Objective To explore the predictive value of artificial intelligence(AI)plaque quantitative analysis combined with CT derived fractional flow reserve(CT-FFR)and pericoronary fat attenuation index(FAI)in coronary heart disease(CHD)in Qinghai.Methods A total of 118 suspected CHD patients were selected,and were divided into a stenosis group(n=76)and a non-stenosis group(n=42)based on whether their vascular stenosis rate was＞50％.The plaque volume,load,CT-FFR value,and pericoronary FAI of the two groups were measured and compared,and their predictive value in CHD was further analyzed.Results The plaque total volume,calcified and non-calcified plaque volume,lipid plaque volume,and corresponding volume load of the stenosis group were significantly higher than those of the non-stenosis group(P＜0.05),the percentage of napkin ring sign and pericoronary FAI were significantly higher than those of the non-stenosis group,and the CT-FFR was significantly lower than that of the non-stenosis group(P＜0.05).Logistic regression analysis found that the volume load of calcified and lipid plaques,napkin ring sign,CT-FFR,and pericoronary FAI were independent risk factors for CHD(P＜0.05).The combination of AI plaque quantitative analysis,CT-FFR,and pericoronary FAI had high sensitivity and specificity,with high value in CHD diagnosis.Conclusion The combination of AI plaque quantitative analysis,CT-FFR,and pericoronary FAI has high value in the diagnosis of CHD,and may be worthy of clinical promotion application.