Random Forest Model for Predicting Rupture of Middle Cerebral Aneurysms in Elderly Patients

Corresponding author: ZHOU JIA FENG, 179254021@qq.com

DOI: 10.12201/bmr.202509.00035

•  

  Abstract: Objective: To predict therisk of middle cerebral artery (MCA) aneurysm rupture in elderly patients by establishing a random forest model. Methods: A retrospective analysis was conducted on data from elderly patients (age > 60) with MCA aneurysms treated at the First Affiliated Hospital of Wenzhou Medical University between March 2009 and June 2020. The data were randomly divided into a training group and a validation group (n=7:3). Independent risk factors for MCA aneurysms rupture in elderly patients were obtained by unifactorial and multifactorial logistic regression, based on these a random forest model was constructed, which was externally validated using data from four other hospitals. Its predictive performance was evaluated using the area under the curve (AUC) of receiver operating characteristic (ROC). Results: A total of 242 MCA aneurysms from 226 patients were included, with 169 cases in the training group, 73 cases in the internal validation group, and 48 cases in the external validation group. Multifactorial logistic regression analysis showed that the size ratio, aneurysm angle, height-width ratio, and irregular morphology were independent risk factors for MCA aneurysms rupture in elderly patients. The random forest model achieved AUC values of0.916 (95% CI, 0.878–0.946), 0.925 (95% CI, 0.874–0.968), and 0.834 (95% CI, 0.725–0.932) for the training, internal validation, and external validation groups, respectively. Conclusion: The random forest model demonstrated excellent performance in predicting the risk of MCA aneurysm rupture in elderly patients and can be used to assist clinical decision-making.

  Key words: intracranial aneurysm; elderly; middle cerebral artery; rupture; random forest

  Submit time: 15 September 2025

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• zhou wei. Construction and Analysis of a Prediction Model for Hypertension Combined with Left Ventricular Diastolic Dysfunction Based on Random Forest AlgorithmWANG Tingting1 ,ZHOU Wei1*. 2025. doi: 10.12201/bmr.202503.00046

  涂宇星, chenyijun. . 2025. doi: 10.12201/bmr.202502.00034

  Mo Wei, Xiang Ya, Liao Qiujiao, He Liu, Ling Chaoling, Lu Qixiang, Liu Fangyin. Research progress on risk prediction model of postoperative delirium in elderly patients with hip fractureWEI Yunshi1? MO Wei1? XIANG YA1? LIAO Qiujiao1? HE Liu2? LING Chaoling2? LU Qixiang2? LIU Fangyin3▲. 2024. doi: 10.12201/bmr.202409.00029

  lixintai, tonli, yangjw. Contrast agent induced "cerebral infarction" imaging changes: a case of Contrast-induced Encephalopathy and literature review. 2024. doi: 10.12201/bmr.202406.00035

  Ren Jiaqing, Su binbin, Zheng xiaoying. A study on the relationship between education and health of middle-aged and elderly population in China. 2022. doi: 10.12201/bmr.202111.00018

  肖岑昕, HUANG Xuri, ZHAO Weidan. The correlation assessment of serum iron in the identification of community-acquired pneumonia in middle-aged and elderly individuals. 2025. doi: 10.12201/bmr.202501.00002

  chenjianling, Wu Gui ping, Shi Rong-li. A Study on the Current Status and Enhancement Pathways of Electronic Health Literacy among Middle-aged and Elderly People in Guangzhou City. 2024. doi: 10.12201/bmr.202404.00032

  SHU Wenxiu, LUO Liufei, Tong Jiaqi, Le Jing. Construction and effect evaluation of risk prediction model for grades 3-4 myeloma bone disease in newly diagnosed multiple myeloma patients. 2024. doi: 10.12201/bmr.202410.00057

  dengxiongwei. Effect of early weight-bearing exercise on postoperative function and satisfaction in patients with anterior talofibular ligament rupture. 2025. doi: 10.12201/bmr.202506.00053

  guoxinlong, yanglinying. The predictive value of FAP/ALB and NLPR in predicting the severity of CAP in the elderly. 2024. doi: 10.12201/bmr.202412.00057

• ID	Submit time	Number	Download
  1	2025-07-16	bmr.202509.00035V1	Download

• Public  Anonymous  To author only Submit Comments