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

Holmes, Jennifer; Roberts, Gethin; Geen, John; Dodd, Alan; Selby, Nicholas M.; Lewington, Andrew; Scholey, Gareth; Williams, Julie; Phillips, Aled Owain

doi:10.1016/j.jcrc.2017.10.024

Cited by 13 publications

(12 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the AKI definitions, Loo and Zainal [13], Obialo et al [25], Al-Homrany [14], and Wang et al [24] required serum creatinine (SCr) >2 mg/dL. The KDIGO criteria [21, 26] were applied in 6 studies [5, 12, 18, 27‒29], RIFLE [30] was applied in 4 studies [15, 18, 19, 23], and Sesso et al [31] defined AKI as a SCr level >1.4 mg/dL (124 mol/L) for men or >1.3 mg/dL (115 mol/L) for women. Mortality was compared in 14 studies [5, 13, 14, 17‒20, 24, 25, 27‒29, 31, 32], among which 11 studies compared in-hospital mortality; Wonnacott et al [28] compared in-hospital and 14-month mortality; Sawhney et al [27] provided 30-day, 1-year, and 5-year mortality; and Holmes et al [29] compared 90-day mortality.…”

Section: Resultsmentioning

confidence: 99%

“…The KDIGO criteria [21, 26] were applied in 6 studies [5, 12, 18, 27‒29], RIFLE [30] was applied in 4 studies [15, 18, 19, 23], and Sesso et al [31] defined AKI as a SCr level >1.4 mg/dL (124 mol/L) for men or >1.3 mg/dL (115 mol/L) for women. Mortality was compared in 14 studies [5, 13, 14, 17‒20, 24, 25, 27‒29, 31, 32], among which 11 studies compared in-hospital mortality; Wonnacott et al [28] compared in-hospital and 14-month mortality; Sawhney et al [27] provided 30-day, 1-year, and 5-year mortality; and Holmes et al [29] compared 90-day mortality. To reduce bias due to data extraction, we collected the 30-day mortality data from Sawhney et al[27] and the overall mortality from Wonnacott et al [28].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

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

Huang

Xue

Kuai

et al. 2019

Kidney Blood Press Res

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

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

Huang

Xue

Kuai

et al. 2019

Kidney Blood Press Res

View full text Add to dashboard Cite

show abstract

“…There are however, significant variations in the disease phenotype. For example, markedly differing mortality has been reported when diagnosed in the community (CA‐AKI, 19%‐26%), hospital (HA‐AKI, 30%‐43%) and within the intensive care unit (ICU‐AKI, 22%‐53%) . In surviving patients long‐term consequences are well recognised as survivors are at increased risk of de‐novo/progressive chronic kidney disease (CKD), end‐stage renal disease (ESRD) and early death …”

mentioning

confidence: 99%

Epidemiology of emergency department acute kidney injury

et al. 2019

Self Cite

View full text Add to dashboard Cite

Aim: The epidemiology of acute kidney injury (AKI) diagnosed in the emergency department (ED) is poorly described. This study describes the incidence, demographics and outcomes of patients diagnosed with AKI in the ED (ED-AKI).Methods: A prospective cohort study was completed in a University Teaching Hospital, (UK) between April and August 2016. In total, 20 421 adult patients attended the ED and had a serum creatinine measurement. The incident ED-AKI patient episodes were compared with a randomly selected cohort of non-AKI ED patients.Results: A total of 572 patients had confirmed eAlert ED-AKI (548 incident cases), incidence 2.8% (of all ED attendances). ED-AKI was associated with a 24.4% in-patient mortality (non-AKI 3.2%, P < .001) of which 22.3% of deaths occurred within 24 hours and 58% within 7 days. Progression of the admission AKI stage to a higher AKI stage was associated with a 38.8% mortality compared with a 21.4% mortality in those who did not progress (P < .001). In multivariate analysis, ED-AKI was an independent risk for mortality (hazard ratio, 6.293; 95% confidence interval, 1.887-20.790, P = .003). For those discharged from hospital, 20.4% of ED-AKI patients re-attend for acute assessment within 30-days post-discharge (non-AKI 7.6%, P < .001). At 90-days post-discharge, 10.0% of ED-AKI patients died (non-AKI 1.4%, P < .001). Twelve months post-discharge 17.8% of ED-AKI patients developed CKD progression or de-novo CKD (non-AKI 6.0%). Conclusion:The ED-AKI is an independent predictor of death. Mortality is predominantly in the early stages of hospital admission, but for those who survive to discharge have significant long-term morbidity and mortality. K E Y W O R D S acute kidney injury, emergency departments, epidemiology Acute kidney injury (AKI) is a common medical emergency, complicating 6% to 18% of all hospital admissions.

show abstract

“…AKI is a critical clinical event manifested by an abrupt decrease of renal function, affecting more than 50% of patients admitted to the ICU. (39,49) AI based AKI prediction models are good risk management tools. These models can be used to identify patients with high risk of developing severe AKI accurately.…”

Section: Aki Articlesmentioning

confidence: 99%

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

Çayirtepe¹,

Senel

2022

Journal of Basic and Clinical Health Sciences

View full text Add to dashboard Cite

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.

show abstract

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

Cited by 13 publications

References 25 publications

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

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

Epidemiology of emergency department acute kidney injury

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

Contact Info

Product

Resources

About