Diagnostic Value of Coronary Heart Disease by Artificial Intelligence CTA Automatic Post-processing System
ZHANG Zirui
SHENG Meihong
ZHANG Yujiao
Abstract：Objective: To analyze the diagnostic value of artificial intelligence (AI) and coronary artery computed tomography angiography (CTA) automatic post-processing system in the diagnosis of coronary heart disease. Methods: A total of 124 patients suspected of coronary heart disease admitted to our hospital from February 2020 to July 2021 were selected, all of whom met the indications for digital subtraction angiography (DSA). Taking the DSA results as the 'gold standard', the diagnostic value of the AI coronary CTA automatic post-processing system in diagnosing coronary heart disease was analyzed. Results: There was no statistically significant difference in image reconstruction success rate between the AI group and the manual group (P > 0.05). The time required for image post-processing in the AI group was shorter than that in the manual group, with a statistically significant difference (P < 0.001). There was no statistically significant difference in image quality scores of the main branches of the coronary arteries between the AI group and the manual group (P > 0.05). There was no statistically significant difference in plaque composition assessment between the AI group and the manual group (χ2 = 0.106, P = 0.948). The consistency between the AI group and the manual group in diagnosing moderate or higher stenosis of the coronary arteries and the 'gold standard' was high (Kappa values were 0.905 and 0.958, respectively, P < 0.001). There was no statistically significant difference in sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and diagnostic accuracy of coronary heart disease between the AI group and the manual group (P > 0.05). Conclusion: The AI coronary CTA automatic post-processing system has good application value in the diagnosis of coronary heart disease, and it is more efficient than manual processing.
Keywords：coronary heart diseaseartificial intelligencecoronary arterycomputed tomography angiographydigital subtraction angiography
Publication Date：2025-03-25
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 894-898 )