B-lines score on lung ultrasound as a direct measure of respiratory dysfunction in ICU patients with acute kidney injury

Abstract Acute kidney injury (AKI) has an incidence rate of 5-6% among intensive care unit (ICU) patients and sepsis is the most frequent etiology. Aims: To assess patients in the ICU that developed AKI, AKI on chronic kidney disease (CKD), and/or sepsis, and identify the risk factors and outcomes of these diseases. Methods: A prospective observational cohort quantitative study that included patients who stayed in the ICU > 48 hours and had not been on dialysis previously was carried out. Results: 302 patients were included and divided into: no sepsis and no AKI (nsnAKI), sepsis alone (S), septic AKI (sAKI), non-septic AKI (nsAKI), septic AKI on CKD (sAKI/CKD), and non-septic AKI on CKD (nsAKI/CKD). It was observed that 94% of the patients developed some degree of AKI. Kidney Disease Improving Global Outcomes (KDIGO) stage 3 was predominant in the septic groups (p = 0.018). Nephrologist follow-up in the non-septic patients was only 23% vs. 54% in the septic groups (p < 0.001). Dialysis was performed in 8% of the non-septic and 37% of the septic groups (p < 0.001). Mechanical ventilation (MV) requirement was higher in the septic groups (p < 0.001). Mortality was 38 and 39% in the sAKI and sAKI/CKD groups vs 16% and 0% in the nsAKI and nsAKI/CKD groups, respectively (p < 0.001). Conclusions: Patients with sAKI and sAKI/CKD had worse prognosis than those with nsAKI and nsAKI/CKD. The nephrologist was not contacted in a large number of AKI cases, except for KDIGO stage 3, which directly influenced mortality rates. The urine output was considerably impaired, ICU stay was longer, use of MV and mortality were higher when kidney injury was combined with sepsis.

Download Full-text

Furosemide as a functional marker of acute kidney injury in ICU patients: a new role for an old drug

Journal of Nephrology ◽

10.1007/s40620-019-00614-1 ◽

2019 ◽

Vol 32 (6) ◽

pp. 883-893 ◽

Cited By ~ 5

Author(s):

Filippo Mariano ◽

Alberto Mella ◽

Marco Vincenti ◽

Luigi Biancone

Keyword(s):

Acute Kidney Injury ◽

Kidney Injury ◽

Functional Marker ◽

Icu Patients

Download Full-text

Comparing Machine Learning Algorithms for Predicting Acute Kidney Injury

The American Surgeon ◽

10.1177/000313481908500731 ◽

2019 ◽

Vol 85 (7) ◽

pp. 725-729 ◽

Cited By ~ 3

Author(s):

Joshua Parreco ◽

Hahn Soe-Lin ◽

Jonathan J. Parks ◽

Saskya Byerly ◽

Matthew Chatoor ◽

...

Keyword(s):

Machine Learning ◽

Acute Kidney Injury ◽

Learning Algorithms ◽

Vital Signs ◽

Kidney Injury ◽

Machine Learning Algorithms ◽

Laboratory Measurements ◽

Icu Patients ◽

Laboratory Values ◽

F Measure

Prior studies have used vital signs and laboratory measurements with conventional modeling techniques to predict acute kidney injury (AKI). The purpose of this study was to use the trend in vital signs and laboratory measurements with machine learning algorithms for predicting AKI in ICU patients. The eICU Collaborative Research Database was queried for five consecutive days of laboratory measurements per patient. Patients with AKI were identified and trends in vital signs and laboratory values were determined by calculating the slope of the least-squares-fit linear equation using three days for each value. Different machine learning classifiers (gradient boosted trees [GBT], logistic regression, and deep learning) were trained to predict AKI using the laboratory values, vital signs, and slopes. There were 151,098 ICU stays identified and the rate of AKI was 5.6 per cent. The best performing algorithm was GBT with an AUC of 0.834 ± 0.006 and an F-measure of 42.96 per cent ± 1.26 per cent. Logistic regression performed with an AUC of 0.827 ± 0.004 and an F-measure of 28.29 per cent ± 1.01 per cent. Deep learning performed with an AUC of 0.817 ± 0.005 and an F-measure of 42.89 per cent ± 0.91 per cent. The most important variable for GBT was the slope of the minimum creatinine (30.32%). This study identifies the best performing machine learning algorithms for predicting AKI using trends in laboratory values in ICU patients. Early identification of these patients using readily available data indicates that incorporating machine learning predictive models into electronic medical record systems is an inevitable requisite for improving patient outcomes.

Download Full-text

Prognostic Significance of Serum NGAL and Troponin I against Acute Kidney Injury in Egyptian ICU Patients after Open Heart Surgery: A Pilot Study

Kidney Diseases ◽

10.1159/000490246 ◽

2018 ◽

Vol 4 (4) ◽

pp. 246-254

Author(s):

Osama F. Mosa

Keyword(s):

Acute Kidney Injury ◽

Pilot Study ◽

Heart Surgery ◽

Troponin I ◽

Prognostic Significance ◽

Open Heart Surgery ◽

Kidney Injury ◽

Open Heart ◽

Icu Patients

Download Full-text

Characteristics and risk factors of postoperative acute kidney injury in ICU patients

International Urology and Nephrology ◽

10.1007/s11255-018-1981-z ◽

2018 ◽

Vol 50 (11) ◽

pp. 2111-2112

Author(s):

Liu-Jia-Zi Shao ◽

Fu-Shan Xue ◽

Rui-Juan Guo ◽

Li Zheng

Keyword(s):

Risk Factors ◽

Acute Kidney Injury ◽

Kidney Injury ◽

Icu Patients

Download Full-text

Renal

10.1093/med/9780199696277.003.0007 ◽

2013 ◽

Author(s):

Martin Beed ◽

Richard Sherman ◽

Ravi Mahajan

Keyword(s):

Acute Kidney Injury ◽

Fluid Resuscitation ◽

Fluid Balance ◽

Fluid Overload ◽

Kidney Injury ◽

Crush Syndrome ◽

Careful Attention ◽

Icu Patients ◽

Balance Disorders ◽

Maintenance Fluids

Fluid balance disordersAcute kidney injuryRhabdomyolysis/crush syndromeFluid balance disorders include hypovolaemia (oligaemia), dehydration/acute fluid depletion, and hypervolaemia/fluid overload. Careful attention to fluid balance is essential in ICU. Patients are likely to require ‘maintenance’ fluids in addition to any fluid resuscitation.Hypovolaemia (see also Shock, ...

Download Full-text