期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
Deep learning algorithm using fundus photographs for 10-year risk assessment of ischemic cardiovascular diseases in China 被引量:4
1
作者 Yanjun Ma Jianhao Xiong +15 位作者 Yidan Zhu Zongyuan Ge Rong Hua Meng Fu Chenglong Li Bin Wang Li Dong Xin Zhao Jili Chen Ce Rong Chao He Yuzhong Chen Zhaohui Wang Wenbin Wei Wuxiang Xie Yangfeng Wu 《Science Bulletin》 SCIE EI CSCD 2022年第1期17-20,M0003,共5页
缺血性心脑血管病(ischemic cardiovascular diseases,ICVD)包括缺血性卒中与缺血性心脏病.传统的基于危险因素的ICVD风险预测模型在实践推广中受限,本文旨在开发并验证一种利用眼底照片估算10年ICVD风险的深度学习算法,用于替代传统模... 缺血性心脑血管病(ischemic cardiovascular diseases,ICVD)包括缺血性卒中与缺血性心脏病.传统的基于危险因素的ICVD风险预测模型在实践推广中受限,本文旨在开发并验证一种利用眼底照片估算10年ICVD风险的深度学习算法,用于替代传统模型.算法的开发和验证均以传统模型所预测的10年ICVD风险为参照.研究基于体检人群(390,947人)数据开发卷积神经网络算法.在内部验证(20,571人)中,该算法估算10年ICVD风险的自然对数的调整R^(2)为0.876,筛查临界/中等及以上(≥5%/≥7.5%)ICVD风险人群的受试者工作特征曲线(ROC)下面积(AUC)分别为0.971(95%CI:0.967~0.975)和0.976(95%CI:0.973~0.980);在中老年人群的外部验证(1309人)中,调整R^(2)为0.638,AUC分别为0.859(95%CI:0.822~0.895)和0.876(95%CI:0.816~0.937).该算法有望替代传统ICVD风险预测模型,用于在基层医疗机构进行ICVD风险快速筛查,但仍需前瞻性研究进行验证. 展开更多
关键词 风险预测模型 基层医疗机构 缺血性卒中 缺血性心脑血管病 缺血性心脏病 体检人群 中老年人群 卷积神经网络
原文传递
Low levels of low-density lipoprotein cholesterol and cognitive decline 被引量:4
2
作者 Rong Hua Yanjun Ma +2 位作者 Chenglong Li Baoliang Zhong Wuxiang Xie 《Science Bulletin》 SCIE EI CSCD 2021年第16期1684-1690,M0004,共8页
The relationship between low levels of serum low-density lipoprotein cholesterol(LDL-C)and subsequent cognitive decline remains unclear.The present study aimed to evaluate the longitudinal association between low LDL-... The relationship between low levels of serum low-density lipoprotein cholesterol(LDL-C)and subsequent cognitive decline remains unclear.The present study aimed to evaluate the longitudinal association between low LDL-C levels and cognition decline in the context of the current aggressive guideline-recommended targets(LDL-C levels less than 55 mg/dL for individuals at very high risk of cardiovascular events,and less than 70 mg/dL for high risk individuals).Data from wave 13(2016)to wave 14(2018)of the Health and Retirement Study(HRS)were utilized.LDL-C concentrations measured at wave 13 were categorized into 5 levels,reflecting currently recommended values for lipid lowering treatment.Of 7129 included participants(mean age:69.0±9.9 years,60.3%female),we found that compared to participants with LDL-C levels of 70.0-99.9 mg/dL,those with LDL-C levels of<55 mg/dL had significantly slower 2-year decline rates in global cognitive function(0.244 point/year;95%confidence interval(CI):0.065-0.422;P=0.008),working memory(0.068 point/year;95%CI:0.004-0.133;P=0.038),and borderline significantly in episodic memory(0.155 point/year;95%CI:-0.004-0.315;P=0.057).Similarly,significantly slower decline rates were observed in those with LDL-C levels of 55.0-69.9 mg/dL.The present study demonstrated that compared with LDL-C levels 70.0-99.9 mg/dL,low LDL-C levels(<70 mg/dL,especially<55 mg/dL)were associated with significantly slower cognitive decline in population-based setting.Future randomized controlled trials are warranted to ascertain the safety and benefit of current aggressive guideline-recommended targets on cognitive function. 展开更多
关键词 Low-density lipoprotein cholesterol Cognitive decline Longitudinal cohort study The Health and Retirement Study
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部