Alerting to acute kidney injury - Challenges, benefits, and strategies

Ivica, Josko; Sanmugalingham, Geetha; Selvaratnam, Rajeevan

doi:10.1016/j.plabm.2022.e00270

Cited by 6 publications

(4 citation statements)

References 93 publications

(230 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In summary, if investigators need to demonstrate that prediction tools may have the potential to be applied in a real-world setting [ 46 ], our study is able to confirm it: the Random Forest model for AKI 2/3 prediction was externally validated and optimally calibrated, resulting applicable to different sets of critically ill patients.…”

Section: Discussionsupporting

confidence: 52%

Continuous and early prediction of future moderate and severe Acute Kidney Injury in critically ill patients: Development and multi-centric, multi-national external validation of a machine-learning model

Alfieri,

Ancona,

Tripepi

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Background Acute Kidney Injury (AKI) is a major complication in patients admitted to Intensive Care Units (ICU), causing both clinical and economic burden on the healthcare system. This study develops a novel machine-learning (ML) model to predict, with several hours in advance, the AKI episodes of stage 2 and 3 (according to KDIGO definition) acquired in ICU. Methods A total of 16’760 ICU adult patients from 145 different ICU centers and 3 different countries (US, Netherland, Italy) are retrospectively enrolled for the study. Every hour the model continuously analyzes the routinely-collected clinical data to generate a new probability of developing AKI stage 2 and 3, according to KDIGO definition, during the ICU stay. Results The predictive model obtains an auROC of 0.884 for AKI (stage 2/3 KDIGO) prediction, when evaluated on the internal test set composed by 1’749 ICU stays from US and EU centers. When externally tested on a multi-centric US dataset of 6’985 ICU stays and multi-centric Italian dataset of 1’025 ICU stays, the model achieves an auROC of 0.877 and of 0.911, respectively. In all datasets, the time between model prediction and AKI (stage 2/3 KDIGO) onset is at least of 14 hours after the first day of ICU hospitalization. Conclusions In this study, a novel ML model for continuous and early AKI (stage 2/3 KDIGO) prediction is successfully developed, leveraging only routinely-available data. It continuously predicts AKI episodes during ICU stay, at least 14 hours in advance when the AKI episode happens after the first 24 hours of ICU admission. Its performances are validated in an extensive, multi-national and multi-centric cohort of ICU adult patients. This ML model overcomes the main limitations of currently available predictive models. The benefits of its real-world implementation enable an early proactive clinical management and the prevention of AKI episodes in ICU patients. Furthermore, the software could be directly integrated with IT system of the ICU.

show abstract

Section: Discussionsupporting

confidence: 52%

Continuous and early prediction of future moderate and severe Acute Kidney Injury in critically ill patients: Development and multi-centric, multi-national external validation of a machine-learning model

Alfieri,

Ancona,

Tripepi

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…These factors could explain why we found a higher incidence of PC-AKI after sequential administration of ICM and GBCA than in the previous study [ 22 ]. Although the equations for calculating eGFR can induce measurement errors and augment the clearance rate, often resulting in overestimation, it is commonly used in AKI screening to predict the risk status [ 27 – 29 ]. Furthermore, one previous study stated that the serum creatinine level increases immediately after a decrease in the eGFR in the presence of AKI, making creatinine a suboptimal indicator of renal function in patients with AKI [ 30 ].…”

Section: Discussionmentioning

confidence: 99%

Risk factors for post-contrast acute kidney injury in patients sequentially administered iodine- and gadolinium-based contrast media on the same visit to the emergency department: a retrospective study

Kang

Han

Park

et al. 2023

Kidney Res Clin Pract

View full text Add to dashboard Cite

Background: This study compares the incidence of post-contrast acute kidney injury (PC-AKI) in patients who received a single administration of iodine-based contrast medium (ICM) with that in patients who received a sequential administration of ICM and gadolinium-based contrast agents (GBCA) in a single visit to an emergency department (ED) to determine the risk factors for PC-AKI. Methods: Patients who received one or more contrast media in the ED from 2016 to 2021 were included in this retrospective study. They were divided into the ICM alone and ICM + GBCA groups, and the incidence of PC-AKI was compared between the groups. The risk factors were assessed using a multivariable analysis after propensity score matching (PSM). Results: Overall, 6,318 patients were analyzed, of whom 139 were in the ICM + GBCA group. The incidence of PC-AKI was significantly higher in the ICM + GBCA group than in the ICM alone group (10.9% vs. 27.3%, p < 0.001). In the multivariable analysis, sequential administration was a risk factor for PC-AKI, and single administration was not (adjusted odds ratio [95% confidence interval] in the 1:1, 2:1, and 3:1 PSM cohorts: 2.38 [1.25-4.55], 2.13 [1.26-3.60], and 2.28 [1.39-3.72], respectively). In subgroup analyses of the ICM + GBCA group, osmolality (1. 05 [1.01-1.10]) and estimated glomerular filtration rate (eGFR,) were associated with PC-AKI. Conclusion: Compared with a single administration of ICM alone, sequential administration of ICM and GBCA during a single ED visit might be a risk factor for PC-AKI. Osmolality and eGFR might be associated with PC-AKI after sequential administration.

show abstract

“…Over 20 years since introduction of the term acute kidney injury (AKI), and 10 years since the KDIGO AKI clinical practice guidelines were published [ 1 ], clinical research has consistently demonstrated associations between AKI and adverse outcomes, including mortality, development and progression of chronic kidney disease (CKD), and cardiovascular events [ 2 ]. In many jurisdictions, AKI is now identified in clinical settings using e-alerts to facilitate and monitor improvement work [ 3 , 4 ]. The 2012 KDIGO guideline also described AKI as a condition within a broader group of disorders termed acute kidney diseases and disorders (AKD).…”

Section: Introductionmentioning

confidence: 99%

Recovery of kidney function after acute kidney disease—a multi-cohort analysis

Sawhney

Ball

Bell

et al. 2023

Nephrology Dialysis Transplantation

View full text Add to dashboard Cite

Background There are no consensus definitions for evaluating kidney function recovery after acute kidney injury (AKI) and acute kidney disease (AKD), nor is it clear how recovery varies across populations and clinical subsets. We present a federated analysis of four population-based cohorts from Canada, Denmark, and Scotland, 2011–2018. Methods We identified incident AKD defined by serum creatinine changes within 48 hours, 7 days, and 90 days based on KDIGO AKI and AKD criteria. Separately, we applied changes up to 365 days to address widely used e-alert implementations that extend beyond the KDIGO AKI and AKD timeframes. Kidney recovery was based on resolution of AKD and a subsequent creatinine measurement below 1.2x baseline. We evaluated transitions between non-recovery, recovery, and death up to one year; within age, sex, and comorbidity subgroups; between subset AKD definitions; and across cohorts. Results There were 464 868 incident cases, median ages 67–75 years. At one year, results were consistent across cohorts, with pooled mortalities for creatinine changes within 48 hours, 7 days, 90 days and 365 days (and 95% CI) of 40% (34–45%), 40% (34–46%), 37% (31–42%), 22% (16–29%) respectively; and non-recovery of kidney function of 19% (15–23%), 30% (24–35%), 25% (21–29%), 37% (30–43%) respectively. Recovery by 14 and 90 days was frequently not sustained at one year. Older males and those with heart failure or cancer were more likely to die than experience sustained non-recovery, whereas the converse was true for younger females and those with diabetes. Conclusion Consistently across multiple cohorts, based on one-year mortality and non-recovery, KDIGO AKD (up to 90 days) is at least prognostically similar to KDIGO AKI (7 days), and covers more people. Outcomes associated with AKD vary by age, sex and comorbidities such that older males are more likely to die, and younger females are less likely to recover.

show abstract

Alerting to acute kidney injury - Challenges, benefits, and strategies

Cited by 6 publications

References 93 publications

Continuous and early prediction of future moderate and severe Acute Kidney Injury in critically ill patients: Development and multi-centric, multi-national external validation of a machine-learning model

Continuous and early prediction of future moderate and severe Acute Kidney Injury in critically ill patients: Development and multi-centric, multi-national external validation of a machine-learning model

Risk factors for post-contrast acute kidney injury in patients sequentially administered iodine- and gadolinium-based contrast media on the same visit to the emergency department: a retrospective study

Recovery of kidney function after acute kidney disease—a multi-cohort analysis

Contact Info

Product

Resources

About