AUTHOR=Luo Jingmin , Zhang Wei , Tan Shiyang , Liu Lijue , Bai Yongping , Zhang Guogang 

TITLE=Aortic Dissection Auxiliary Diagnosis Model and Applied Research Based on Ensemble Learning

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2021.777757

DOI=10.3389/fcvm.2021.777757

ISSN=2297-055X

ABSTRACT=Aortic dissection ( AD) is a serious disease that is a serious threat to human life. AD has a hidden onset and rapid progression, and there is a lack of adequate diagnostic methods for early diagnosis. CT angiography, which is accepted as the gold standard for AD diagnosis, is so costly and time consuming that it can hardly offer enough help to patients. Today, the technology of artificial intelligence is developing quickly, and raises the question of whether there is a way to collect the general conditions of AD patients, like basic inspection information and inspection data, then build an auxiliary diagnosis model to improve the early diagnosis rate of AD by using this technology. Our research combines the clinical analysis of AD with machine learning methods, such as ensemble learning, to establish an integrated quantitative diagnosis model. The model has been proven to have more than 80% accuracy for AD early discriminant in a number of ways . Furthermore, the membership degree of the model  can improve the auxiliary diagnostic accuracy by constantly adjusting with new data follow the accumulation of auxiliary diagnosis system for diagnosing case constantly adjust, improve the auxiliary diagnostic accuracy. The auxiliary diagnostic system of the model can effectively improve the early detection rate of AD, which can provide an effective reference for the majority of basic level medical staff.