Method for establishing post-coronary artery bypass transplantation acute kidney injury prediction model
A technology for acute kidney injury and coronary artery, applied in the field of biomedicine, can solve the problem of bias in patient evaluation, and achieve the effects of abundant samples, good discrimination, and high prediction accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] From 2010 to 2019, 3659 domestic patients with complete clinical data who received coronary artery bypass grafting due to heart failure were collected as modeling research objects. The collected patients included: gender, hyperlipidemia, brain natriuretic peptide, thyroid function, Hemoglobin, alanine aminotransferase, hypertension, body mass index, history of myocardial infarction, diabetes, cardiovascular stent implantation, elevated serum creatinine, cardiac surgery, smoking history, peripheral arterial disease, cerebrovascular events, preoperative Critical condition, CCS level 4, preoperative atrial fibrillation or atrial flutter, NYHA class III or IV, left ventricular ejection fraction (LVEF<35%), combined valve surgery, combined aortic surgery, non-elective surgery, chronic obstructive Twenty-seven risk factors including lung disease, cardiopulmonary bypass surgery and perioperative blood transfusion were used as research objects.
[0035] The definition of acute ...
Embodiment 2
[0038] Statistical analysis: All variables are categorical variables, represented by frequency (percentage). In univariate analysis, the significance of risk factors is sorted according to the absolute value of the correct rate, and the P value is required to be less than 0.1. Multi-factor Logistic regression analysis adopts the "Enter" method, which is an optional analysis method in the regression analysis method column, and a line graph prediction model is established based on the Logistic regression equation.
[0039] The 3659 patients were divided into two groups according to age, sex and body mass index, one of which was used as a modeling group, and the other was used as a verification group. The number of people in the modeling group was 2365, and the number of people in the verification group was 1294. The distribution of age, gender and body mass index indicators in the modeling group and the verification group is basically the same.
[0040] In the modeling group (n=...
Embodiment 3
[0051] Independent risk factors alanine aminotransferase and brain natriuretic peptide on the influence experiment of this line diagram prediction model, the verification object is the modeling group population, when this line diagram prediction model includes gender, preoperative serum creatinine increased, LVEF<35 %, 7 independent risk factors including previous myocardial infarction, hypertension, cardiopulmonary bypass surgery and perioperative blood transfusion, the area under the receiver operating curve (AUC) was 0.738; when gender was included in the model, preoperative serum creatinine increased , LVEF<35%, previous myocardial infarction, hypertension, cardiopulmonary bypass surgery, perioperative blood transfusion and alanine aminotransferase and other 8 independent risk factors, the area under the receiver operating curve (AUC) was 0.762; When the model includes 8 independent risk factors such as gender, preoperative serum creatinine increase, LVEF<35%, previous myoc...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com