Quantitative prognostic factor extraction of epidemicthrombosis using machine learning strategy

In recent years, artificial intelligence and machine learning have become increasingly involved in the treatment of prevalent human diseases. Acute ischemic stroke (AIS) is an increasingly severe disease with a high risk of thrombosis resulting in loss of neurological function or death. MT with mechanical thrombectomy has become the mainstream treatment. Apart from the common factors such as blood glucose, NIHSS, and blood pressure level, etc., there are still unknown factors which may have influence for prognosis after MT surgery. In this study, with the help of machine learning strategy, high-dimensional data of patients are mined, and the AIS prognostic prediction model is established in order to quantify the key influencing factors and determine the relationship between these parameters and the prognosis. This study is supposed to provide a set of methodology to evaluate the prognosis effectively.