Exploration of Fractional Flow Reservation Score Based on Artificial Intelligence Post-processing for Coronary Artery Lesions in Patients with Diabetes and Coronary Heart Disease.

Researchers

Journal

Modalities

Models

Abstract

In order to evaluate the relationship between coronary heart disease (CHD) and fractional flow reservation (FFR) in patients with different levels of CHD and diabetes, this paper used AI (artificial intelligence) post-processing technology to detect CHD and FFR. In this paper, 94 patients suspected of CHD who underwent coronary arteriography (CAG) in a hospital between December 2022 and February 2023 were examined by coronary computed tomography angiography (CCTA) and FFR. Based on CCTA, AI software is used to process CCTA images, diagnose coronary plaques, coronary stenosis, corresponding stenosis of different types of plaques, and FFR values. The diagnostic performance of AI was evaluated using expert diagnosis, CAG diagnosis, and FFR examination results as the “gold standard”. According to the diagnosis results, the relationship between FFR and CHD patients with diabetes at different levels was studied. The research results showed that AI image diagnosis has high sensitivity, specificity, and accuracy, and has good diagnostic effects on coronary plaques, coronary stenosis, stenosis corresponding to different types of plaques, and FFR values. The fasting blood glucose levels and FFR values of three groups of CHD patients were statistically significant, and correlation analysis revealed a negative correlation between the two. Using AI for CCTA diagnosis can efficiently, conveniently, and accurately obtain the required data, improving clinical diagnostic efficiency and accuracy. The analysis of AI recognition results found that in patients with CHD, the FFR value of patients with diabetes decreased, and the FFR value was negatively correlated with the fasting blood glucose concentration, indicating that CHD patients may lead to myocardial ischemia in the blood supply area due to the decline of their coronary blood flow reserve. CHD patients with diabetes are very common. It is known that high blood sugar can cause coronary artery damage. Many CHD patients with diabetes have complex angiopathy, so the advantages and disadvantages of stent placement should be carefully considered in clinical practice. CAG is currently the most commonly used examination method in clinical practice, and is considered the “gold standard” for imaging evaluation and diagnosis of CHD. FFR evaluates the blood flow status in the coronary artery by measuring the pressure inside the coronary artery, and determines whether it has changed based on its changes (i.e. functional assessment). Diabetes is closely related to CHD and is a risk factor of CHD. The range of vascular lesions in diabetes patients is very wide, which can involve capillaries to large arteries, thereby damaging their microvascular function [1]. McKenzie-Sampson Safyer studied whether gestational diabetes would increase the risk of cardiovascular disease after more than 20 years [2]. Piche Marie-Eve discussed the interaction between obesity type 2 diabetes and cardiovascular disease [3]. Li Jing studied the relationship between pregnancy diabetes and long-term risk of cardiovascular disease [4]. Petrie John R discussed the pathophysiological characteristics of common diseases of diabetes and hypertension and related vascular complications [5]. Kemps Hareld proposed a physical exercise program suitable for type 2 diabetes with cardiovascular disease by analyzing the clinical characteristics of type 2 diabetes with cardiovascular disease [6]. Sattar Naveed analyzed the mortality and cardiovascular disease results of patients with or without type 2 diabetes [7]. Using FFR to study diabetes with CHD can help coronary artery remodeling and provide new ideas and methods for clinical treatment. Coronary artery CCTA is the preferred examination method for screening and diagnosis of CHD. However, the large number of coronary artery CCTA images requires doctors to perform post-processing, which brings a lot of workload to doctors. Doctors are prone to visual fatigue, and it can also lead to doctors missing out on coronary artery stenosis (CAS) segments and misevaluating the degree of stenosis [8]. AI technology have advantages such as speed, efficiency, repeatability, quantification, and low cost. The use of AI technology can appropriately reduce the workload of doctors in medical imaging diagnosis, which helps drive doctors to improve workflow and reduce the probability of errors [9]. von Knebel Doeberitz Philipp L studied the diagnostic efficacy of combining plaque markers generated by CCTA with deep learning (DL) based blood reserve scores [10]. Zhou Zhen further reduced the contrast agent dose for whole aortic CT angiography imaging using the enhanced period consistent adversarial framework algorithm [11]. AI can be used to measure CAS, plaque and FFR on CCTA images. This paper used AI to process CCTA images to assist in the study of diabetes with CHD. This article selected 94 patients with suspected CHD and uses AI for CCTA image analysis. The expert diagnosis results were used as the “gold standard” to evaluate the effectiveness of AI in identifying coronary plaques; using the CAG results as the “gold standard”, the effectiveness of AI in identifying CAS was evaluated; using expert diagnosis and CAG results as the “gold standard”, the effectiveness of AI in identifying stenosis corresponding to different types of plaques was evaluated; the effectiveness of AI in identifying myocardial ischemia was evaluated using FFR measurement results as the “gold standard”. Based on the above diagnostic results, the relationship between FFR and the difference of CHD in diabetes patients with CHD was studied, and the correlation between FFR and the difference of CHD was discussed.Copyright © 2024. Published by Elsevier Inc.