Utility of electronic AKI alerts in intensive care: A national multicentre cohort study

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.

Utilising routine clinical laboratory data to support quality improvement in health care: Application of a national acute kidney injury alert system as a proof of concept

BACKGROUND

Acute kidney injury (AKI) is a global health issue known to cause avoidable harm and death. Improvement in its prevention and management is therefore considered an important goal for the health-care sector. The work here aimed to develop a tool which could be used to robustly and reliably measure, monitor, and compare the effectiveness of health-care interventions related to AKI across the Welsh NHS, a mechanism which did not exist previously.

METHODS

Using serum creatinine (SCr) as a biomarker for AKI and a validated national data-set collected from the all Wales Laboratory Information Management System, work involved applying Donabedian's framework to develop indicators with which to measure outcomes related to AKI, and exploring the potential of statistical process control (SPC) techniques for analysing data on these indicators.

RESULTS

Rate of AKI incidence and 30-day AKI-associated mortality are proposed as valid, feasible indicators with which to measure the effectiveness of health-care interventions related to AKI. The control chart, funnel plot, and Pareto chart are proposed as appropriate, robust SPC techniques to analyse and visualise variation in AKI-related outcomes.

CONCLUSIONS

This work demonstrates that routinely collected large SCr data offer a significant opportunity to monitor and therefore inform improvement in patient outcomes related to AKI. Moreover, while this work concerns utilisation of SCr data for improvement in AKI strategies, it is a proof of concept which could be replicated for other routinely collected clinical laboratory data, to improve the prevention and/or management of the conditions to which they relate.

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.

Risk Management In Intensive Care Units With Artificial Intelligence Technologies: Systematic Review of Prediction Models Using Electronic Health Records

Background and aim: Clinical risk assessments should be made to protect patients from negative outcomes, and the definition, frequency and severity of the risk should be determined. The information contained in the electronic health records (EHRs) can use in different areas such as risk prediction, estimation of treatment effect ect. Many prediction models using artificial intelligence (AI) technologies that can be used in risk assessment have been developed. The aim of this study is to bring together the researches on prediction models developed with AI technologies using the EHRs of patients hospitalized in the intensive care unit (ICU) and to evaluate them in terms of risk management in healthcare. Methods: The study restricted the search to the Web of Science, Pubmed, Science Direct, and Medline databases to retrieve research articles published in English in 2010 and after. Studies with a prediction model using data obtained from EHRs in the ICU are included. The study focused solely on research conducted in ICU to predict a health condition that poses a significant risk to patient safety using artificial intellegence (AI) technologies. Results: Recognized prediction subcategories were mortality (n=6), sepsis (n=4), pressure ulcer (n=4), acute kidney injury (n=3), and other areas (n=10). It has been found that EHR-based prediction models are good risk management and decision support tools and adoption of such models in ICUs may reduce the prevalence of adverse conditions. Conclusions: The article results remarks that developed models was found to have higher performance and better selectivity than previously developed risk models, so they are better at predicting risks and serious adverse events in ICU. It is recommended to use AI based prediction models developed using EHRs in risk management studies. Future work is still needed to researches to predict different health conditions risks.

Impact of integrated clinical decision support systems in the management of pediatric acute kidney injury: a pilot study

BACKGROUND

Acute kidney injury (AKI) is common but not often recognized. Early recognition and management may improve patient outcomes.

METHODS

This is a prospective, nonrandomized study of clinical decision support (CDS) system [combining electronic alert and standardized care pathway (SCP)] to evaluate AKI detection and progression in hospitalized children. The study was done in three phases: pre-, intervention (CDS) and post. During CDS, text-page with AKI stage and link to SCP was sent to patient's contact provider at diagnosis of AKI using creatinine. The SCP provided guidelines on AKI management [AEIOU: Assess cause of AKI, Evaluate drug doses, Intake-Output charting, Optimize volume status, Urine dipstick].

RESULTS

In all, 239 episodes of AKI in 225 patients (97 females, 43.1%) were analyzed. Proportion of patients with decrease in the stage of AKI after onset was 71.4% for CDS vs. 64.4% for pre- and 55% for post-CDS phases (p = 0.3). Documentation of AKI was higher during CDS (74.3% CDS vs. 47.5% pre- and 57.5% post-, p < 0.001). Significantly greater proportion of patients had nephrotoxic medications adjusted, or fluid plan changed during CDS. Patients from CDS phase had higher eGFR at discharge and at follow-up.

CONCLUSIONS

AKI remains under-recognized. CDS (electronic alerts and SCP) improve recognition and allow early intervention. This may improve long-term outcomes, but larger studies are needed.

IMPACT

Acute kidney injury can cause significant morbidity and mortality. It is under-recognized in children. Clinical decision support can be used to leverage existing data in the electronic health record to improve AKI recognition. This study demonstrates the use of a novel, electronic health record-linked, clinical decision support tool to improve the recognition of AKI and guideline-adherent clinical care.

Derivation of a prediction model for emergency department acute kidney injury

BACKGROUND AND OBJECTIVE

Quality management of Acute Kidney Injury (AKI) is dependent on early detection, which is currently deemed to be suboptimal. The aim of this study was to identify combinations of variables associated with AKI and to derive a prediction tool for detecting patients attending the emergency department (ED) or hospital with AKI (ED-AKI).

DESIGN, SETTING, PARTICIPANTS AND MEASUREMENTS

This retrospective observational study was conducted in the ED of a tertiary university hospital in Wales. Between April and August 2016 20,421 adult patients attended the ED of a University Hospital in Wales and had a serum creatinine measurement. Using an electronic AKI reporting system, 548 incident adult ED-AKI patients were identified and compared to a randomly selected cohort of adult non-AKI ED patients (n = 571). A prediction model for AKI was derived and subsequently internally validated using bootstrapping. The primary outcome measure was the number of patients with ED-AKI.

RESULTS

In 1119 subjects, 27 variables were evaluated. Four ED-AKI models were generated with C-statistics ranging from 0.800 to 0.765. The simplest and most practical multivariate model (model 3) included eight variables that could all be assessed at ED arrival. A 31-point score was derived where 0 is minimal risk of ED-AKI. The model discrimination was adequate (C-statistic 0.793) and calibration was good (Hosmer & Lomeshow test 27.4). ED-AKI could be ruled out with a score of <2.5 (sensitivity 95%). Internal validation using bootstrapping yielded an optimal Youden index of 0.49 with sensitivity of 80% and specificity of 68%.

CONCLUSION

A risk-stratification model for ED-AKI has been derived and internally validated. The discrimination of this model is objective and adequate. It requires refinement and external validation in more generalisable settings.

Clinical Characteristics and Outcomes of Community-Acquired versus Hospital-Acquired Acute Kidney Injury: A Meta-Analysis

BACKGROUND

The different clinical characteristics of community-acquired acute kidney injury (CA-AKI) versus hospital-acquired AKI (HA-AKI) have remained inconclusive, and thus, a meta-analysis was conducted to summarize and quantify the clinical significance distinguishing the 2 types of AKI.

METHODS

We identified observational studies reporting the clinical characteristics and prognosis of HA-AKI and CA-AKI. ORs and mean differences (MDs) were extracted for each outcome and the results aggregated. The primary outcome was defined as the mortality rate; renal recovery, oliguria incidence, dialysis, intensive care unit (ICU) requirement, and length of hospital stay were secondary outcomes.

RESULTS

Fifteen eligible studies involving 46,157 patients (22,791 CA-AKI patients and 23,366 HA-AKI patients) were included. Mortality was significantly lower in CA-AKI than in HA-AKI patients, with an OR of 0.43 (95% CI 0.35-0.53). The incidence of oliguria and need for ICU were also lower in CA-AKI patients (OR 0.58, 95% CI 0.38-0.88; OR 0.24, 95% CI 0.14-0.40, respectively). CA-AKI patients had a shorter hospital stay (MD -9.42, 95% CI -13.73 to -5.12). The renal recovery rate and dialysis need between CA- and HA-AKI were similar (OR 1.27, 95% CI 0.53-3.02; OR 1.05, 95% CI 0.82-1.34, respectively).

CONCLUSIONS

CA-AKI showed better clinical manifestations with a lower incidence of oliguria, reduced risk of ICU treatment, and shorter hospital stay. Mortality associated with CA-AKI was lower compared with HA-AKI, indicating a better prognosis. The rate of renal recovery and need for dialysis showed no significant difference between the 2 groups.

Principles of Automation for Patient Safety in Intensive Care: Learning From Aviation

BACKGROUND

The transition away from written documentation and analog methods has opened up the possibility of leveraging data science and analytic techniques to improve health care. In the implementation of data science techniques and methodologies, high-acuity patients in the ICU can particularly benefit. The Principles of Automation for Patient Safety in Intensive Care (PASPIC) framework draws on Billings's principles of human-centered aviation (HCA) automation and helps in identifying the advantages, pitfalls, and unintended consequences of automation in health care.

THE FRAMEWORK AND ITS KEY CHARACTERISTICS

Billings's HCA principles are based on the premise that human operators must remain "in command," so that they are continuously informed and actively involved in all aspects of system operations. In addition, automated systems need to be predictable, simple to train, to learn, and to operate, and must be able to monitor the human operators, and every intelligent system element must know the intent of other intelligent system elements. In applying Billings's HCA principles to the ICU setting, PAPSIC has three key characteristics: (1) integration and better interoperability, (2) multidimensional analysis, and (3) enhanced situation awareness.

RECOMMENDATIONS

PAPSIC suggests that health care professionals reduce overreliance on automation and implement "cooperative automation" and that vendors reduce mode errors and embrace interoperability.

CONCLUSION

Much can be learned from the aviation industry in automating the ICU. Because it combines "smart" technology with the necessary controls to withstand unintended consequences, PAPSIC could help ensure more informed decision making in the ICU and better patient care.