No abstract

No abstract

Coronary artery lesions (CAL) are not uncommon in pediatrics, but their causesare complex， such as congenital coronary artery disease, atherosclerosis, infectious diseases, and rheumatic immune diseases, which can lead to CAL. This review provides a systematic evaluation of the published medical literature on potential etiologies and associated pathogenesis that may lead to CAL in children, in order to broaden clinical diagnosis and avoid misdiagnosis and underdiagnosis. The main pathogenesis of CAL is an innate immunity imbalance due to exposure of genetically susceptible people to various infections and/or environmental factors. Kawasaki disease is not the only cause of CAL, and pediatricians need to better understand the immunological mechanisms of the CAL to suspect and diagnose.In addition, attach great importance to rheumatic immune diseases and cardiovascular diseases secondary to CAL.

Purpose: To explore the role of artificial intelligence in distinguishing Kawasaki disease from other multi-system inflammatory syndromes. Methods: We refer to the existing relevant articles at home and abroad for analysis. Results: The clinical application of artificial intelligence has played a time-saving and labour-saving role in the differentiation of Kawasaki disease and other multi-system inflammatory syndromes, suggesting that the application of big data in clinical practice can bring new development opportunities for medical treatment. Conclusion: Kawasaki disease and other multi-system inflammatory syndromes are similar and overlapping in clinical practice, which is difficult to distinguish and easy to misdiagnose and miss diagnose. Artificial intelligence is applied to analyze the above disease data, to achieve the effect of accurate differentiation, timely diagnosis, symptomatic treatment and reduction of complications.