scholarly journals Use of Deep Learning to Predict Acute Kidney Injury after Intravenous Contrast Media Administration: Prediction Model Development Study (Preprint)

10.2196/27177 ◽  
2021 ◽  
Author(s):  
Donghwan Yun ◽  
Semin Cho ◽  
Yong Chul Kim ◽  
Dong Ki Kim ◽  
Kook-Hwan Oh ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Deep Learning ◽  
Contrast Media ◽  
Prediction Model ◽  
Model Development ◽  
Kidney Injury ◽  
Intravenous Contrast ◽  
Development Study ◽  
Intravenous Contrast Media ◽  
Contrast Media Administration

MO419THE ROLE OF SHORT-TERM, HIGH-DOSE ATORVASTATIN FOR PREVENTION OF CONTRAST-INDUCED ACUTE KIDNEY INJURY (CI-AKI) IN PATIENTS WITH CARDIOVASCULAR DISEASES UNDERGOING COMPUTED TOMOGRAPHY WITH INTRAVENOUS CONTRAST ADMINISTRATION

2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
Andrey Vasin ◽  
Olga Mironova ◽  
Viktor Fomin
Keyword(s):  
Computed Tomography ◽  
Acute Kidney Injury ◽  
Cardiovascular Diseases ◽  
Contrast Media ◽  
Kidney Injury ◽  
Ct Scans ◽  
Intravenous Contrast ◽  
Dosing Regimens ◽  
Intravenous Contrast Media ◽  
Contrast Media Administration

Abstract Background and Aims Computed tomography with intravenous contrast media is widely used in hospitals. The incidence of CI-AKI due to intravenous contrast media administration in high-risk patients remains not studied as well as CI-AKI after intraarterial contrast media administration is. According to other researchers, the use of statins in the prevention of AKI after intra-arterial administration of a contrast agent is currently considered an efficient preventive measure. The aim of our study is to assess the incidence of contrast-induced acute kidney injury in patients with cardiovascular diseases during CT scan with intravenous contrast media and analyze the efficacy and safety of various statin dosing regimens for prevention of CI-AKI. Method A randomized controlled open prospective study is planned. Statin naive patients with cardiovascular diseases will be divided into 3 groups. Patients in the first group will receive atorvastatin 80mg 24 hours and 40mg 2 hours before CT scans and 40 mg after. The second group – 40 mg 2 hours before CT scans and 40 mg after. A third group is a control group. Exclusion criteria were current or previous statin treatment, contraindications to statins, severe renal failure, acute coronary syndrome, administration of nephrotoxic drugs. The primary endpoint will the development of CI-AKI, defined as an increase in serum Cr concentration 0.5 mg/dl (44.2 mmol/l) or 25% above baseline at 72 h after exposure to the contrast media. Results We assume a higher incidence of contrast-induced acute kidney injury in the group of patients not receiving statin therapy (about 5-10%). At the same time, it is unlikely to get a significant difference between statin dosing regimens. Risk factors such as age over 75 years, the presence of chronic kidney disease, diabetes mellitus, and chronic heart failure increase the risk of contrast-induced acute kidney injury. Conclusion Despite the significantly lower incidence of CI-AKI with intravenous contrast compared to intra-arterial, patients with CVD have a greater risk of this complication even with intravenous contrast. Therefore, the development of prevention methods and scales for assessing the likelihood of CI-AKI is an important problem. As a result of the study, we expect to conclude the benefits of statins in CI-AKI prevention and the optimal dosage regimen. This information will help us to reduce the burden of CI-AKI after CT scanning in statin naive patients with cardiovascular diseases in everyday clinical practice. ClinicalTrials.gov ID: NCT04666389

Risk of Acute Kidney Injury After Intravenous Contrast Media Administration

2017 ◽  
Vol 69 (5) ◽  
pp. 577-586.e4 ◽  
Author(s):  
Jeremiah S. Hinson ◽  
Michael R. Ehmann ◽  
Derek M. Fine ◽  
Elliot K. Fishman ◽  
Matthew F. Toerper ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Contrast Media ◽  
Kidney Injury ◽  
Intravenous Contrast ◽  
Intravenous Contrast Media ◽  
Contrast Media Administration

Association between intravenous contrast media exposure and non-recovery from dialysis-requiring septic acute kidney injury: a nationwide observational study

2019 ◽  
Vol 45 (11) ◽  
pp. 1570-1579 ◽  
Author(s):  
Yoshihisa Miyamoto ◽  
Masao Iwagami ◽  
Shotaro Aso ◽  
Hideo Yasunaga ◽  
Hiroki Matsui ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Observational Study ◽  
Contrast Media ◽  
Media Exposure ◽  
Kidney Injury ◽  
Intravenous Contrast ◽  
Septic Acute Kidney Injury ◽  
Nationwide Observational Study ◽  
Intravenous Contrast Media

Use of deep learning to predict acute kidney injury after intravenous contrast media administration (Preprint)

2021 ◽  
Author(s):  
Donghwan Yun ◽  
Semin Cho ◽  
Yong Chul Kim ◽  
Dong Ki Kim ◽  
Kook-Hwan Oh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computed Tomography ◽  
Deep Learning ◽  
Contrast Media ◽  
Learning Algorithm ◽  
Kidney Injury ◽  
Time Varying ◽  
Intravenous Contrast ◽  
Deep Learning Algorithm ◽  
Intravenous Contrast Media

BACKGROUND Precise prediction of contrast media-induced acute kidney injury (CIAKI) is an important issue because of its relationship with worse outcomes. OBJECTIVE Herein, we examined whether a deep learning algorithm could predict the risk of intravenous CIAKI better than other machine learning and logistic regression models in patients undergoing computed tomography. METHODS A total of 14,185 cases that underwent intravenous contrast media for computed tomography under the preventive and monitoring facility in Seoul National University Hospital were reviewed. CIAKI was defined as an increase in serum creatinine ≥0.3 mg/dl within 2 days and/or ≥50% within 7 days. Using both time-varying and time-invariant features, machine learning models, such as the recurrent neural network (RNN), light gradient boosting machine, extreme boosting machine, random forest, decision tree, support vector machine, κ-nearest neighboring, and logistic regression, were developed using a training set, and their performance was compared using the area under the receiver operating characteristic curve (AUROC) in a test set. RESULTS CIAKI developed in 261 cases (1.8%). The RNN model had the highest AUROC value of 0.755 (0.708–0.802) for predicting CIAKI, which was superior to those obtained from other machine learning models. Although CIAKI was defined as an increase in serum creatinine ≥0.5 mg/dl and/or ≥25% within 3 days, the highest performance was achieved in the RNN model with an AUROC of 0.716 (0.664–0.768). In the feature ranking analysis, albumin level was the most highly contributing factor to RNN performance, followed by time-varying kidney function. CONCLUSIONS Application of a deep learning algorithm improves the predictability of intravenous CIAKI after computed tomography, representing a basis for future clinical alarming and preventive systems.

scholarly journals Risk of acute kidney injury after contrast-enhanced computed tomography in emergency department

2020 ◽  
pp. 102490792091339
Author(s):  
Seda Dağar ◽  
Emine Emektar ◽  
Hüseyin Uzunosmanoğlu ◽  
Şeref Kerem Çorbacıoğlu ◽  
Özge Öztekin ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Emergency Department ◽  
Acute Kidney Injury ◽  
Intensive Care ◽  
Contrast Media ◽  
Kidney Injury ◽  
Intravenous Contrast ◽  
Contrast Enhanced ◽  
Enhanced Computed Tomography ◽  
Contrast Enhanced Computed Tomography

Background: Despite its risks associated with renal injury, intravenous contrast media increases diagnostic efficacy and hence the chance of early diagnosis and treatment, which leaves clinicians in a dilemma regarding its use in emergency settings. Objective: The aim of this study was to determine the risk and predictors of contrast-induced acute kidney injury following intravenous contrast media administration for computed tomography in the emergency department. Methods: All patients aged 18 years and older who had a basal creatinine measurement within the last 8 h before contrast-enhanced computed tomography and a second creatinine measurement within 48–72 h after computed tomography scan between 1 January 2015 and 31 December 2017 were included in the study. Characteristics of patients with and without contrast-induced acute kidney injury development were compared. Multivariate regression analysis was used to assess the predictors for contrast-induced acute kidney injury. Results: A total of 631 patients were included in the final statistical analysis. After contrast media administration, contrast-induced acute kidney injury developed in 4.9% ( n = 31) of the patients. When the characteristics of patients are compared according to the development of contrast-induced acute kidney injury, significant differences were detected for age, initial creatinine, initial estimated glomerular filtration rate, and all acute illness severity indicators (hypotension, anemia, hypoalbuminemia, and need for intensive care unit admission). A multivariate logistic regression analysis was performed. The need for intensive care unit admission (odds ratio: 6.413 (95% confidence interval: 1.709–24.074)) and hypotension (odds ratio: 5.575 (95% confidence interval: 1.624–19.133)) were the main factors for contrast-induced acute kidney injury development. Conclusion: Our study results revealed that hypotension, need for intensive care, and advanced age were associated with acute kidney injury in patients receiving contrast media. Therefore, we believe that to perform contrast-enhanced computed tomography in emergency department should not be decided only by checking for renal function tests and that these predictors should be taken into consideration.

Sign in / Sign up

Export Citation Format

Share Document