Objective Asymptomatic carotid stenosis(ACS)is closely associated to the incidence of severe cerebrovascular diseases.Early identifying the individuals with ACS and its associated risk factors could be beneficial for ...Objective Asymptomatic carotid stenosis(ACS)is closely associated to the incidence of severe cerebrovascular diseases.Early identifying the individuals with ACS and its associated risk factors could be beneficial for primary prevention of stroke.This study aimed to investigate a machine-learning algorithm for the detection of ACS among high-risk population of stroke based on the associated risk factors.Methods A novel model of machine learning was utilized to screen the associated predictors of ACS based on 30 potential risk factors.The algorithm of this model adopted a random forest pattern based on the training data and then was verified using the testing data.All of the original data were retrieved from the China National Stroke Screening and Prevention Project(CNSSPP),including demographic,clinical and laboratory characteristics.The individuals with high risk of stroke were enrolled and randomly divided into a training group and a testing group at a ratio of 4:1.The identification of carotid stenosis by carotid artery duplex scans was set as the golden standard.The receiver operating characteristic(ROC)curve and the area under the curve(AUC)was used to evaluate the efficacy of the model in detecting ACS.Results Of 2841 high risk individual of stroke enrolled,326(11.6%)were diagnosed as ACS by ultrasonography.The top five risk fectors contributing to ACS in this model were identified as family history of dyslipidemia,high level of lowdensity lipoprotein cholesterol(LDL-c),low level of high-density lipoprotein cholesterol(HDL-c),aging,and low body.展开更多
Objective: This paper aims to screen and analyze the current status of high-risk stroke patients in Shashi District of Jingzhou City and the exposure levels of related risk factors, and provides suggestions as the ref...Objective: This paper aims to screen and analyze the current status of high-risk stroke patients in Shashi District of Jingzhou City and the exposure levels of related risk factors, and provides suggestions as the references for prevention and treatment of stroke. Methods: Using cluster sampling, on-site investigations were conducted on 1060 permanent residents aged 40 years and over at 3 townships and 2 communities in Shashi District of Jingzhou City from January 2018 to December 2018. Risk assessment of stroke is based on the stroke risk screening form. Statistical analysis was performed by using SPSS 22.0 software. Results: After making a stroke risk assessment, a total of 313 high-risk stroke patients were screened, and the detection rate was 29.53%. The exposure rate of risk factors from high to low was hypertension (70.93%), dyslipidemia (46.33%), less physical exercise (46.01%), diabetes (36.10%), overweight (33.55%), smoking (33.23%), family history of stroke (24.92%), atrial fibrillation or valvular heart disease (7.35%). There are statistically significant differences among all risk factors between the high-risk group and middle and low-risk groups (P Conclusion: The detection rate of high-risk stroke patients in Shashi District of Jingzhou City is high. Hypertension, dyslipidemia and less physical exercise are the main risk factors of stroke occurrence and recurrence in the region. The prevention and treatment of risk factors for stroke should be strengthened to control the incidence and recurrence rate of stroke.展开更多
目的:探讨中风高危人群腰高比(Waist to Height Ratio,WHtR)及其他危险因素与颈动脉粥样硬化(CAS)的关系。方法:选取2013年5月至2016年7月北京市丰台区8个社区卫生服务中心进行横断面研究。筛选9605例脑卒中高危患者并收集基本信息。CA...目的:探讨中风高危人群腰高比(Waist to Height Ratio,WHtR)及其他危险因素与颈动脉粥样硬化(CAS)的关系。方法:选取2013年5月至2016年7月北京市丰台区8个社区卫生服务中心进行横断面研究。筛选9605例脑卒中高危患者并收集基本信息。CAS的诊断是基于颈动脉斑块的存在和颈动脉内膜中层厚度(cIMT)的增加。结果:对9605例受试者进行分析,CAS的患病率为75.12%。在最终调整的模型中,WHtR与CAS升高显著相关(OR 1.23,95%CI 1.10~1.39)。影响CAS的其他风险因素包括:年龄、性别、中风、高血压、糖尿病、吸烟、缺乏体育锻炼。结论:在脑卒中高危人群中,建议将WHtR作为CAS的提示指标。控制WHtR有利于CAS的早期发现和早期干预,减少脑血管事件的发生。展开更多
基金Fund supported by the Medical Science and Tech no logy Development Foundatio n(YKK18114)the Gen era I Social Development Medical and Health Project of Nanjing Science and Technology Commission(201803029).
文摘Objective Asymptomatic carotid stenosis(ACS)is closely associated to the incidence of severe cerebrovascular diseases.Early identifying the individuals with ACS and its associated risk factors could be beneficial for primary prevention of stroke.This study aimed to investigate a machine-learning algorithm for the detection of ACS among high-risk population of stroke based on the associated risk factors.Methods A novel model of machine learning was utilized to screen the associated predictors of ACS based on 30 potential risk factors.The algorithm of this model adopted a random forest pattern based on the training data and then was verified using the testing data.All of the original data were retrieved from the China National Stroke Screening and Prevention Project(CNSSPP),including demographic,clinical and laboratory characteristics.The individuals with high risk of stroke were enrolled and randomly divided into a training group and a testing group at a ratio of 4:1.The identification of carotid stenosis by carotid artery duplex scans was set as the golden standard.The receiver operating characteristic(ROC)curve and the area under the curve(AUC)was used to evaluate the efficacy of the model in detecting ACS.Results Of 2841 high risk individual of stroke enrolled,326(11.6%)were diagnosed as ACS by ultrasonography.The top five risk fectors contributing to ACS in this model were identified as family history of dyslipidemia,high level of lowdensity lipoprotein cholesterol(LDL-c),low level of high-density lipoprotein cholesterol(HDL-c),aging,and low body.
文摘Objective: This paper aims to screen and analyze the current status of high-risk stroke patients in Shashi District of Jingzhou City and the exposure levels of related risk factors, and provides suggestions as the references for prevention and treatment of stroke. Methods: Using cluster sampling, on-site investigations were conducted on 1060 permanent residents aged 40 years and over at 3 townships and 2 communities in Shashi District of Jingzhou City from January 2018 to December 2018. Risk assessment of stroke is based on the stroke risk screening form. Statistical analysis was performed by using SPSS 22.0 software. Results: After making a stroke risk assessment, a total of 313 high-risk stroke patients were screened, and the detection rate was 29.53%. The exposure rate of risk factors from high to low was hypertension (70.93%), dyslipidemia (46.33%), less physical exercise (46.01%), diabetes (36.10%), overweight (33.55%), smoking (33.23%), family history of stroke (24.92%), atrial fibrillation or valvular heart disease (7.35%). There are statistically significant differences among all risk factors between the high-risk group and middle and low-risk groups (P Conclusion: The detection rate of high-risk stroke patients in Shashi District of Jingzhou City is high. Hypertension, dyslipidemia and less physical exercise are the main risk factors of stroke occurrence and recurrence in the region. The prevention and treatment of risk factors for stroke should be strengthened to control the incidence and recurrence rate of stroke.
