国家神经系统疾病临床医学研究中心数据管理与共享系统
Data Management And Sharing System of China National Clinical Research Center for Neurological Diseases
Predicting functional outcome in ischemic stroke patients using genetic, environmental, and clinical factors: a machine learning analysis of population-based prospective cohort study
第一作者：Siding chen
基本信息
- 负责人：Siding chen
- 数据来源： CNSR-Ⅲ
- 论文编号：CNSR-Ⅲ20230053
- 发表时间：2024-10-13
2024-10-13
已发表文章
主要研究背景及目的
background: The burden of cerebrovascular disease in China ranks first in the world. The incidence, recurrence rate, disability rate, high mortality rate, and social burden of cerebrovascular disease are heavy. In the existing treatment model, there are still residual risks after treatment of patients with cerebrovascular disease. It is necessary to understand the potential pathological mechanism of cerebrovascular disease by integrating multiple groups of scientific materials. The genetic mechanism is part of the reasons that affect the prognosis of stroke. The results have supported the effects of genes in human and animal research on the recovery of genes after brain injury. To date, few GWAS studies have been published on the prognosis and outcomes of patients with AIS, and this hypothetical approach may identify variations in the pathophysiological process after stroke or new pathways affecting recovery, thereby providing new targets for intervention and drug development. purpose: To explore the influence of SNPs variants on functional outcomes after AIS, genome-wide association analysis (GWAS) was used to discover common genetic variants related to prognosis after stroke, and to explore the mechanism association with recovery after stroke. An accurate prediction model was constructed based on genomic data to provide reference for patients to customize personalized secondary prevention and rehabilitation plans.
方法
The risk factors related to stroke prognosis and recovery were described, and the loci related to the phenotype were found by GWAS. According to the results of the loci, the SNP loci included in the subsequent prediction modeling were considered, and the dimensionality reduction modeling was performed by machine learning algorithms
结论
In conclusion, this study established a 6-month functional outcome prediction model for IS patients by integrating genetic, environmental, and clinical factors through ML algorithms. Our results demonstrated that ML outperformed LR models in predictive power, with the XGBoost model exhibiting the highest performance. Moreover, our analysis indicated the ANKS1B gene as a potentially crucial genetic factor in IS.
主要结果
We conducted genome-wide association studies (GWAS) in the development cohort, identifying rs11109607 (ANKS1B) as the most significant variant associated with IS functional outcome. We employed principal component analysis to reduce dimensionality on the top 100 significant variants identified by the GWAS, incorporating them as genetic factors in the predictive model. We employed a machine learning algorithm capable of identifying nonlinear relationships to establish predictive models for IS patient functional outcome. The optimal model was the XGBoost model, which outperformed the logistic regression model (AUC 0.818 versus 0.756, P < .05) and significantly improved reclassification efficiency. Our study innovatively incorporated genetic, environmental, and clinical factors for predicting the IS functional outcome in East Asian populations, thereby offering novel insights into IS functional outcome.