Literature DB >> 33424738

Rupture Risk Assessment for Cerebral Aneurysm Using Interpretable Machine Learning on Multidimensional Data.

Chubin Ou1,2, Jiahui Liu1, Yi Qian2, Winston Chong3, Xin Zhang1, Wenchao Liu1, Hengxian Su1, Nan Zhang1, Jianbo Zhang1, Chuan-Zhi Duan1, Xuying He1.   

Abstract

Background: Assessment of cerebral aneurysm rupture risk is an important task, but it remains challenging. Recent works applying machine learning to rupture risk evaluation presented positive results. Yet they were based on limited aspects of data, and lack of interpretability may limit their use in clinical setting. We aimed to develop interpretable machine learning models on multidimensional data for aneurysm rupture risk assessment.
Methods: Three hundred seventy-four aneurysms were included in the study. Demographic, medical history, lifestyle behaviors, lipid profile, and morphologies were collected for each patient. Prediction models were derived using machine learning methods (support vector machine, artificial neural network, and XGBoost) and conventional logistic regression. The derived models were compared with the PHASES score method. The Shapley Additive Explanations (SHAP) analysis was applied to improve the interpretability of the best machine learning model and reveal the reasoning behind the predictions made by the model.
Results: The best machine learning model (XGBoost) achieved an area under the receiver operating characteristic curve of 0.882 [95% confidence interval (CI) = 0.838-0.927], significantly better than the logistic regression model (0.779; 95% CI = 0.729-0.829; P = 0.002) and the PHASES score method (0.758; 95% CI = 0.713-0.800; P = 0.001). Location, size ratio, and triglyceride level were the three most important features in predicting rupture. Two typical cases were analyzed to demonstrate the interpretability of the model. Conclusions: This study demonstrated the potential of using machine learning for aneurysm rupture risk assessment. Machine learning models performed better than conventional statistical model and the PHASES score method. The SHAP analysis can improve the interpretability of machine learning models and facilitate their use in a clinical setting.
Copyright © 2020 Ou, Liu, Qian, Chong, Zhang, Liu, Su, Zhang, Zhang, Duan and He.

Entities:  

Keywords:  intracranial aneurysm; machine learning; rupture; stroke; subarachnoid hemorrhage

Year:  2020        PMID: 33424738      PMCID: PMC7785850          DOI: 10.3389/fneur.2020.570181

Source DB:  PubMed          Journal:  Front Neurol        ISSN: 1664-2295            Impact factor:   4.003


  9 in total

1.  Development and assessment of machine learning models for predicting recurrence risk after endovascular treatment in patients with intracranial aneurysms.

Authors:  ShiTeng Lin; Yang Zou; Jue Hu; Lan Xiang; LeHeng Guo; XinPing Lin; DaiZun Zou; Xiaoping Gao; Hui Liang; JianJun Zou; ZhiHong Zhao; XiaoMing Dai
Journal:  Neurosurg Rev       Date:  2021-10-18       Impact factor: 2.800

2.  Classifying Ruptured Middle Cerebral Artery Aneurysms With a Machine Learning Based, Radiomics-Morphological Model: A Multicentral Study.

Authors:  Dongqin Zhu; Yongchun Chen; Kuikui Zheng; Chao Chen; Qiong Li; Jiafeng Zhou; Xiufen Jia; Nengzhi Xia; Hao Wang; Boli Lin; Yifei Ni; Peipei Pang; Yunjun Yang
Journal:  Front Neurosci       Date:  2021-08-11       Impact factor: 4.677

3.  Increased Carotid Siphon Tortuosity Is a Risk Factor for Paraclinoid Aneurysms.

Authors:  Shilin Liu; Yu Jin; Xukou Wang; Yang Zhang; Luwei Jiang; Guanqing Li; Xi Zhao; Tao Jiang
Journal:  Front Neurol       Date:  2022-05-10       Impact factor: 4.086

4.  An Integrated Model Combining Machine Learning and Deep Learning Algorithms for Classification of Rupture Status of IAs.

Authors:  Rong Chen; Xiao Mo; Zhenpeng Chen; Pujie Feng; Haiyun Li
Journal:  Front Neurol       Date:  2022-05-12       Impact factor: 4.086

5.  Identification of Small, Regularly Shaped Cerebral Aneurysms Prone to Rupture.

Authors:  S F Salimi Ashkezari; F Mut; M Slawski; C M Jimenez; A M Robertson; J R Cebral
Journal:  AJNR Am J Neuroradiol       Date:  2022-03-24       Impact factor: 3.825

6.  What Are the Predictors of Intracranial Aneurysm Rupture in Indonesian Population Based on Angiographic Findings? Insight from Intracranial Aneurysm Registry on Three Comprehensive Stroke Centres in Indonesia.

Authors:  Jovian P Swatan; Achmad F Sani; Dedy Kurniawan; Hermanto Swatan; Shakir Husain
Journal:  Stroke Res Treat       Date:  2022-03-17

7.  A Comparison of XGBoost, Random Forest, and Nomograph for the Prediction of Disease Severity in Patients With COVID-19 Pneumonia: Implications of Cytokine and Immune Cell Profile.

Authors:  Wandong Hong; Xiaoying Zhou; Shengchun Jin; Yajing Lu; Jingyi Pan; Qingyi Lin; Shaopeng Yang; Tingting Xu; Zarrin Basharat; Maddalena Zippi; Sirio Fiorino; Vladislav Tsukanov; Simon Stock; Alfonso Grottesi; Qin Chen; Jingye Pan
Journal:  Front Cell Infect Microbiol       Date:  2022-04-12       Impact factor: 6.073

8.  A web-based dynamic nomogram for rupture risk of posterior communicating artery aneurysms utilizing clinical, morphological, and hemodynamic characteristics.

Authors:  Heng Wei; Wenrui Han; Qi Tian; Kun Yao; Peibang He; Jianfeng Wang; Yujia Guo; Qianxue Chen; Mingchang Li
Journal:  Front Neurol       Date:  2022-09-14       Impact factor: 4.086

9.  Predicting 1-Hour Thrombolysis Effect of r-tPA in Patients With Acute Ischemic Stroke Using Machine Learning Algorithm.

Authors:  Bin Zhu; Jianlei Zhao; Mingnan Cao; Wanliang Du; Liuqing Yang; Mingliang Su; Yue Tian; Mingfen Wu; Tingxi Wu; Manxia Wang; Xingquan Zhao; Zhigang Zhao
Journal:  Front Pharmacol       Date:  2022-01-03       Impact factor: 5.810

  9 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.