Integrate prediction of machine learning for single ACoA rupture risk: a multicenter retrospective analysis

Yang Li; Linchun Huan; Wenpeng Lu; Jian Li; Hongping Wang; Bangyue Wang; Yunfei Song; Chao Peng; Jiyue Wang; Xinyu Yang; Jiheng Hao

doi:10.3389/fneur.2023.1126640

Integrate prediction of machine learning for single ACoA rupture risk: a multicenter retrospective analysis

Front Neurol. 2023 Oct 18:14:1126640. doi: 10.3389/fneur.2023.1126640. eCollection 2023.

Authors

Yang Li¹, Linchun Huan^{1

2}, Wenpeng Lu³, Jian Li¹, Hongping Wang⁴, Bangyue Wang¹, Yunfei Song¹, Chao Peng¹, Jiyue Wang⁵, Xinyu Yang¹, Jiheng Hao⁵

Affiliations

¹ Department of Neurosurgery, Tianjin Medical University General Hospital, Tianjin, China.
² Department of Neurosurgery, Linyi People's Hospital of Shandong Province, Linyi, Shandong, China.
³ Department of Neurosurgery, The First People's Hospital of Jining, Jining, Shandong, China.
⁴ Department of Neurosurgery, Tangshan Workers Hospital, Tangshan, Hebei, China.
⁵ Department of Neurosurgery, Liaocheng People's Hospital, Liaocheng, Shandong, China.

Abstract

Background: Statistically, Anterior communicating aneurysm (ACoA) accounts for 30 to 35% of intracranial aneurysms. ACoA, once ruptured, will have an acute onset and cause severe neurological dysfunction and even death. Therefore, clinical analysis of risk factors related to ACoA and the establishment of prediction model are the benefits to the primary prevention of ACoA.

Methods: Among 1,436 cases of single ACoA patients, we screened 1,325 valid cases, classified risk factors of 1,124 cases in the ruptured group and 201 cases in the unruptured group, and assessed the risk factors, respectively, and predicted the risk of single ACoA rupture by using the logistic regression and the machine learning.

Results: In the ruptured group (84.8%) of 1,124 cases and the unruptured group (15.2%) of 201 cases, the multivariable logistic regression (MLR) model shows hemorrhagic stroke history (OR 95%CI, p:0.233 (0.120-0.454),<0.001) and the age stratification of 60-69 years (OR 95%CI, p:0.425 (0.271-0.668),<0.001) has a significant statistic difference. In the RandomForest (RF) model, hemorrhagic stroke history and age are the best predictive factors.

Conclusion: We combined the analysis of MLR, RF, and PCA models to conclude that hemorrhagic stroke history and gender affect single ACoA rupture. The RF model with web dynamic nomogram, allows for real-time personalized analysis based on different patients' conditions, which is a tremendous advantage for the primary prevention of single ACoA rupture.

Clinical trial registration: https://www.chictr.org.cn/showproj.html?proj=178501.

Keywords: AcoA; machine learning; prediction model; rupture risk factors; web dynamic nomogram.

Grants and funding

This work was supported by the Natural Science Foundation of Tianjin, China (Grant no. 20JCZDJC00300) and by Tianjin Medical University Clinical Research Program (Grant no. 2018kylc008).