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

Early detection of acute kidney injury through an alert system improves outcomes in hospitalized patients

BACKGROUND AND AIMS

Acute kidney injury (AKI) acquired in hospital settings has emerged as a significant public health issue. It is linked to prolonged hospital stays, increased healthcare costs, heightened risk of developing chronic kidney disease, mortality, and the need for ongoing post-hospitalization care. Our hypothesis suggests that timely recognition of AKI, identification of its underlying causes, and expert management by specialists could lead to improved prognoses for hospitalized patients.

MATERIALS AND METHODS

We have devised an electronic-alert system that incorporates an action and follow-up plan overseen by a multidisciplinary team of hospital professionals. We compared the prognosis of patients measured in terms of length of hospital stay, in-hospital mortality and improvement of renal function at different points.

RESULTS

Almost 80 % of patients in the Intervention group had a significant decrease in serum creatinine 48 h after the alert. The length of hospital stay was longer in the Non-Intervention group than in the Intervention group: 12 (8 - 20) vs 10 (6 - 15) days (p = 0.002), as was mortality during hospitalization: 34 % of cases vs 19.9 % (p = 0.002). The median survival of the Non-Intervention group was estimated at 20 (14 - 26) days, while that of the Intervention group was estimated at 33 (20 - 45) days.

CONCLUSIONS

Our study highlights the importance of closely monitoring at-risk patients for AKI during and after hospitalization. Prompt risk assessment and interventions by healthcare professionals, including clinical laboratory involvement, could improve AKI prognosis.

A quality improvement project to improve treatment of severe hypertriglyceridemia in veterans

BACKGROUND

Severe hypertriglyceridemia (sHTG) is associated with an increased risk of acute pancreatitis. Prompt recognition and treatment of sHTG is key for prevention of acute pancreatitis and its associated life-threatening complications.

LOCAL PROBLEM

Patients with sHTG at a primary care clinic within the Veterans Affairs Eastern Colorado Health Care System were receiving suboptimal treatment that did not align with evidence-based guidelines.

METHODS

We initiated a quality improvement (QI) project to improve the management of sHTG in an outpatient primary care clinic. Veterans with a triglyceride level between 500 and 1,500 mg/dl were included in the project.

INTERVENTIONS

Project interventions included provider education, patient education, and targeted electronic consultations (e-consults) with treatment recommendations. The primary outcome was to decrease the percentage of patients with triglycerides ≥500 mg/dl by 25%. The secondary outcome was to decrease the mean triglyceride level of the patient population by 15%.

RESULTS

Education on evaluation and treatment of sHTG was given to 100% ( n = 21) of primary care clinicians. Overall, 72.8% (95% CI [62.6-81.6%]) of patients ( n = 67) received appropriate written education materials, and 72.8% (95% CI [62.6-81.6%]) of patients ( n = 67) received a targeted e-consult. The percentage of patients with sHTG decreased by 47%. Average triglyceride level decreased from 651 to 483 mg/dl (25.8% decrease).

CONCLUSION

A multipronged QI project consisting of provider education, patient education, and targeted e-consults resulted in decreased triglyceride levels and improved access to specialist expertise. Clinical implications include decreased prevalence of sHTG and risk of acute pancreatitis among patients in the project.

10 tips on how to use dynamic risk assessment and alerts for AKI

Acute kidney injury (AKI) is a common syndrome in hospitalized patients and is associated with increased morbidity and mortality. The focus of AKI care requires a shift away from strictly supportive management of established injury to the early identification and timely prevention of worsening renal injury. Identifying patients at risk for developing or progression of severe AKI is crucial for improving patient outcomes, reducing the length of hospitalization and minimizing resource utilization. Implementation of dynamic risk scores and incorporation of novel biomarkers show promise for early detection and minimizing progression of AKI. Like any risk assessment tools, these require further external validation in a variety of clinical settings prior to widespread implementation. Additionally, alerts that may minimize exposure to a variety of nephrotoxic medications or prompt early nephrology consultation are shown to reduce the incidence and progression of AKI severity and enhance renal recovery. While dynamic risk scores and alerts are valuable, implementation requires thoughtfulness and should be used in conjunction with the overall clinical picture in certain situations, particularly when considering the initiation of fluid and diuretic administration or renal replacement therapy. Despite the contemporary challenges encountered with alert fatigue, implementing an alert-based bundle to improve AKI care is associated with improved outcomes, even when implementation is incomplete. Lastly, all alert-based interventions should be validated at an institutional level and assessed for their ability to improve institutionally relevant and clinically meaningful outcomes, reduce resource utilization and provide cost-effective interventions.

Artificial intelligence and predictive models for early detection of acute kidney injury: transforming clinical practice

Acute kidney injury (AKI) presents a significant clinical challenge due to its rapid progression to kidney failure, resulting in serious complications such as electrolyte imbalances, fluid overload, and the potential need for renal replacement therapy. Early detection and prediction of AKI can improve patient outcomes through timely interventions. This review was conducted as a narrative literature review, aiming to explore state-of-the-art models for early detection and prediction of AKI. We conducted a comprehensive review of findings from various studies, highlighting their strengths, limitations, and practical considerations for implementation in healthcare settings. We highlight the potential benefits and challenges of their integration into routine clinical care and emphasize the importance of establishing robust early-detection systems before the introduction of artificial intelligence (AI)-assisted prediction models. Advances in AI for AKI detection and prediction are examined, addressing their clinical applicability, challenges, and opportunities for routine implementation.

Effect of electronic alerts on the care and outcomes in patients with acute kidney injury: a meta-analysis and trial sequential analysis

BACKGROUND

Although electronic alerts are being increasingly implemented in patients with acute kidney injury (AKI), their effect remains unclear. Therefore, we conducted this meta-analysis aiming at investigating their impact on the care and outcomes of AKI patients.

METHODS

PubMed, Embase, Cochrane Library, and Clinical Trial Registries databases were systematically searched for relevant studies from inception to March 2024. Randomized controlled trials comparing electronic alerts with usual care in patients with AKI were selected.

RESULTS

Six studies including 40,146 patients met the inclusion criteria. The pooled results showed that electronic alerts did not improve mortality rates (relative risk (RR) = 1.02, 95% confidence interval (CI) = 0.97-1.08, P = 0.44) or reduce creatinine levels (mean difference (MD) =  - 0.21, 95% CI =  - 1.60-1.18, P = 0.77) and AKI progression (RR = 0.97, 95% CI = 0.90-1.04, P = 0.40). Instead, electronic alerts increased the odds of dialysis and AKI documentation (RR = 1.14, 95% CI = 1.05-1.25, P = 0.002; RR = 1.21, 95% CI = 1.01-1.44, P = 0.04, respectively), but the trial sequential analysis (TSA) could not confirm these results. No differences were observed in other care-centered outcomes including renal consults and investigations between the alert and usual care groups.

CONCLUSIONS

Electronic alerts increased the incidence of AKI and dialysis in AKI patients, which likely reflected improved recognition and early intervention. However, these changes did not improve the survival or kidney function of AKI patients. The findings warrant further research to comprehensively evaluate the impact of electronic alerts.

Electronic Alert Systems for Patients With Acute Kidney Injury: A Systematic Review and Meta-Analysis

Importance

The acute kidney injury (AKI) electronic alert (e-alert) system was hypothesized to improve the outcomes of AKI. However, its association with different patient outcomes and clinical practice patterns remains systematically unexplored.

Objective

To assess the association of AKI e-alerts with patient outcomes (mortality, AKI progression, dialysis, and kidney recovery) and clinical practice patterns.

Data Sources

A search of Embase and PubMed on March 18, 2024, and a search of the Cochrane Library on March 20, 2024, to identify all relevant studies. There were no limitations on language or article types.

Study Selection

Studies evaluating the specified outcomes in adult patients with AKI comparing AKI e-alerts with standard care or no e-alerts were included. Studies were excluded if they were duplicate cohorts, had insufficient outcome data, or had no control group.

Data Extraction and Synthesis

Two investigators independently extracted data and assessed bias. The systematic review and meta-analysis followed the PRISMA guidelines. Random-effects model meta-analysis, with predefined subgroup analysis and trial sequential analyses, were conducted.

Main Outcomes and Measures

Primary outcomes included mortality, AKI progression, dialysis, and kidney recovery. Secondary outcomes were nephrologist consultations, post-AKI exposure to nonsteroidal anti-inflammatory drugs (NSAID), post-AKI angiotensin-converting enzyme inhibitor and/or angiotensin receptor blocker (ACEI/ARB) prescription, hospital length of stay, costs, and AKI documentation.

Results

Thirteen unique studies with 41 837 unique patients were included (mean age range, 60.5-79.0 years]; 29.3%-48.5% female). The risk ratios (RRs) for the AKI e-alerts group compared with standard care were 0.96 for mortality (95% CI, 0.89-1.03), 0.91 for AKI stage progression (95% CI, 0.84-0.99), 1.16 for dialysis (95% CI, 1.05-1.28), and 1.13 for kidney recovery (95% CI, 0.86-1.49). The AKI e-alerts group had RRs of 1.45 (95% CI, 1.04-2.02) for nephrologist consultation, 0.75 (95% CI, 0.59-0.95) for post-AKI NSAID exposure. The pooled RR for post-AKI ACEI/ARB exposure in the AKI e-alerts group compared with the control group was 0.91 (95% CI, 0.78-1.06) and 1.28 (95% CI, 1.04-1.58) for AKI documentation. Use of AKI e-alerts was not associated with lower hospital length of stay (mean difference, -0.09 [95% CI, -0.47 to 0.30] days) or lower cost (mean difference, US $655.26 [95% CI, -$656.98 to $1967.5]) but was associated with greater AKI documentation (RR, 1.28 [95% CI, 1.04-1.58]). Trial sequential analysis confirmed true-positive results of AKI e-alerts on increased nephrologist consultations and reduced post-AKI NSAID exposure and its lack of association with mortality.

Conclusions and Relevance

In this systematic review and meta-analysis, AKI e-alerts were not associated with a lower risk for mortality but were associated with changes in clinical practices. They were associated with lower risk for AKI progression. Further research is needed to confirm these results and integrate early AKI markers or prediction models to improve outcomes.

Utilizing electronic medical records alert to improve documentation of neonatal acute kidney injury

BACKGROUND

Neonatal acute kidney injury (AKI) is a common yet underdiagnosed condition in neonates with significant implications for long-term kidney health. Lack of timely recognition and documentation of AKI contributes to missed opportunities for nephrology consultation and follow-up, potentially leading to adverse outcomes.

METHODS

We conducted a quality improvement (QI) project to address this by incorporating an automated real-time electronic medical record (EMR)-AKI alert system in the Neonatal Intensive Care Unit (NICU) at Le Bonheur Children's Hospital. Our primary objective was to improve documentation of neonatal AKI (defined as serum creatinine (SCr) > 1.5 mg/dL) by 25% compared to baseline levels. The secondary goal was to increase nephrology consultations and referrals to the neonatal nephrology clinic. We designed an EMR-AKI alert system to trigger for neonates with SCr > 1.5 mg/dL, automatically adding AKI diagnosis to the problem list. This prompted physicians to consult nephrology, refer neonates to the nephrology clinic, and consider medication adjustments.

RESULTS

Our results demonstrated a significant improvement in AKI documentation after implementing the EMR-AKI alert, reaching 100% compared with 7% at baseline (p < 0.001) for neonates with SCr > 1.5 mg/dL. Although the increase in nephrology consultations was not statistically significant (p = 0.5), there was a significant increase in referrals to neonatal nephrology clinics (p = 0.005).

CONCLUSIONS

Integration of an EMR alert system with automated documentation offers an efficient and economical solution for improving neonatal AKI diagnosis and documentation. This approach enhances healthcare provider engagement, streamlines workflows, and supports QI. Widespread adoption of similar approaches can lead to improved patient outcomes and documentation accuracy in neonatal AKI care.

Effect of electronic records on mortality among patients in hospital and primary healthcare settings: a systematic review and meta-analyses

Background

Electronic medical records or electronic health records, collectively called electronic records, have significantly transformed the healthcare system and service provision in our world. Despite a number of primary studies on the subject, reports are inconsistent and contradictory about the effects of electronic records on mortality. Therefore, this review examined the effect of electronic records on mortality.

Methods

The review followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses 2020 guideline. Six databases: PubMed, EMBASE, Scopus, CINAHL, Cochrane Library, and Google Scholar, were searched from February 20 to October 25, 2023. Studies that assessed the effect of electronic records on mortality and were published between 1998 and 2022 were included. Joanna Briggs Institute quality appraisal tool was used to assess the methodological quality of the studies. Narrative synthesis was performed to identify patterns across studies. Meta-analysis was conducted using fixed effect and random-effects models to estimate the pooled effect of electronic records on mortality. Funnel plot and Egger's regression test were used to assess for publication bias.

Results

Fifty-four papers were found eligible for the systematic review, of which 42 were included in the meta-analyses. Of the 32 studies that assessed the effect of electronic health record on mortality, eight (25.00%) reported a statistically significant reduction in mortality, 22 (68.75%) did not show a statistically significant difference, and two (6.25%) studies reported an increased risk of mortality. Similarly, among the 22 studies that determined the effect of electronic medical record on mortality, 12 (54.55%) reported a statistically significant reduction in mortality, and ten (45.45%) studies didn't show a statistically significant difference. The fixed effect and random effects on mortality were OR = 0.95 (95% CI: 0.93-0.97) and OR = 0.94 (95% CI: 0.89-0.99), respectively. The associated I-squared was 61.5%. Statistical tests indicated that there was no significant publication bias among the studies included in the meta-analysis.

Conclusion

Despite some heterogeneity among the studies, the review indicated that the implementation of electronic records in inpatient, specialized and intensive care units, and primary healthcare facilities seems to result in a statistically significant reduction in mortality. Maturity level and specific features may have played important roles.

Systematic Review Registration

PROSPERO (CRD42023437257).

A proposed framework for advancing acute kidney injury risk stratification and diagnosis in children: a report from the 26th Acute Disease Quality Initiative (ADQI) conference

Acute kidney injury (AKI) in children is associated with increased morbidity, reduced health-related quality of life, greater resource utilization, and higher mortality. Improvements in the timeliness and precision of AKI diagnosis in children are needed. In this report, we highlight existing, novel, and on-the-horizon diagnostic and risk-stratification tools for pediatric AKI, and outline opportunities for integration into clinical practice. We also summarize pediatric-specific high-risk diagnoses and exposures for AKI, as well as the potential role of real-time risk stratification and clinical decision support to improve outcomes. Lastly, the key characteristics of important pediatric AKI phenotypes will be outlined. Throughout, we identify key knowledge gaps, which represent prioritized areas of focus for future research that will facilitate a comprehensive, timely and personalized approach to pediatric AKI diagnosis and management.

Automated Electronic Alert for the Care and Outcomes of Adults With Acute Kidney Injury: A Randomized Clinical Trial

Importance

Despite the expansion of published electronic alerts for acute kidney injury (AKI), there are still concerns regarding their effect on the clinical outcomes of patients.

Objective

To evaluate the effect of the AKI alert combined with a care bundle on the care and clinical outcomes of patients with hospital-acquired AKI.

Design, Setting, and Participants

This single-center, double-blind, parallel-group randomized clinical trial was conducted in a tertiary teaching hospital in Nanjing, China, from August 1, 2019, to December 31, 2021. The inclusion criteria were inpatient adults aged 18 years or older with AKI, which was defined using the Kidney Disease: Improving Global Outcomes creatinine criteria. Participants were randomized 1:1 to either the alert group or the usual care group, which were stratified by medical vs surgical ward and by intensive care unit (ICU) vs non-ICU setting. Analyses were conducted on the modified intention-to-treat population.

Interventions

A programmatic AKI alert system generated randomization automatically and sent messages to the mobile telephones of clinicians (alert group) or did not send messages (usual care group). A care bundle accompanied the AKI alert and consisted of general, nonindividualized, and nonmandatory AKI management measures.

Main Outcomes and Measures

The primary outcome was maximum change in estimated glomerular filtration rate (eGFR) within 7 days after randomization. Secondary patient-centered outcomes included death, dialysis, AKI progression, and AKI recovery. Care-centered outcomes included diagnostic and therapeutic interventions for AKI.

Results

A total of 2208 patients (median [IQR] age, 65 [54-72] years; 1560 males [70.7%]) were randomized to the alert group (n = 1123) or the usual care group (n = 1085) and analyzed. Within 7 days of randomization, median (IQR) maximum absolute changes in eGFR were 3.7 (-6.4 to 19.3) mL/min/1.73 m2 in the alert group and 2.9 (-9.2 to 16.9) mL/min/1.73 m2 in the usual care group (P = .24). This result was robust in all subgroups in an exploratory analysis. For care-centered outcomes, patients in the alert group had more intravenous fluids (927 [82.6%] vs 670 [61.8%]; P < .001), less exposure to nonsteroidal anti-inflammatory drugs (56 [5.0%] vs 119 [11.0%]; P < .001), and more AKI documentation at discharge (560 [49.9%] vs 296 [27.3%]; P < .001) than patients in the usual care group. No differences were observed in patient-centered secondary outcomes between the 2 groups.

Conclusions and Relevance

Results of this randomized clinical trial showed that the electronic AKI alert did not improve kidney function or other patient-centered outcomes but changed patient care behaviors. The findings warrant the use of a combination of high-quality interventions and AKI alert in future clinical practice.

Trial Registration

ClinicalTrials.gov Identifier: NCT03736304.

Adherence to guidelines for management of acute kidney injury

BACKGROUND AND AIM

Acute kidney injury (AKI) affects a significant number of patients and the prognosis for this condition remains poor. The aim of this study was to assess adherence to KDIGO clinical practice guidelines and identify areas for improvement.

METHODS

For this retrospective study, data were extracted from the medical database of the University Hospital Brandenburg, for patients who had been diagnosed with AKI from January to March 2021. Implementation rates of eight KDIGO AKI therapeutic measures were analyzed in relation to several AKI severity/risk categories.

RESULTS

Data from 200 patients were included in the study. Three specific measures were commonly implemented: hyperglycemia control (100%), volume therapy (82%), and fluid balance management (65%). Nephrotoxic medications were discontinued in 51% patients, while iodinated contrast media was used in 35% patients. Patients with an increased risk of complications, such as those requiring ICU therapy or with sepsis, received these measures more frequently.

CONCLUSIONS

While some 2012 KDIGO recommended measures were implemented for a substantial number of affected individuals, others were not. Our study highlights the need for improvement in the quality of care for patients with AKI.

Digital health and acute kidney injury: consensus report of the 27th Acute Disease Quality Initiative workgroup

Acute kidney injury (AKI), which is a common complication of acute illnesses, affects the health of individuals in community, acute care and post-acute care settings. Although the recognition, prevention and management of AKI has advanced over the past decades, its incidence and related morbidity, mortality and health care burden remain overwhelming. The rapid growth of digital technologies has provided a new platform to improve patient care, and reports show demonstrable benefits in care processes and, in some instances, in patient outcomes. However, despite great progress, the potential benefits of using digital technology to manage AKI has not yet been fully explored or implemented in clinical practice. Digital health studies in AKI have shown variable evidence of benefits, and the digital divide means that access to digital technologies is not equitable. Upstream research and development costs, limited stakeholder participation and acceptance, and poor scalability of digital health solutions have hindered their widespread implementation and use. Here, we provide recommendations from the Acute Disease Quality Initiative consensus meeting, which involved experts in adult and paediatric nephrology, critical care, pharmacy and data science, at which the use of digital health for risk prediction, prevention, identification and management of AKI and its consequences was discussed.

Electronic alert outpatient protocol improves the quality of care for the risk of postcontrast acute kidney injury following computed tomography

BACKGROUND

Prevention and diagnosis of postcontrast acute kidney injury (AKI) after contrast-enhanced computed tomography is burdensome in outpatient department. We investigated whether an electronic alert system could improve prevention and diagnosis of postcontrast AKI.

METHODS

In March 2018, we launched an electronic alert system that automatically identifies patients with a baseline estimated glomerular filtration rate of <45 mL/min/1.73 m2, provides a prescription of fluid regimen, and recommends a follow-up for serum creatinine measurement. Participants prescribed contrast-enhanced computed tomography at outpatient department before and after the launch of the system were categorized as historical and alert group, respectively. Propensity for the surveillance of postcontrast AKI was compared using logistic regression. Risks of AKI, admission, mortality, and renal replacement therapy were analyzed.

RESULTS

The historical and alert groups included 289 and 309 participants, respectively. The alert group was more likely to be men and take diuretics. The most frequent volume of prophylactic fluid in historical and alert group was 1,000 and 750 mL, respectively. Follow-up for AKI was more common in the alert group (adjusted odds ratio, 6.00; p < 0.001). Among them, incidence of postcontrast AKI was not statistically different. The two groups did not differ in risks of admission, mortality, or renal replacement therapy.

CONCLUSION

The electronic alert system could assist in the detection of high-risk patients, prevention with reduced fluid volume, and proper diagnosis of postcontrast AKI, while limiting the prescribing clinicians' burden. Whether the system can improve long-term outcomes remains unclear.

Clinical characteristics and outcomes of community acquired-acute kidney injury

PURPOSE

Published works have reported the impact of a nephrologist intervention on outcomes for patients with hospital-acquired acute kidney injury (HA-AKI), however little is known about the clinical characteristics of patients with community-acquired acute kidney injury (CA-AKI) and the impact of nephrology interventions on outcomes in these patients.

METHODS

A retrospective study on all adult patients admitted to a large tertiary care hospital in 2019 who were identified to have CA-AKI were followed from hospital admission to discharge. Clinical characteristics and outcomes of these patients were analysed by receipt of nephrology consultation. Statistical analysis included descriptive, simple Chi-squared/Fischer Exact test, independent samples t-test/Mann-Whitney U test and logistic regression.

RESULTS

182 patients fulfilled the study inclusion criteria. Mean age was 75 ± 14 years, 41% were female, 64% had stage 1 AKI on admission, 35% received nephrology input and 52% had achieved recovery of kidney function by discharge. Higher admission and discharge serum creatinine (SCr) (290.5 vs 159 and 173 vs 109 µmol/L respectively, p =  < 0.001), and younger age (68 vs 79, p =  < 0.001) were associated with nephrology consultations, whilst length of hospitalisation, mortality and rehospitalisation rates were not significantly different between the two groups. At least 65% were recorded to be on at least one nephrotoxic medication.

CONCLUSION

Our findings provide a snapshot of current practice where close to two-thirds of hospitalised patients with CA-AKI had a mild form of AKI that was associated with good clinical outcomes. While higher SCr on admission and younger age were predictors of receiving a nephrology consultation, nephrology consultations did not have any impact on outcomes.

Early recognition and prevention of acute kidney injury in hospitalised children

Acute kidney injury is common in hospitalised children and is associated with poor patient outcomes. Once acute kidney injury occurs, effective therapies to improve patient outcomes or kidney recovery are scarce. Early identification of children at risk of acute kidney injury or at an early injury stage is essential to prevent progression and mitigate complications. Paediatric acute kidney injury is under-recognised by clinicians, which is a barrier to optimisation of inpatient care and follow-up. Acute kidney injury definitions rely on functional biomarkers (ie, serum creatinine and urine output) that are inadequate, since they do not account for biological variability, analytical issues, or physiological responses to volume depletion. Improved predictive tools and diagnostic biomarkers of kidney injury are needed for earlier detection. Novel strategies, including biomarker-guided care algorithms, machine-learning methods, and electronic alerts tied to clinical decision support tools, could improve paediatric acute kidney injury care. Clinical prediction models should be studied in different paediatric populations and acute kidney injury phenotypes. Research is needed to develop and test prevention strategies for acute kidney injury in hospitalised children, including care bundles and therapeutics.

Perspectives of Pediatric Nephrologists, Intensivists and Nurses Regarding AKI Management and Expected Outcomes

Background

Acute kidney injury (AKI) in critically ill children is associated with increased risk for short- and long-term adverse outcomes. Currently, there is no systematic follow-up for children who develop AKI in intensive care unit (ICU).

Objective

This study aimed to assess variation regarding management, perceived importance, and follow-up of AKI in the ICU setting within and between healthcare professional (HCP) groups.

Design

Anonymous, cross-sectional, web-based surveys were administered nationally to Canadian pediatric nephrologists, pediatric intensive care unit (PICU) physicians, and PICU nurses, via professional listservs.

Setting

All Canadian pediatric nephrologists, PICU physicians, and nurses treating children in the ICU were eligible for the survey.

Patients

N/A.

Measurements

Surveys included multiple choice and Likert scale questions on current practice related to AKI management and long-term follow-up, including institutional and personal practice approaches, and perceived importance of AKI severity with different outcomes.

Methods

Descriptive statistics were performed. Categorical responses were compared using Chi-square or Fisher's exact tests; Likert scale results were compared using Mann-Whitney and Kruskal-Wallis tests.

Results

Surveys were completed by 34/64 (53%) pediatric nephrologists, 46/113 (41%) PICU physicians, and 82 PICU nurses (response rate unknown). Over 65% of providers reported hemodialysis to be prescribed by nephrology; a mix of nephrology, ICU, or a shared nephrology-ICU model was reported responsible for peritoneal dialysis and continuous renal replacement therapy (CRRT). Severe hyperkalemia was the most important renal replacement therapy (RRT) indication for both nephrologists and PICU physicians (Likert scale from 0 [not important] to 10 [most important]; median = 10, 10, respectively). Nephrologists reported a lower threshold of AKI for increased mortality risk; 38% believed stage 2 AKI was the minimum compared to 17% of PICU physicians and 14% of nurses. Nephrologists were more likely than PICU physicians and nurses to recommend long-term follow-up for patients who develop any AKI during ICU stay (Likert scale from 0 [none] to 10 [all patients]; mean=6.0, 3.8, 3.7, respectively) (P < .05).

Limitations

Responses from all eligible HCPs in the country could not obtained. There may be differences in opinions between HCPs that completed the survey compared to those that did not. Additionally, the cross-sectional design of our study may not adequately reflect changes in guidelines and knowledge since survey completion, although no specific guidelines have been released in Canada since survey dissemination.

Conclusions

Canadian HCP groups have variable perspectives on pediatric AKI management and follow-up. Understanding practice patterns and perspectives will help optimize pediatric AKI follow-up guideline implementation.

An Electronic Algorithm to Identify Vancomycin-Associated Acute Kidney Injury

Background

The burden of vancomycin-associated acute kidney injury (V-AKI) is unclear because it is not systematically monitored. The objective of this study was to develop and validate an electronic algorithm to identify cases of V-AKI and to determine its incidence.

Methods

Adults and children admitted to 1 of 5 health system hospitals from January 2018 to December 2019 who received at least 1 dose of intravenous (IV) vancomycin were included. A subset of charts was reviewed using a V-AKI assessment framework to classify cases as unlikely, possible, or probable events. Based on review, an electronic algorithm was developed and then validated using another subset of charts. Percentage agreement and kappa coefficients were calculated. Sensitivity and specificity were determined at various cutoffs, using chart review as the reference standard. For courses ≥48 hours, the incidence of possible or probable V-AKI events was assessed.

Results

The algorithm was developed using 494 cases and validated using 200 cases. The percentage agreement between the electronic algorithm and chart review was 92.5% and the weighted kappa was 0.95. The electronic algorithm was 89.7% sensitive and 98.2% specific in detecting possible or probable V-AKI events. For the 11 073 courses of ≥48 hours of vancomycin among 8963 patients, the incidence of possible or probable V-AKI events was 14.0%; the V-AKI incidence rate was 22.8 per 1000 days of IV vancomycin therapy.

Conclusions

An electronic algorithm demonstrated substantial agreement with chart review and had excellent sensitivity and specificity in detecting possible or probable V-AKI events. The electronic algorithm may be useful for informing future interventions to reduce V-AKI.

Effects and characteristics of clinical decision support systems on the outcomes of patients with kidney disease: a systematic review

OBJECTIVES

This systematic review was conducted to investigate the characteristics and effects of clinical decision support systems (CDSSs) on clinical and process-of-care outcomes of patients with kidney disease.

METHODS

A comprehensive systematic search was conducted in electronic databases to identify relevant studies published until November 2020. Randomized clinical trials evaluating the effects of using electronic CDSS on at least one clinical or process-of-care outcome in patients with kidney disease were included in this study. The characteristics of the included studies, features of CDSSs, and effects of the interventions on the outcomes were extracted. Studies were appraised for quality using the Cochrane risk-of-bias assessment tool.

RESULTS

Out of 8722 retrieved records, 11 eligible studies measured 32 outcomes, including 10 clinical outcomes and 22 process-of-care outcomes. The effects of CDSSs on 45.5% of the process-of-care outcomes were statistically significant, and all the clinical outcomes were not statistically significant. Medication-related process-of-care outcomes were the most frequently measured (54.5%), and CDSSs had the most effective and positive effect on medication appropriateness (18.2%). The characteristics of CDSSs investigated in the included studies comprised automatic data entry, real-time feedback, providing recommendations, and CDSS integration with the Computerized Provider Order Entry system.

CONCLUSION

Although CDSS may potentially be able to improve processes of care for patients with kidney disease, particularly with regard to medication appropriateness, no evidence was found that CDSS affects clinical outcomes in these patients. Further research is thus required to determine the effects of CDSSs on clinical outcomes in patients with kidney diseases.

Predicting outcomes of continuous renal replacement therapy using body composition monitoring: a deep-learning approach

Fluid balance is a critical prognostic factor for patients with severe acute kidney injury (AKI) requiring continuous renal replacement therapy (CRRT). This study evaluated whether repeated fluid balance monitoring could improve prognosis in this clinical population. This was a multicenter retrospective study that included 784 patients (mean age, 67.8 years; males, 66.4%) with severe AKI requiring CRRT during 2017-2019 who were treated in eight tertiary hospitals in Korea. Sequential changes in total body water were compared between patients who died (event group) and those who survived (control group) using mixed-effects linear regression analyses. The performance of various machine learning methods, including recurrent neural networks, was compared to that of existing prognostic clinical scores. After adjusting for confounding factors, a marginal benefit of fluid balance was identified for the control group compared to that for the event group (p = 0.074). The deep-learning model using a recurrent neural network with an autoencoder and including fluid balance monitoring provided the best differentiation between the groups (area under the curve, 0.793) compared to 0.604 and 0.606 for SOFA and APACHE II scores, respectively. Our prognostic, deep-learning model underlines the importance of fluid balance monitoring for prognosis assessment among patients receiving CRRT.

Electronic alerts and a care bundle for acute kidney injury-an Australian cohort study

BACKGROUND

Early recognition of hospital-acquired acute kidney injury (AKI) may improve patient management and outcomes.

METHODS

This multicentre study was conducted at three hospitals (H1-intervention; H2 and H3-controls) served by a single laboratory. The intervention bundle [an interruptive automated alerts (aAlerts) showing AKI stage and baseline creatinine in the eMR, a management guide and junior medical staff education] was implemented only at H1. Outcome variables included length-of-stay (LOS), all-cause in-hospital mortality and management quality.

RESULTS

Over 6 months, 639 patients developed AKI (265 at H1 and 374 at controls), with 94.7% in general wards; 537 (84%) patients developed Stage 1, 58 (9%) Stage 2 and 43 (7%) Stage 3 AKI. Median LOS was 9 days (IQR 4-17) and was not different between intervention and controls. However, patients with AKI stage 1 had shorter LOS at H1 [median 8 versus 10 days (P = 0.021)]. Serum creatinine had risen prior to admission in most patients. Documentation of AKI was better in H1 (94.8% versus 83.4%; P = 0.001), with higher rates of nephrology consultation (25% versus 19%; P = 0.04) and cessation of nephrotoxins (25.3 versus 18.8%; P = 0.045). There was no difference in mortality between H1 versus controls (11.7% versus 13.0%; P = 0.71).

CONCLUSIONS

Most hospitalized patients developed Stage 1 AKI and developed AKI in the community and remained outside the intensive care unit (ICU). The AKI eAlert bundle reduced LOS in most patients with AKI and increased AKI documentation, nephrology consultation rate and cessation of nephrotoxic medications.

Consulting to nephrologist when starting continuous renal replacement therapy for acute kidney injury is associated with a survival benefit

BACKGROUND

Several studies suggest improved outcomes for patients with kidney disease who consult a nephrologist. However, it remains undetermined whether a consultation with a nephrologist is related to a survival benefit after starting continuous renal replacement therapy (CRRT) due to acute kidney injury (AKI).

METHODS

Data from 2,397 patients who started CRRT due to severe AKI at Seoul National University Hospital, Korea between 2010 and 2020 were retrospectively collected. The patients were divided into two groups according to whether they underwent a nephrology consultation regarding the initiation and maintenance of CRRT. The Cox proportional hazards model was used to calculate the hazard ratio (HR) of mortality during admission to the intensive care unit after adjusting for multiple variables.

RESULTS

A total of 2,153 patients (89.8%) were referred to nephrologists when starting CRRT. The patients who underwent a nephrology consultation had a lower mortality rate than those who did not have a consultation (HR = 0.47 [0.40-0.56]; P < 0.001). Subsequently, patients who had nephrology consultations were divided into two groups (i.e., early and late) according to the timing of the consultation. Both patients with early and late consultation had lower mortality rates than patients without consultations, with HRs of 0.45 (0.37-0.54) and 0.51 (0.42-0.61), respectively.

CONCLUSIONS

Consultation with a nephrologist may contribute to a survival benefit after starting CRRT for AKI.

Acceptance of Acute Kidney Injury Alert by Providers in Cardiac Surgery Intensive Care Unit

BACKGROUND

Acute kidney injury (AKI) is a common complication after cardiac surgery and is associated with worse outcomes. Its management relies on early diagnosis, and therefore, electronic alerts have been used to alert clinicians for development of AKI. Electronic alerts are, however, associated with high rates of alert fatigue.

OBJECTIVES

We designed this study to assess the acceptance of user-centered electronic AKI alert by clinicians.

METHODS

We developed a user-centered electronic AKI alert that alerted clinicians of development of AKI in a persistent yet noninterruptive fashion. As the goal of the alert was to alert toward new or worsening AKI, it disappeared 48 hours after being activated. We assessed the acceptance of the alert using surveys at 6 and 12 months after the alert went live.

RESULTS

At 6 months after their implementation, 38.9% providers reported that they would not have recognized AKI as early as they did without this alert. This number increased to 66.7% by 12 months of survey. Most providers also shared that they re-dosed or discontinued medications earlier, provided earlier management of volume status, avoided intravenous contrast use, and evaluated patients by using point-of-care ultrasounds more due to the alert. Overall, 83.3% respondents reported satisfaction with the electronic AKI alerts at 6 months and 94.4% at 12 months.

CONCLUSION

This study showed high rates of acceptance of a user-centered electronic AKI alert over time by clinicians taking care of patients with AKI.

Impact of an Electronic Alert in Combination with a Care Bundle on the Outcomes of Acute Kidney Injury

Early diagnosis is essential for the appropriate management of acute kidney injury (AKI). We evaluated the impact of an electronic AKI alert together with a care bundle on the progression and mortality of AKI. This was a single-center prospective study that included AKI patients aged ≥ 18 years, whereas those in palliative care, nephrology, and transplantation departments were excluded. An AKI alert was issued in electronic medical records and a care bundle was suggested. A series of classes were administered to the multidisciplinary teams by nephrologists, and a clinical pharmacist audited prescriptions. Patients were categorized into pre-alert and post-alert groups. The baseline characteristics were comparable between the pre-alert (n = 1613) and post-alert (n = 1561) groups. The 30-day mortality rate was 33.6% in the entire cohort and was lower in the post-alert group (30.5% vs. 36.7%; p < 0.001). Age, pulmonary disease, malignancy, and ICU admission were associated with an increase in 30-day mortality. The electronic AKI alert together with a care bundle and a multidisciplinary education program was associated with a reduction in 30-day mortality in patients with AKI.

Opportunities in digital health and electronic health records for acute kidney injury care

PURPOSE OF REVIEW

The field of digital health is evolving rapidly with applications relevant to the prediction, detection and management of acute kidney injury (AKI). This review will summarize recent publications in these areas.

RECENT FINDINGS

Machine learning (ML) approaches have been applied predominantly for AKI prediction, but also to identify patients with AKI at higher risk of adverse outcomes, and to discriminate different subgroups (subphenotypes) of AKI. There have been multiple publications in this area, but a smaller number of ML models have robust external validation or the ability to run in real-time in clinical systems. Recent studies of AKI alerting systems and clinical decision support systems continue to demonstrate variable results, which is likely to result from differences in local context and implementation strategies. In the design of AKI alerting systems, choice of baseline creatinine has a strong effect on performance of AKI detection algorithms.

SUMMARY

Further research is required to overcome barriers to the validation and implementation of ML models for AKI care. Simpler electronic systems within the electronic medical record can lead to improved care in some but not all settings, and careful consideration of local context and implementation strategy is recommended.

Derivation and evaluation of baseline creatinine equations for hospitalized children and adolescents: the AKI baseline creatinine equation

BACKGROUND

Acute kidney injury (AKI) definitions incorporate baseline creatinine (Cr_b) values, but Cr_b are frequently unknown in pediatrics. Our primary aim was to derive and validate a novel AKI Baseline Creatinine (ABC) estimation equation and compare it to existing methods of estimating Cr_b values.

METHODS

We conducted a single-center retrospective analysis of pediatric patients (0-25 years) admitted from 2012 to 2019. Included patients required at least one outpatient Cr_b prior to hospitalization (gold standard). Novel equations were developed with demographic and initial creatinine data. Existing methods included back-calculating Cr_b based on Schwartz, Full Age Spectrum (FAS), and CKiD-under-25 (U25) equations. To determine an optimal equation, we compared novel and existing equations to the gold standard.

RESULTS

The optimal simplified equation (ABC) included only age and had R² = 59.9% and 73.2% of values within 30% of true Cr_b. The precision increased significantly when the equation included age and minimum creatinine within initial 72 h (ABC-cr): R² = 75.4% and 86.5% of values within 30% of true Cr_b. The best performing existing equation was the age-based FAS, which had R² = 61.0% and 78.0% of values within 30% of true Cr_b. All other existing equations performed worse, some methods as low as 52.6% within 30% of true Cr_b.

CONCLUSIONS

The newly derived ABC equation is simple, and the ABC-cr equation can more accurately estimate Cr_b by ≥ 25% compared to previous methods. The potential applicability of these equations is vast, including faster recognition of AKI on initial patient contact and improved standardization of pediatric AKI definitions, enhancing health services research. A higher resolution version of the Graphical abstract is available as Supplementary information.

A Prediction Model for Acute Kidney Injury in Adult Patients With Minimal Change Disease

Background

Early prediction of acute kidney injury (AKI) can allow for timely interventions, but there are still few methods that are easy and convenient to apply in predicting AKI, specially targeted at patients with minimal change disease (MCD). Motivated by this, we aimed to develop a predicting model for AKI in patients with MCD within the KDIGO criteria.

Methods

Data on 401 hospitalized adult patients, whose biopsy was diagnosed as MCD from 12/31/2010 to 15/7/2021, were retrospectively collected. Among these data, patients underwent biopsy earlier formed the training set (n = 283), while the remaining patients formed the validation set (n = 118). Independent risk factors associated with AKI were analyzed. From this, the prediction model was developed and nomogram was plotted.

Results

AKI was found in 55 of 283 patients (19%) and 15 of 118 patients (13%) in the training and validation cohorts, respectively. According to the results from lasso regression and logistic regression, it was found that four factors, including mean arterial pressure, serum albumin, uric acid, and lymphocyte counts, were independent of the onset of AKI. Incorporating these factors, the nomogram achieved a reasonably good concordance index of 0.84 (95%CI 0.77–0.90) and 0.75 (95%CI 0.62–0.87) in predicting AKI in the training and validation cohorts, respectively. Decision curve analysis suggested clinical benefit of the prediction models.

Conclusions

Our predictive nomogram provides a feasible approach to identify high risk MCD patients who might develop AKI, which might facilitate the timely treatment.

Effect of Early Nutritional Support on Clinical Outcomes of Critically Ill Patients with Sepsis and Septic Shock: A Single-Center Retrospective Study

The initial nutritional delivery policy for patients with sepsis admitted to the intensive care unit (ICU) has not been fully elucidated. We aimed to determine whether an initial adequate nutrition supply and route of nutrition delivery during the first week of sepsis onset improve clinical outcomes of critically ill patients with sepsis. We reviewed adult patients with sepsis and septic shock in the ICU in a single tertiary teaching hospital between 31 November 2013 and 20 May 2017. Poisson log-linear and Cox regressions were performed to assess the relationships between clinical outcomes and sex, modified nutrition risk in the critically ill score, sequential organ failure assessment score, route of nutrition delivery, acute physiology and chronic health evaluation score, and daily energy and protein delivery during the first week of sepsis onset. In total, 834 patients were included. Patients who had a higher protein intake during the first week of sepsis onset had a lower in-hospital mortality (adjusted hazard ratio (HR), 0.55; 95% confidence interval (CI), 0.39−0.78; p = 0.001). A higher energy intake was associated with a lower 30-day mortality (adjusted HR, 0.94; 95% CI, 0.90−0.98; p = 0.003). The route of nutrition delivery was not associated with 1-year mortality in the group which was underfed; however, in patients who met > 70% of their nutritional requirement, enteral feeding (EN) with supplemental parenteral nutrition (PN) was superior to only EN (p = 0.016) or PN (p = 0.042). In patients with sepsis and septic shock, a high daily average protein intake may lower in-hospital mortality, and a high energy intake may lower the 30-day mortality, especially in those with a high modified nutrition risk in the critically ill scores. In patients who receive adequate energy, EN with supplemental PN may be better than only EN or PN, but not in underfed patients.

Role of artificial intelligence in the diagnosis and management of kidney disease: applications to chronic kidney disease and acute kidney injury

PURPOSE OF REVIEW

Chronic kidney disease (CKD) and acute kidney injury (AKI) are global public health problems associated with a significant burden of morbidity, healthcare resource use, and all-cause mortality. This review explores recently published studies that take a machine learning approach to the diagnosis, management, and prognostication in patients with AKI or CKD.

RECENT FINDINGS

The release of novel therapeutics for CKD has highlighted the importance of accurately identifying patients at the highest risk of progression. Many models have been constructed with reasonable predictive accuracy but have not been extensively externally validated and peer reviewed. Similarly, machine learning models have been developed for prediction of AKI and have found sufficient accuracy. There are issues to implementing these models, however, with conflicting results with respect to the relationship between prediction of an AKI outcome and improvements in the occurrence of other adverse events, and in some circumstances potential harm.

SUMMARY

Artificial intelligence models can help guide management of CKD and AKI, but it is important to ensure that they are broadly applicable and generalizable to various settings and associated with improved clinical decision-making and outcomes.

The Impact of Health Information Technology for Early Detection of Patient Deterioration on Mortality and Length of Stay in the Hospital Acute Care Setting: Systematic Review and Meta-Analysis

OBJECTIVE

To evaluate the impact of health information technology (HIT) for early detection of patient deterioration on patient mortality and length of stay (LOS) in acute care hospital settings.

DATA SOURCES

We searched MEDLINE and Epub Ahead of Print, In-Process & Other Non-Indexed Citations and Daily, Embase, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Scopus from 1990 to January 19, 2021.

STUDY SELECTION

We included studies that enrolled patients hospitalized on the floor, in the ICU, or admitted through the emergency department. Eligible studies compared HIT for early detection of patient deterioration with usual care and reported at least one end point of interest: hospital or ICU LOS or mortality at any time point.

DATA EXTRACTION

Study data were abstracted by two independent reviewers using a standardized data extraction form.

DATA SYNTHESIS

Random-effects meta-analysis was used to pool data. Among the 30 eligible studies, seven were randomized controlled trials (RCTs) and 23 were pre-post studies. Compared with usual care, HIT for early detection of patient deterioration was not associated with a reduction in hospital mortality or LOS in the meta-analyses of RCTs. In the meta-analyses of pre-post studies, HIT interventions demonstrated a significant association with improved hospital mortality for the entire study cohort (odds ratio, 0.78 [95% CI, 0.70-0.87]) and reduced hospital LOS overall.

CONCLUSIONS

HIT for early detection of patient deterioration in acute care settings was not significantly associated with improved mortality or LOS in the meta-analyses of RCTs. In the meta-analyses of pre-post studies, HIT was associated with improved hospital mortality and LOS; however, these results should be interpreted with caution. The differences in patient outcomes between the findings of the RCTs and pre-post studies may be secondary to confounding caused by unmeasured improvements in practice and workflow over time.

An Early Warning System for the Differential Diagnosis of In-Hospital Acute Kidney Injury for Better Patient Outcome: Study of a Quality Improvement Initiative

Background: Acute kidney injury (AKI) is a syndrome with heterogeneous causes and mechanisms. An early warning system (EWS) for AKI was created to reduce the incidence and improve outcomes. However, the benefits of AKI-EWS remain debatable. Methods: We launched a project to design and create AKI-EWS for inpatients in our institute. Incidence of AKI and its outcome before and after the implementation of AKI-EWS were collected for analysis. Results: We enlisted a stakeholder map before creating AKI-EWS. We then started an action plan for this initiative. The diagnosis was automatic and based on the definition of Kidney Disease: Improving Global Outcomes (KDIGO). The differential diagnosis of causes of AKI was also automatic. Users are to adjust the threshold of detection. After the implementation of this AKI-EWS, the incidence of AKI fell. The proportion of AKI > 4% was reduced significantly (47.7% and 41.6%, p = 0.010) in patients with serum creatinine measured. The proportion of AKI > 0.9% also dropped significantly (51.67% and 35.94%, p = 0.024) in all inpatients. Trends of AKI outcomes also showed improvement. The loading of consultation of nephrologists decreased by 15.5%. Conclusions: Through well-designed AKI-EWS, the incidence of AKI dropped, showing improved outcomes. The factors affecting benefits from AKI-EWS included high-risk identification (individual threshold detection), timely and automatic diagnosis, real-time alerting on electronic health information systems, fast self-diagnosing of the cause of AKI, and coverage of all inpatients.

Nephrotoxins and acute kidney injury - The consensus of the Taiwan acute kidney injury Task Force

The Taiwan Acute Kidney Injury (AKI) Task Force conducted a review of data and developed a consensus regarding nephrotoxins and AKI. This consensus covers: (1) contrast-associated AKI; (2) drug-induced nephrotoxicity; (3) prevention of drug-associated AKI; (4) follow up after AKI; (5) re-initiation of medication after AKI. Strategies for the avoidance of contrast media related AKI, including peri-procedural hydration, sodium bicarbonate solutions, oral N-acetylcysteine, and iso-osmolar/low-osmolar non-ionic iodinated contrast media have been recommended, given the respective evidence levels. Regarding anticoagulants, both warfarin and new oral anticoagulants have potential nephrotoxicity, and dosage should be reduced if renal pathology exam proves renal injury. Recommended strategies to prevent drug related AKI have included assessment of 5R/(6R) reactions - risk, recognition, response, renal support, rehabilitation and (research), use of AKI alert system and computerized decision support. In terms of antibiotics-associated AKI, avoiding concomitant administration of vancomycin and piperacillin-tazobactam, monitoring vancomycin trough level, switching from vancomycin to teicoplanin in high-risk patients, and replacing conventional amphotericin B with lipid-based amphotericin B have been shown to reduce drug related AKI. With respect to non-steroidal anti-inflammatory drug associated AKI, it is recommended to use these drugs cautiously in the elderly and in patients receiving renin-angiotensin-aldosterone system inhibitors/diuretics triple combinations.

Hospital-Acquired Acute Kidney Injury in Noncritical Care Setting: Clinical Characteristics and Outcomes

BACKGROUND

There is limited Australian data on the incidence and outcomes of hospital-acquired acute kidney injury (HA-AKI) in noncritically ill patients.

AIMS

This study aimed to characterise HA-AKI and assess the impact of nephrology consultations on outcomes.

METHODS

A retrospective cohort of all noncritically ill patients with HA-AKI admitted to a large tertiary hospital in 2018 were followed up from hospital admission to discharge. HA-AKI was defined using the Kidney Disease Improving Global Outcomes (KDIGO) criteria. The primary outcome of this study was the clinical characteristics of patients who developed HA-AKI and the difference in these characteristics by nephrology consultation.

RESULTS

A total of 222 noncritically ill patients were included in the study. The mean age of included patients was 74.8 ± 15.8 years and 57.2% were females. While most patients (92%)were characterised to have KDIGO stage 1, 14% received a nephrology consultation, and 80% had complete or partial recovery of kidney function at discharge. Lower recovery rates (65% versus 83%, P = 0.022), longer hospitalisations (10 versus 5 days, P = 0.001), and higher serum creatinine values on discharge (152 versus 101 μmol/L, P < 0.001) were associated with receipt of nephrology consultation. There was no difference in mortality rates (13% versus 11%, P = 0.754) between those with and without nephrology consultation.

CONCLUSIONS

Our findings indicate that signficant proportion of noncritically ill patients experience mild form of AKI and have good recovery of kidney function during hospitalisation. Although severity of AKI and length of hospitalisation were associated with nephrology interventions, large scale study is required to understand the impact of such interventions on clinical outcomes, such as hospital readmission and mortality.

A deep-learning model to continuously predict severe acute kidney injury based on urine output changes in critically ill patients

BACKGROUND

Acute Kidney Injury (AKI), a frequent complication of pateints in the Intensive Care Unit (ICU), is associated with a high mortality rate. Early prediction of AKI is essential in order to trigger the use of preventive care actions.

METHODS

The aim of this study was to ascertain the accuracy of two mathematical analysis models in obtaining a predictive score for AKI development. A deep learning model based on a urine output trends was compared with a logistic regression analysis for AKI prediction in stages 2 and 3 (defined as the simultaneous increase of serum creatinine and decrease of urine output, according to  the Acute Kidney Injury Network (AKIN) guidelines). Two retrospective datasets including 35,573 ICU patients were analyzed. Urine output data were used to train and test the logistic regression and the deep learning model.

RESULTS

The deep learning model defined an area under the curve (AUC) of 0.89 (± 0.01), sensitivity = 0.8 and specificity = 0.84, which was higher than the logistic regression analysis. The deep learning model was able to predict 88% of AKI cases more than 12 h before their onset: for every 6 patients identified as being at risk of AKI by the deep learning model, 5 experienced the event. On the contrary, for every 12 patients not considered to be at risk by the model, 2 developed AKI.

CONCLUSION

In conclusion, by using urine output trends, deep learning analysis was able to predict AKI episodes more than 12 h in advance, and with a higher accuracy than the classical urine output thresholds. We suggest that this algorithm could be integrated in the ICU setting to better manage, and potentially prevent, AKI episodes.

Does Artificial Intelligence Make Clinical Decision Better? A Review of Artificial Intelligence and Machine Learning in Acute Kidney Injury Prediction

Acute kidney injury (AKI) is a common complication of hospitalization that greatly and negatively affects the short-term and long-term outcomes of patients. Current guidelines use serum creatinine level and urine output rate for defining AKI and as the staging criteria of AKI. However, because they are not sensitive or specific markers of AKI, clinicians find it difficult to predict the occurrence of AKI and prescribe timely treatment. Advances in computing technology have led to the recent use of machine learning and artificial intelligence in AKI prediction, recent research reported that by using electronic health records (EHR) the AKI prediction via machine-learning models can reach AUROC over 0.80, in some studies even reach 0.93. Our review begins with the background and history of the definition of AKI, and the evolution of AKI risk factors and prediction models is also appraised. Then, we summarize the current evidence regarding the application of e-alert systems and machine-learning models in AKI prediction.

Renal Recovery after the Implementation of an Electronic Alert and Biomarker-Guided Kidney-Protection Strategy following Major Surgery

Background: The facilitation of early recovery of acute kidney injury (AKI) is an important step to improve outcome, particularly because of the limited therapeutic interventions currently available for AKI. The combination of an electronic alert and biomarker-guided kidney-protection strategy implemented in the routine care may have an impact on the incidence of early complete reversal of AKI after major non-cardiac surgery. Methods: We studied 294 patients in two cohorts before (n = 151) and after protocol implementation (n = 143). Data collection required 6 months for each cohort. The kidney-protection protocol included an electronic alert to detect patients who were eligible for urinary biomarker [TIMP2 × IGFBP7]-guided kidney-protection intervention. Intervention was stratified according to three levels of immediate AKI risk: low, moderate, and high. After intervention, postoperative changes in the glomerular filtration rate (eGFR) were identified with a tracking software that included an alert for nephrology consultation if the eGFR had declined by >25% from the preoperative reference value. Primary outcome was early AKI recovery, i.e., the complete reversal of any AKI stage to absence of AKI within the first 7 postoperative days. Results: Protocol implementation significantly increased the recovery of AKI (36/46, 78% compared to control 27/48, 56%, (p = 0.025)) and reduced the length of the ICU stay (p < 0.001). There was no significant difference in the overall incidence of all AKI and moderate and severe AKI in the first 7 postoperative days: 46/143 (32%) and 12/151 (8%) in the protocol implementation group compared to 48/151 (32%) and 18/151 (12%) in the historical control group. Patients with AKI reversal within the first 7 postoperative days had lower in-hospital mortality than patients without AKI reversal. Conclusions: Implementing a combined electronic alert and biomarker-guided kidney-protection strategy in routine care improved early recovery of AKI after major surgery.

Renal outcomes of laparoscopic versus open surgery in patients with rectal cancer: a propensity score analysis

Background

A laparoscopic approach is widely used in abdominal surgery. Although several studies have compared surgical and oncological outcomes between laparoscopic surgery (LS) and open surgery (OS) in rectal cancer patients, there have been few studies on postoperative renal outcomes.

Methods

We conducted a retrospective cohort study involving 1,633 patients who underwent rectal cancer surgery between 2003 and 2017. Postoperative acute kidney injury (AKI) was diagnosed according to the serum creatinine criteria of the Kidney Disease: Improving Global Outcomes classification.

Results

Among the 1,633 patients, 1,072 (65.6%) underwent LS. After matching propensity scores, 395 patients were included in each group. The incidence of postoperative AKI in the LS group was significantly lower than in the OS group (9.9% vs. 15.9%; p = 0.01). Operation time, estimated blood loss, and incidence of transfusion in the LS group were significantly lower than those in the OS group. Cox proportional hazard models revealed that LS was associated with decreased risk of postoperative AKI (hazard ratio [HR], 0.599; 95% confidence interval [CI], 0.402–0.893; p = 0.01) and postoperative transfusion was associated with increased risk of AKI (HR, 2.495; 95% CI, 1.529–4.072; p < 0.001). In the subgroup analysis, the incidence of postoperative AKI in patients with middle or high rectal cancer who underwent LS was much lower than in those who underwent OS (HR, 0.373; 95% CI, 0.197–0.705; p = 0.002).

Conclusion

This study showed that LS may have a favorable effect on the development of postoperative AKI in patients with rectal cancer.

Effect of clinical decision support systems on clinical outcome for acute kidney injury: a systematic review and meta-analysis

Background

Clinical decision support systems including both electronic alerts and care bundles have been developed for hospitalized patients with acute kidney injury.

Methods

Electronic databases were searched for randomized, before-after and cohort studies that implemented a clinical decision support system for hospitalized patients with acute kidney injury between 1990 and 2019. The studies must describe their impact on care processes, patient-related outcomes, or hospital length of stay. The clinical decision support system included both electronic alerts and care bundles.

Results

We identified seven studies involving 32,846 participants. Clinical decision support system implementation significantly reduced mortality (OR 0.86; 95 % CI, 0.75–0.99; p = 0.040, I² = 65.3 %; n = 5 studies; N = 30,791 participants) and increased the proportion of acute kidney injury recognition (OR 3.12; 95 % CI, 2.37–4.10; p < 0.001, I² = 77.1 %; n = 2 studies; N = 25,121 participants), and investigations (OR 3.07; 95 % CI, 2.91–3.24; p < 0.001, I² = 0.0 %; n = 2 studies; N = 25,121 participants).

Conclusions

Nonrandomized controlled trials of clinical decision support systems for acute kidney injury have yielded evidence of improved patient-centered outcomes and care processes. This review is limited by the low number of randomized trials and the relatively short follow-up period.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12882-021-02459-y.

Scoping review exploring the impact of digital systems on processes and outcomes in the care management of acute kidney injury and progress towards establishing learning healthcare systems

OBJECTIVES

Digital systems have long been used to improve the quality and safety of care when managing acute kidney injury (AKI). The availability of digitised clinical data can also turn organisations and their networks into learning healthcare systems (LHSs) if used across all levels of health and care. This review explores the impact of digital systems i.e. on patients with AKI care, to gauge progress towards establishing LHSs and to identify existing gaps in the research.

METHODS

Embase, PubMed, MEDLINE, Cochrane, Scopus and Web of Science databases were searched. Studies of real-time or near real-time digital AKI management systems which reported process and outcome measures were included.

RESULTS

Thematic analysis of 43 studies showed that most interventions used real-time serum creatinine levels to trigger responses to enable risk prediction, early recognition of AKI or harm prevention by individual clinicians (micro level) or specialist teams (meso level). Interventions at system (macro level) were rare. There was limited evidence of change in outcomes.

DISCUSSION

While the benefits of real-time digital clinical data at micro level for AKI management have been evident for some time, their application at meso and macro levels is emergent therefore limiting progress towards establishing LHSs. Lack of progress is due to digital maturity, system design, human factors and policy levers.

CONCLUSION

Future approaches need to harness the potential of interoperability, data analytical advances and include multiple stakeholder perspectives to develop effective digital LHSs in order to gain benefits across the system.

A simulation-based evaluation of machine learning models for clinical decision support: application and analysis using hospital readmission

The interest in applying machine learning in healthcare has grown rapidly in recent years. Most predictive algorithms requiring pathway implementations are evaluated using metrics focused on predictive performance, such as the c statistic. However, these metrics are of limited clinical value, for two reasons: (1) they do not account for the algorithm's role within a provider workflow; and (2) they do not quantify the algorithm's value in terms of patient outcomes and cost savings. We propose a model for simulating the selection of patients over time by a clinician using a machine learning algorithm, and quantifying the expected patient outcomes and cost savings. Using data on unplanned emergency department surgical readmissions, we show that factors such as the provider's schedule and postoperative prediction timing can have major effects on the pathway cohort size and potential cost reductions from preventing hospital readmissions.

Changing trends in dialysis modalities utilization and mortality in children, adolescents and young adults with acute kidney injury, 2010-2017

The aim of the study was to assess trends in the relative use of dialysis modalities in the hospital-based pediatric cohort and to determine risk factors associated with in-hospital morality among pediatric patients receiving dialysis for acute kidney injury (AKI). Patients aged < 20 years who received dialysis between 2010 and 2017 were identified from electronic health records databases of a Taiwan's healthcare delivery system. The annual uses of intermittent hemodialysis (HD), continuous and automated peritoneal dialysis (PD) and continuous kidney replacement therapy (CKRT) were assessed using Cochran-Armitage Tests for trend. Among patients who received their first dialysis as inpatients for AKI, a multivariate logistic regression model was employed to assess mortality risks associated with dialysis modalities, patient demographics, complexity of baseline chronic disease, and healthcare service use during their hospital stays. Kidney dialysis was performed 37.9 per patient per year over the study period. Intermittent hemodialysis (HD) (73.3%) was the most frequently used dialysis modality. In the inpatient setting, the relative annual use of CKRT increased over the study period, while HD use concomitantly declined (P < 0.0001). The overall in-hospital mortality rate after dialysis for AKI was 33.6%, which remained steady over time (P = 0.2411). Patients aged < 2 years [adjusted odds ratio: (aOR) 3.36; 95% confidence interval (CI) 1.34-8.93] and greater vasoactive regimen use (aOR: 17.1; 95% CI: 5.3-55.21) were significantly associated with dialysis-related mortality. Overall treatment modality used for dialysis in pediatric patients increased slowly in the study period, and HD and CRKT modality uses largely evolved in the inpatient setting. Younger ages and use of more vasoactive medication regimens were independently associated with increased early mortality in patients on AKI-dialysis.

The importance of the urinary output criterion for the detection and prognostic meaning of AKI

Most reports on AKI claim to use KDIGO guidelines but fail to include the urinary output (UO) criterion in their definition of AKI. We postulated that ignoring UO alters the incidence of AKI, may delay diagnosis of AKI, and leads to underestimation of the association between AKI and ICU mortality. Using routinely collected data of adult patients admitted to an intensive care unit (ICU), we retrospectively classified patients according to whether and when they would be diagnosed with KDIGO AKI stage ≥ 2 based on baseline serum creatinine (Screa) and/or urinary output (UO) criterion. As outcomes, we assessed incidence of AKI and association with ICU mortality. In 13,403 ICU admissions (62.2% male, 60.8 ± 16.8 years, SOFA 7.0 ± 4.1), incidence of KDIGO AKI stage ≥ 2 was 13.2% when based only the SCrea criterion, 34.3% when based only the UO criterion, and 38.7% when based on both criteria. By ignoring the UO criterion, 66% of AKI cases were missed and 13% had a delayed diagnosis. The cause-specific hazard ratios of ICU mortality associated with KDIGO AKI stage ≥ 2 diagnosis based on only the SCrea criterion, only the UO criterion and based on both criteria were 2.11 (95% CI 1.85–2.42), 3.21 (2.79–3.69) and 2.85 (95% CI 2.43–3.34), respectively. Ignoring UO in the diagnosis of KDIGO AKI stage ≥ 2 decreases sensitivity, may lead to delayed diagnosis and results in underestimation of KDIGO AKI stage ≥ 2 associated mortality.

Convolutional Neural Network Model for Intensive Care Unit Acute Kidney Injury Prediction

INTRODUCTION

Acute kidney injury (AKI) is common among hospitalized patients and has a significant impact on morbidity and mortality. Although early prediction of AKI has the potential to reduce adverse patient outcomes, it remains a difficult condition to predict and diagnose. The purpose of this study was to evaluate the ability of a machine learning algorithm to predict for AKI as defined by Kidney Disease: Improving Global Outcomes (KDIGO) stage 2 or 3 up to 48 hours in advance of onset using convolutional neural networks (CNNs) and patient electronic health record (EHR) data.

METHODS

A CNN prediction system was developed to use EHR data gathered during patients' stays to predict AKI up to 48 hours before onset. A total of 12,347 patient encounters were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) database. An XGBoost AKI prediction model and the sequential organ failure assessment (SOFA) scoring system were used as comparators. The outcome was AKI onset. The model was trained on routinely collected patient EHR data. Measurements included area under the receiver operating characteristic (AUROC) curve, positive predictive value (PPV), and a battery of additional performance metrics for advance prediction of AKI onset.

RESULTS

On a hold-out test set, the algorithm attained an AUROC of 0.86 and PPV of 0.24, relative to a cohort AKI prevalence of 7.62%, for long-horizon AKI prediction at a 48-hour window before onset.

CONCLUSION

A CNN machine learning-based AKI prediction model outperforms XGBoost and the SOFA scoring system, revealing superior performance in predicting AKI 48 hours before onset, without reliance on serum creatinine (SCr) measurements.

Real-Time Clinical Decision Support Based on Recurrent Neural Networks for In-Hospital Acute Kidney Injury: External Validation and Model Interpretation

Background

Acute kidney injury (AKI) is commonly encountered in clinical practice and is associated with poor patient outcomes and increased health care costs. Despite it posing significant challenges for clinicians, effective measures for AKI prediction and prevention are lacking. Previously published AKI prediction models mostly have a simple design without external validation. Furthermore, little is known about the process of linking model output and clinical decisions due to the black-box nature of neural network models.

Objective

We aimed to present an externally validated recurrent neural network (RNN)–based continuous prediction model for in-hospital AKI and show applicable model interpretations in relation to clinical decision support.

Methods

Study populations were all patients aged 18 years or older who were hospitalized for more than 48 hours between 2013 and 2017 in 2 tertiary hospitals in Korea (Seoul National University Bundang Hospital and Seoul National University Hospital). All demographic data, laboratory values, vital signs, and clinical conditions of patients were obtained from electronic health records of each hospital. We developed 2-stage hierarchical prediction models (model 1 and model 2) using RNN algorithms. The outcome variable for model 1 was the occurrence of AKI within 7 days from the present. Model 2 predicted the future trajectory of creatinine values up to 72 hours. The performance of each developed model was evaluated using the internal and external validation data sets. For the explainability of our models, different model-agnostic interpretation methods were used, including Shapley Additive Explanations, partial dependence plots, individual conditional expectation, and accumulated local effects plots.

Results

We included 69,081 patients in the training, 7675 in the internal validation, and 72,352 in the external validation cohorts for model development after excluding cases with missing data and those with an estimated glomerular filtration rate less than 15 mL/min/1.73 m2 or end-stage kidney disease. Model 1 predicted any AKI development with an area under the receiver operating characteristic curve (AUC) of 0.88 (internal validation) and 0.84 (external validation), and stage 2 or higher AKI development with an AUC of 0.93 (internal validation) and 0.90 (external validation). Model 2 predicted the future creatinine values within 3 days with mean-squared errors of 0.04-0.09 for patients with higher risks of AKI and 0.03-0.08 for those with lower risks. Based on the developed models, we showed AKI probability according to feature values in total patients and each individual with partial dependence, accumulated local effects, and individual conditional expectation plots. We also estimated the effects of feature modifications such as nephrotoxic drug discontinuation on future creatinine levels.

Conclusions

We developed and externally validated a continuous AKI prediction model using RNN algorithms. Our model could provide real-time assessment of future AKI occurrences and individualized risk factors for AKI in general inpatient cohorts; thus, we suggest approaches to support clinical decisions based on prediction models for in-hospital AKI.

Opportunities in the cloud or pie in the sky? Current status and future perspectives of telemedicine in nephrology

The use of telehealth to support, enhance or substitute traditional methods of delivering healthcare is becoming increasingly common in many specialties, such as stroke care, radiology and oncology. There is reason to believe that this approach remains underutilized within nephrology, which is somewhat surprising given the fact that nephrologists have always driven technological change in developing dialysis technology. Despite the obvious benefits that telehealth may provide, robust evidence remains lacking and many of the studies are anecdotal, limited to small numbers or without conclusive proof of benefit. More worryingly, quite a few studies report unexpected obstacles, pitfalls or patient dissatisfaction. However, with increasing global threats such as climate change and infectious disease, a change in approach to delivery of healthcare is needed. The current pandemic with coronavirus disease 2019 (COVID-19) has prompted the renal community to embrace telehealth to an unprecedented extent and at speed. In that sense the pandemic has already served as a disruptor, changed clinical practice and shown immense transformative potential. Here, we provide an update on current evidence and use of telehealth within various areas of nephrology globally, including the fields of dialysis, inpatient care, virtual consultation and patient empowerment. We also provide a brief primer on the use of artificial intelligence in this context and speculate about future implications. We also highlight legal aspects and pitfalls and discuss the 'digital divide' as a key concept that healthcare providers need to be mindful of when providing telemedicine-based approaches. Finally, we briefly discuss the immediate use of telenephrology at the onset of the COVID-19 pandemic. We hope to provide clinical nephrologists with an overview of what is currently available, as well as a glimpse into what may be expected in the future.

Incidence and risk factors of acute kidney injury, and its effect on mortality among Japanese patients receiving immune check point inhibitors: a single-center observational study

BACKGROUND

Immune checkpoint inhibitors (ICPis) are associated with multi-organ immune-related adverse effects. Here, we examined the incidence rate, recovery rate, and risk factors of acute kidney injury complicated with ICPis (ICPi-AKI) and evaluted the association between ICPi-AKI and mortality in Japanese patients.

METHODS

We analyzed 152 consecutive patients receiving ICPis between 2015 and 2019. A logistic regression analysis was performed to identify risk factors for ICPi-AKI incidence and Cox regression analysis was performed to evaluate the association between ICPi-AKI and mortality.

RESULTS

The mean patient age was 67 ± 10 years, with the median baseline serum creatinine level of 0.78 mg/dL. Twenty-seven patients (18%) developed ICPi-AKI, and 19 (73%) of them recovered. Pembrolizumab use and liver diseases were significant risk factors for the ICPi-AKI incidence. During the follow-up, 85 patients (59%) died, 17 patients (63%) with ICPi-AKI and 68 (54%) patients without ICPi-AKI, respectively. The ICPi-AKI incidence was not independently associated with mortality (adjusted hazard ratio, 0.85; 95% confidence intervals, 0.46-1.61).

CONCLUSIONS

Our finding suggest that pembrolizumab use and liver diseases are associated with a higher risk of ICPi-AKI development, but ICPi-AKI did not affect mortality. Future multi-center studies are needed to develop optimal management and prevention strategies for this complication in patients receiving ICPis.

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

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.

Care of the Survivor of Critical Illness and Acute Kidney Injury: A Multidisciplinary Approach

Acute kidney injury (AKI) is a common complication of critical illness and is associated with adverse short- and long-term health consequences. Survivors of critical illness and AKI experience poor kidney, cardiovascular and quality of life outcomes, along with increased mortality. Yet, many patients surviving AKI are unaware that there is a problem with their kidney health, and post-AKI nephrology follow-up occurs at very low rates. Although there is a paucity of evidence-based studies to guide post-AKI care, attention to risk factors such as hypertension and albuminuria are requisite. There are several ongoing or planned studies which are expected to help inform specific management in the future. Until then, a multidisciplinary approach is warranted to address areas such as quality of life, physical rehabilitation, dietary modifications, and medication reconciliation.