Analysis of risk factors for severe acute kidney injury in patients with acute myocardial infarction: A retrospective study

Abstract

BackgroundPatients with acute myocardial infarction (AMI) complicated by acute kidney injury (AKI) tend to have a poor prognosis. However, the exact mechanism of the co‐occurrence of the two diseases is unknown. Therefore, this study aims to determine the risk factors for severe AKI in patients with AMI.MethodsA total of 2022 patients were included in the Medical Information Mart for Intensive Care. Variables were identified via univariate logistic regression, and the variables were corrected via multivariate logistic regression. Restricted cubic splines were used to examine the risks associated with the variables. The Kaplan–Meier method was used to compare the risk of severe AKI among the patients.ResultsPatients with severe AKI had a higher in‐hospital mortality rate (28.6% vs. 9.0%, P < 0.001) and a longer duration of intensive care (6.5 days vs. 2.9 days, P < 0.001). In patients with AMI, the mean systolic blood pressure (SBP); international normalized ratio (INR); the levels of blood urea nitrogen (BUN), glucose, and calcium; and a history of liver disease were found to be the independent risk factors for developing severe AKI after their admission. Increased levels of BUN and blood glucose and a high INR increased the risk of severe AKI; however, increased levels of calcium decreased the risk; SBP presented a U‐shaped curve relationship.ConclusionsPatients with severe AKI have a poor prognosis following an episode of AMI. Furthermore, in patients with AMI, SBP; INR; a history of liver disease; and the levels of BUN, glucose, and calcium are the independent risk factors for developing severe AKI after their admission.

The leading global health challenges in the artificial intelligence era

“…If we discuss kidney disease progression as a case illustration, AI has its application in pre/post-diagnosis, which can ultimately lead to improved outcomes in a timely and accurate manner ( 20 ). During the analysis phase of patient data, AI can identify the early signs of the diseases from the lab results, medical history, and images ( 21 , 22 ), it can also help in the diagnosis of kidney disease from a kidney biopsy through deep learning-based approaches ( 23 ), and to improve outcome and early detection of other comorbidity in renal patients ( 24 ). The flowing part discusses AI’s applications in the major of NCDs.…”