integration of urinary neutrophil gelatinase-associated lipocalin with serum creatinine delineates acute kidney injury phenotypes in critically ill children

PURPOSE

Acute kidney injury (AKI) is prevalent in critically ill patients and associated with poor outcomes. Current AKI diagnostics- changes to serum creatinine (SCr) and urine output- are imprecise. Integration of injury biomarkers with SCr may improve diagnostic precision.

METHODS

We performed a secondary analysis of a study of critically ill children. Measurements of urine neutrophil gelatinase-associated lipocalin (uNGAL) and SCr samples from ICU admission facilitated the creation of four groups for comparison, based on elevation of SCr from baseline and reference NGAL cut-off value: uNGAL-/SCr-, uNGAL+/SCr-, uNGAL-/SCr + and uNGAL+/SCr+. The primary outcome assessed was AKI severity on Day 3.

RESULTS

178 children were studied. Compared to uNGAL-/SCr-, uNGAL+/SCr- patients had increased risk for all-stage Day 3 AKI (≥ KDIGO stage 1) (OR 3.83, [1.3-11.3], p = .025). Compared to uNGAL-/SCr+, uNGAL+/SCr + patients had increased risk for severe Day 3 AKI (≥ KDIGO stage 2) (OR 12, [1.4-102], p = .018). The only patients to suffer all-stage Day 3 AKI and mortality were uNGAL+ (3.2% uNGAL+/SCr-; 6.5% uNGAL+/SCr+).

CONCLUSIONS

Unique biomarker combinations on admission are predictive of distinct Day 3 AKI severity phenotypes. These classifications may enable a more personalized approach to the early management of AKI. Expanded study in larger populations is warranted.

Community-Acquired Acute Kidney Injury as a Risk Factor of de novo Heart Failure Hospitalization

Objectives: Because patients with hospital-acquired acute kidney injury (AKI) are at risk for subsequent development of heart failure (HF) and little is known about the relation between community-acquired AKI (CA-AKI) and HF, we sought to determine if CA-AKI is a risk factor for incident HF hospitalization. Methods: We utilized Baylor Scott &amp; White Health databases at the primary care and inpatient hospitalization levels to identify adults without a prior history of HF who had 2 or more serum creatinine measurements within 13 months in the primary care setting. We defined CA-AKI as a serum creatinine increase ≥0.3 mg/dL or ≥1.5 times the baseline for consecutive values within a 13-month period. We created a flag for de novo HF hospitalization at 90, 180, and 365 days following CA-AKI evaluation. Results: In the analyses, 210,895 unique adults were included, of whom 5,358 (2.5%) had CA-AKI. Those with CA-AKI had higher rates of comorbidities, higher rate of males (48 vs. 42%, p < 0.001), and were older (61.5 [50.3, 73.1] vs. 54.1 [42.8, 64.7] years, p < 0.001) than those who did not have CA-AKI. In total, 607 (0.3%), 833 (0.4%), and 1,089 (0.5%) individuals had an incident HF hospitalization in the 90, 180, and 365 days following the CA-AKI evaluation, respectively. After adjusting for demographic and clinical characteristics, patients with CA-AKI had >2 times the risk of de novo HF hospitalization compared with patients who did not have CA-AKI (90 days: 2.35 [1.83–3.02], p < 0.001; 180 days: 2.52 [2.04–3.13], p < 0.001; 365 days: 2.16 [1.77–2.64], p < 0.001). These multivariable models yielded strong predictive abilities, with the areas under the receiver-operating characteristic curve >0.90. Conclusion: After controlling for baseline and clinical characteristics, patients with CA-AKI were at approximately twofold the risk of de novo HF hospitalization (within 90, 180, and 365 days) compared with those who did not have CA-AKI. Hence, detecting CA-AKI may provide an opportunity for early intervention at the primary care level to possibly delay HF development.

Hyperuricemia is associated with acute kidney injury and all-cause mortality in hospitalized patients

AIM

Hyperuricemia is a risk factor for high morbidity and mortality in several diseases. However, the relationship between uric acid (UA) and the risk of acute kidney injury (AKI) and mortality remain unresolved in hospitalized patients.

METHODS

Data from 18 444 hospitalized patients were retrospectively reviewed. The odds ratio (OR) for AKI and the hazard ratio (HR) for all-cause mortality were calculated based on the UA quartiles after adjustment for multiple variables. All analyses were performed after stratification by sex.

RESULTS

The fourth quartile group (male, UA > 6.7 mg/dL; female, UA > 5.4 mg/dL) showed a higher risk of AKI compared with the first quartile group (male, UA < 4.5 mg/dL; female, UA < 3.6 mg/dL), with the following OR: 3.2 (2.55-4.10) in males (P < 0.001); and 3.1 (2.40-4.19) in females (P < 0.001). There were more patients who did not recover from AKI in the fourth quartile compared with the first quartile, with the following OR: 2.0 (1.32-3.04) in males (P = 0.001) and 2.4 (1.43-3.96) in females (P = 0.001). The fourth quartile group had a higher risk of all-cause mortality compared with the first quartile group, with the following HR: 1.4 (1.20-1.58) in males (P < 0.001) and 1.2 (1.03-1.46) in females (P = 0.019). The in-hospital mortality risk was also higher in the fourth quartile compared with the first quartile, which was significant only in males (OR, 2.1 (1.33-3.31) (P = 0.002)).

CONCLUSION

Hyperuricemia increases the risks of AKI and all-cause mortality in hospitalized patients.

Perspectives on acute kidney injury strategy: Hong Kong

Acute kidney injury is a common condition in hospitalized patients and a strong predictor of short-term morbidity and mortality. In this article, local epidemiological data on the prevalence and outcome of acute kidney injury amongst hospitalized patient in a tertiary referral center were discussed. The latest practice guidelines endorsed by the Hong Kong College of Physicians will be discussed, with emphasis on local practical issues and problems of guideline implementation.

Big Data and Pediatric Acute Kidney Injury: The Promise of Electronic Health Record Systems

Over the last decade, our understanding of acute kidney injury (AKI) has evolved considerably. The development of a consensus definition standardized the approach to identifying and investigating AKI in children. As a result, pediatric AKI epidemiology has been refined and the consequences of renal injury are better established. Similarly, "big data" methodologies experienced a dramatic evolution and maturation, leading the critical care community to explore potential AKI/big data synergies. One such concept with tremendous potential is electronic health record (EHR) enabled informatics. Much of the promise surrounding these approaches is due to the unique position of the EHR which sits at the intersection of data accumulation and care delivery. EHR data is generated simply via the provision of routine clinical care and should be considered "big" from the standpoint of volume, variety, and velocity as a myriad of diverse elements accumulate rapidly in real time, spontaneously generating an immense dataset. This massive dataset interfaces directly with providers which creates tremendous opportunity. AKI can be diagnosed more accurately, AKI-related care can be optimized, and subsequent outcomes can be improved. Although applying big data concepts to the EHR has proven more challenging than originally thought, we have seen much success and continue to explore its potential. In this review article, we will discuss the EHR in the context of big data concepts, describe approaches applied to date, examine the challenges surrounding optimal application, and explore future directions.

Simple Postoperative AKI Risk (SPARK) Classification before Noncardiac Surgery: A Prediction Index Development Study with External Validation

BACKGROUND

Researchers have suggested models to predict the risk of postoperative AKI (PO-AKI), but an externally validated risk index that can be practically implemented before patients undergo noncardiac surgery is needed.

METHODS

We performed a retrospective observational study of patients without preexisting renal failure who underwent a noncardiac operation (≥1 hour) at two tertiary hospitals in Korea. We fitted a proportional odds model for an ordinal outcome consisting of three categories: critical AKI (defined as Kidney Disease Improving Global Outcomes AKI stage ≥2, post-AKI death, or dialysis within 90 days after surgery), low-stage AKI (defined as PO-AKI events not fulfilling the definition of critical AKI), and no PO-AKI.

RESULTS

The study included 51,041 patients in a discovery cohort and 39,764 patients in a validation cohort. The Simple Postoperative AKI Risk (SPARK) index included a summation of the integer scores of the following variables: age, sex, expected surgery duration, emergency operation, diabetes mellitus, use of renin-angiotensin-aldosterone inhibitors, baseline eGFR, dipstick albuminuria hypoalbuminemia, anemia, and hyponatremia. The model calibration plot showed tolerable distribution of observed and predicted probabilities in both cohorts. The discrimination power of the SPARK index was acceptable in both the discovery (c-statistic 0.80) and validation (c-statistic 0.72) cohorts. When four SPARK classes were defined on the basis of the sum of the risk scores, the SPARK index and classes fairly reflected the risks of PO-AKI and critical AKI.

CONCLUSIONS

Clinicians may consider implementing the SPARK index and classifications to stratify patients' PO-AKI risks before performing noncardiac surgery.

The ICE-AKI study: Impact analysis of a Clinical prediction rule and Electronic AKI alert in general medical patients

BACKGROUND

Acute kidney injury (AKI) is assoicated with high mortality and measures to improve risk stratification and early identification have been urgently called for. This study investigated whether an electronic clinical prediction rule (CPR) combined with an AKI e-alert could reduce hospital-acquired AKI (HA-AKI) and improve associated outcomes.

METHODS AND FINDINGS

A controlled before-and-after study included 30,295 acute medical admissions to two adult non-specialist hospital sites in the South of England (two ten-month time periods, 2014-16); all included patients stayed at least one night and had at least two serum creatinine tests. In the second period at the intervention site a CPR flagged those at risk of AKI and an alert was generated for those with AKI; both alerts incorporated care bundles. Patients were followed-up until death or hospital discharge. Primary outcome was change in incident HA-AKI. Secondary outcomes in those developing HA-AKI included: in-hospital mortality, AKI progression and escalation of care. On difference-in-differences analysis incidence of HA-AKI reduced (odds ratio [OR] 0.990, 95% CI 0.981-1.000, P = 0.049). In-hospital mortality in HA-AKI cases reduced on difference-in-differences analysis (OR 0.924, 95% CI 0.858-0.996, P = 0.038) and unadjusted analysis (27.46% pre vs 21.67% post, OR 0.731, 95% CI 0.560-0.954, P = 0.021). Mortality in those flagged by the CPR significantly reduced (14% pre vs 11% post intervention, P = 0.008). Outcomes for community-acquired AKI (CA-AKI) cases did not change. A number of process measures significantly improved at the intervention site. Limitations include lack of randomization, and generalizability will require future investigation.

CONCLUSIONS

In acute medical admissions a multi-modal intervention, including an electronically integrated CPR alongside an e-alert for those developing HA-AKI improved in-hospital outcomes. CA-AKI outcomes were not affected. The study provides a template for investigations utilising electronically generated prediction modelling. Further studies should assess generalisability and cost effectiveness.

TRIAL REGISTRATION

Clinicaltrials.org NCT03047382.

Acute Kidney Injury in Real Time: Prediction, Alerts, and Clinical Decision Support

Broad adoption of electronic health record (EHR) systems has facilitated acute kidney injury (AKI) research in 2 ways. First, the detection of AKI based on changes in serum creatinine has largely replaced the sensitive but nonspecific administrative coding of AKI that predominated in earlier studies. Second, the ability to implement real-time AKI interventions such as alerts and best-practice advisories has emerged as a promising tool to fight against the harmful sequela of AKI, which include short-term adverse outcomes as well as progression to chronic kidney disease, dialysis, and death. In this review, we discuss the current state-of-the-art in EHR-based tools to predict imminent AKI, alert to the presence of AKI, and modify provider behaviors in the presence of AKI.

Automated acute kidney injury alerts

Acute kidney injury (AKI) is one of the most common and probably one of the more consequential complications of critical illnesses. Recent information indicates that it is at least partially preventable; however, progress in its prevention, management, and treatment has been hindered by the scarcity of knowledge for effective interventions, inconsistencies in clinical practices, late identification of patients at risk for or with AKI, and limitations of access to best practices for prevention and management of AKI. Growing use of electronic health records has provided a platform for computer science to engage in data mining and processing, not only for early detection of AKI but also for the development of risk-stratification strategies and computer clinical decision-support (CDS) systems. Despite promising perspectives, the literature regarding the impact of AKI electronic alerts and CDS systems has been conflicting. Some studies have reported improvement in care processes and patient outcomes, whereas others have shown no effect on clinical outcomes and yet demonstrated an increase in the use of resources. These discrepancies are thought to be due to multiple factors that may be related to technology, human factors, modes of delivery of information to clinical providers, and level of expectations regarding the impact on patient outcomes. This review appraises the current body of knowledge and provides some outlines regarding research into and clinical aspects of CDS systems for AKI.