AUTHOR=Zhou Jiafeng , Xia Nengzhi , Li Qiong , Zheng Kuikui , Jia Xiufen , Wang Hao , Zhao Bing , Liu Jinjin , Yang Yunjun , Chen Yongchun 

TITLE=Predicting the rupture status of small middle cerebral artery aneurysms using random forest modeling

JOURNAL=Frontiers in Neurology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2022.921404

DOI=10.3389/fneur.2022.921404

ISSN=1664-2295

ABSTRACT=Objective: Small intracranial aneurysms are increasingly detected, however, the prediction model for its rupture is rare. To predict the rupture status of small middle cerebral artery (MCA) aneurysms with morphological features by using random forest modeling.
Methods: From January 2009 to June 2020, we retrospectively reviewed patients with small MCA aneurysms (<7 mm) between January 2009 and June 2020. Aneurysms were randomly split into training (70%) and internal validation (30%) cohorts. Additional independent datasets were used for external validation with 78 small MCA aneurysms from another four hospitals. Aneurysm morphologies were determined using computed tomography angiography. The prediction models were developed by using random forest and multivariate logistic regression. 
Results: 426 consecutive patients with 454 small MCA aneurysms (<7 mm) were enrolled in this study. Multivariate logistic regression analysis showed that size ratio, aspect ratio, and daughter dome were associated with aneurysm rupture, whereas aneurysm angle and aneurysm multiplicity were inversely associated with aneurysm rupture. The areas under receiver operating characteristic curves (AUCs) of random forest models by using the five independent risk factors in training, internal validation, and external validation cohorts were 0.922, 0.889, and 0.92, respectively. The performance of the random forest model outperformed that of the logistic regression model (P = 0.048). A nomogram was developed to provide the rupture of small MCA aneurysms. 
Conclusion: Random forest modeling is a good tool for evaluating the ruptured status of small MCA aneurysms and may be considered for the management of small aneurysms.