目的旨在比较logistic回归分析、决策树和随机森林算法构建的3种老年心力衰竭患者衰弱风险预测模型的性能。方法采用便利抽样法,选取2022年9月至2023年10月南通大学附属医院心血管内科收治的老年心力衰竭患者426例。根据衰弱评估结果分...目的旨在比较logistic回归分析、决策树和随机森林算法构建的3种老年心力衰竭患者衰弱风险预测模型的性能。方法采用便利抽样法,选取2022年9月至2023年10月南通大学附属医院心血管内科收治的老年心力衰竭患者426例。根据衰弱评估结果分为衰弱组194例,非衰弱组232例,又按7?3比例分为训练集299例和测试集127例。并在训练集中构建logistic回归分析模型、决策树模型及随机森林模型,在测试集中验证。采用ROC曲线分析计算曲线下面积(area under curve,AUC)及混淆矩阵对训练集和测试集模型进行评价,通过比较模型在测试集中的性能选出最佳模型。结果Logistic回归模型、决策树模型和随机森林模型在测试集的AUC分别为0.898、0.825、0.903,分类正确率分别为84.25%、77.95%、83.46%,敏感性分别为82.76%、68.97%、82.76%,特异性分别为85.51%、85.51%、84.06%,阳性预测值分别为82.76%、80.00%、81.36%,阴性预测值分别为85.51%、76.62%、85.29%。影响因素分别为年龄、左心房内径、抑郁、白蛋白、身体活动水平和社会支持度。结论Logistic回归模型预测老年心力衰竭患者衰弱风险性能较决策树模型和随机森林模型更好。展开更多
Objective To observe value of 0D-1D coupling model and 3D fluid-structure interaction(FSI)model based on coronary CT angiography(CCTA)for displaying hemodynamic characteristics of coronary artery stenosis.Methods Base...Objective To observe value of 0D-1D coupling model and 3D fluid-structure interaction(FSI)model based on coronary CT angiography(CCTA)for displaying hemodynamic characteristics of coronary artery stenosis.Methods Based on CCTA data of the stenosed left anterior descending branch(LAD)in a patient with coronary heart disease,an 0D-1D coupling model and 3D FSI model were built,respectively.Then hemodynamic characteristic indexes,including the pressure,flow velocity and wall shear stress(WSS)were obtained in every 0.01 s during 1 s at 5 sampling points(i.e.sampling point 1—5)using these 2 models,respectively,and the consistencies of the results between models were evaluated with Spearman correlation coefficient r s.Results The time consuming for construction of 0D-1D coupling model and 3D FSI model was 0.033 min and 704 min,respectively.Both models showed basically distribution of the pressure,flow velocity and WSS of the stenosed LAD.For more details,the pressure at the stenosed segment of LAD and the proximal segment of stenosis were both higher,which gradually decreased at the distal segment of stenosis,and the flow velocity at the proximal segment of stenosis was in a relatively slow and uniform condition,with significantly increased flow velocity and WSS at the stenosed segment.Compared with 3D FSI model,0D-1D vascular coupling model was relatively unrefined and lack of distal flow lines when displaying blood flow velocity.For sampling point 2 at the stenosed segment of LAD,no significant consistency for pressure between 2 models was found(P=0.118),but strong consistency for the flow velocity and WSS(r s=0.730,0.807,both P<0.05).The consistencies of pressure,flow velocity and WSS between 2 models at the proximal and distal segment of stenosis,i.e.1,3—5 sampling points were week to moderate(r s=0.237—0.669,all P<0.05).Conclusion 0D-1D coupling model exhibited outstanding computational efficiency and might provide relatively reasonable results,while 3D FSI model showed higher accuracy for details and streamline when simulating LAD stenosis.展开更多
目的了解居家慢性心力衰竭患者家庭照顾者的生存质量并探讨其影响因素。方法方便性抽样选取155例居家慢性心力衰竭患者的家庭照顾者,采用家庭照顾者生存质量量表和一般自我效能感量表对其进行调查。结果居家慢性心力衰竭患者家庭照顾者...目的了解居家慢性心力衰竭患者家庭照顾者的生存质量并探讨其影响因素。方法方便性抽样选取155例居家慢性心力衰竭患者的家庭照顾者,采用家庭照顾者生存质量量表和一般自我效能感量表对其进行调查。结果居家慢性心力衰竭患者家庭照顾者的生存质量总分为(54.91±10.45)分;多元线性逐步回归分析显示,照顾者的自我效能、患者的纽约心脏病协会(the New York Heart Association,NYHA)心功能分级、照顾者的文化程度是居家慢性心力衰竭患者家庭照顾者生存质量的主要影响因素。结论居家慢性心力衰竭患者家庭照顾者的生存质量因照护任务而受损,尤其对于自我效能差、文化水平低、所照顾患者心功能差的照顾者更应给予关注。展开更多
文摘目的旨在比较logistic回归分析、决策树和随机森林算法构建的3种老年心力衰竭患者衰弱风险预测模型的性能。方法采用便利抽样法,选取2022年9月至2023年10月南通大学附属医院心血管内科收治的老年心力衰竭患者426例。根据衰弱评估结果分为衰弱组194例,非衰弱组232例,又按7?3比例分为训练集299例和测试集127例。并在训练集中构建logistic回归分析模型、决策树模型及随机森林模型,在测试集中验证。采用ROC曲线分析计算曲线下面积(area under curve,AUC)及混淆矩阵对训练集和测试集模型进行评价,通过比较模型在测试集中的性能选出最佳模型。结果Logistic回归模型、决策树模型和随机森林模型在测试集的AUC分别为0.898、0.825、0.903,分类正确率分别为84.25%、77.95%、83.46%,敏感性分别为82.76%、68.97%、82.76%,特异性分别为85.51%、85.51%、84.06%,阳性预测值分别为82.76%、80.00%、81.36%,阴性预测值分别为85.51%、76.62%、85.29%。影响因素分别为年龄、左心房内径、抑郁、白蛋白、身体活动水平和社会支持度。结论Logistic回归模型预测老年心力衰竭患者衰弱风险性能较决策树模型和随机森林模型更好。
文摘Objective To observe value of 0D-1D coupling model and 3D fluid-structure interaction(FSI)model based on coronary CT angiography(CCTA)for displaying hemodynamic characteristics of coronary artery stenosis.Methods Based on CCTA data of the stenosed left anterior descending branch(LAD)in a patient with coronary heart disease,an 0D-1D coupling model and 3D FSI model were built,respectively.Then hemodynamic characteristic indexes,including the pressure,flow velocity and wall shear stress(WSS)were obtained in every 0.01 s during 1 s at 5 sampling points(i.e.sampling point 1—5)using these 2 models,respectively,and the consistencies of the results between models were evaluated with Spearman correlation coefficient r s.Results The time consuming for construction of 0D-1D coupling model and 3D FSI model was 0.033 min and 704 min,respectively.Both models showed basically distribution of the pressure,flow velocity and WSS of the stenosed LAD.For more details,the pressure at the stenosed segment of LAD and the proximal segment of stenosis were both higher,which gradually decreased at the distal segment of stenosis,and the flow velocity at the proximal segment of stenosis was in a relatively slow and uniform condition,with significantly increased flow velocity and WSS at the stenosed segment.Compared with 3D FSI model,0D-1D vascular coupling model was relatively unrefined and lack of distal flow lines when displaying blood flow velocity.For sampling point 2 at the stenosed segment of LAD,no significant consistency for pressure between 2 models was found(P=0.118),but strong consistency for the flow velocity and WSS(r s=0.730,0.807,both P<0.05).The consistencies of pressure,flow velocity and WSS between 2 models at the proximal and distal segment of stenosis,i.e.1,3—5 sampling points were week to moderate(r s=0.237—0.669,all P<0.05).Conclusion 0D-1D coupling model exhibited outstanding computational efficiency and might provide relatively reasonable results,while 3D FSI model showed higher accuracy for details and streamline when simulating LAD stenosis.
文摘目的了解居家慢性心力衰竭患者家庭照顾者的生存质量并探讨其影响因素。方法方便性抽样选取155例居家慢性心力衰竭患者的家庭照顾者,采用家庭照顾者生存质量量表和一般自我效能感量表对其进行调查。结果居家慢性心力衰竭患者家庭照顾者的生存质量总分为(54.91±10.45)分;多元线性逐步回归分析显示,照顾者的自我效能、患者的纽约心脏病协会(the New York Heart Association,NYHA)心功能分级、照顾者的文化程度是居家慢性心力衰竭患者家庭照顾者生存质量的主要影响因素。结论居家慢性心力衰竭患者家庭照顾者的生存质量因照护任务而受损,尤其对于自我效能差、文化水平低、所照顾患者心功能差的照顾者更应给予关注。
