Application of a New Attribute Reduction Algorithm in Intracranial Aneurysm Prediction

In order to solve the problem that the attribute reduction algorithm of neighborhood rough set only considers the influence of a single attribute on the decision attributes, but fails to consider the correlation between the attributes, this paper proposes an attribute reduction algorithm of neighborhood rough set based on chi-square test (ChiS-NRS). Firstly, the chi-square test is used to calculate the correlation, and the influence of related attributes is considered when selecting important attributes, which reduces the time complexity and improves the classification accuracy. Then, he improved algorithm uses the Gradient Boosting Decision Tree (GBDT) algorithm to build a classification model, and the model is verified on the UCI data set. Finally, the model is applied to predict the existence of intracranial aneurysms. The experimental results show that the proposed model can better predict the existence of intracranial aneurysms and assist doctors to make more accurate diagnosis.