Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of tra...Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of traditional Machine Learning (ML) and Deep Learning (DL) models in predicting CVD risk, utilizing a meticulously curated dataset derived from health records. Rigorous preprocessing, including normalization and outlier removal, enhances model robustness. Diverse ML models (Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Gradient Boosting) are compared with a Long Short-Term Memory (LSTM) neural network for DL. Evaluation metrics include accuracy, ROC AUC, computation time, and memory usage. Results identify the Gradient Boosting Classifier and LSTM as top performers, demonstrating high accuracy and ROC AUC scores. Comparative analyses highlight model strengths and limitations, contributing valuable insights for optimizing predictive strategies. This study advances predictive analytics for cardiovascular health, with implications for personalized medicine. The findings underscore the versatility of intelligent systems in addressing health challenges, emphasizing the broader applications of ML and DL in disease identification beyond cardiovascular health.展开更多
Cardiovascular disease is a significant cause of death in humans. Various models are necessary for the study ofcardiovascular diseases, but once cellular and animal models have some defects, such as insufficient fidel...Cardiovascular disease is a significant cause of death in humans. Various models are necessary for the study ofcardiovascular diseases, but once cellular and animal models have some defects, such as insufficient fidelity. As anew technology, organoid has certain advantages and has been used in many applications in the study of cardiovasculardiseases. This article aims to summarize the application of organoid platforms in cardiovasculardiseases, including organoid construction schemes, modeling, and application of cardiovascular organoids. Advancesin cardiovascular organoid research have provided many models for different cardiovascular diseases in avariety of areas, including myocardium, blood vessels, and valves. Physiological and pathological models ofdifferent diseases, drug research models, and methods for evaluating and promoting the maturation of differentkinds of organ tissues are provided for various cardiovascular diseases, including cardiomyopathy, myocardialinfarction, and atherosclerosis. This article provides a comprehensive overview of the latest research progress incardiovascular organ tissues, including construction protocols for cardiovascular organoid tissues and theirevaluation system, different types of disease models, and applications of cardiovascular organoid models invarious studies. The problems and possible solutions in organoid development are summarized.展开更多
Aortic valve calcification disease (CAVD) is the most prevalent degenerative valve disease in humans, leading to significant morbidity and mortality. Despite its common occurrence, our understanding of the underlying ...Aortic valve calcification disease (CAVD) is the most prevalent degenerative valve disease in humans, leading to significant morbidity and mortality. Despite its common occurrence, our understanding of the underlying mechanisms remains incomplete, and available treatment options are limited and risky. A more comprehensive understanding of the biology of CAVD is essential to identify new therapeutic strategies. Animal models have played a crucial role in advancing our knowledge of CAVD and exploring potential treatments. However, these models have inherent limitations as they cannot fully replicate the complex physiological mechanisms of human CAVD. In this review, we examine various CAVD models ranging from pigs to mice, highlighting the unique characteristics of each model to enhance our understanding of CAVD. While these models offer valuable insights, they also have limitations and shortcomings. We propose that the guide wire model shows promise for future CAVD research, and streamlining the methodology could enhance our understanding and expand the research scope in this field.展开更多
The human cardiovascular system is a closed- loop and complex vascular network with multi-scaled het- erogeneous hemodynamic phenomena. Here, we give a selective review of recent progress in macro-hemodynamic modeling...The human cardiovascular system is a closed- loop and complex vascular network with multi-scaled het- erogeneous hemodynamic phenomena. Here, we give a selective review of recent progress in macro-hemodynamic modeling, with a focus on geometrical multi-scale model- ing of the vascular network, micro-hemodynamic modeling of microcirculation, as well as blood cellular, subcellular, endothelial biomechanics, and their interaction with arter- ial vessel mechanics. We describe in detail the methodology of hemodynamic modeling and its potential applications in cardiovascular research and clinical practice. In addition, we present major topics for future study： recent progress of patient-specific hemodynamic modeling in clinical applica- tions, micro-hemodynamic modeling in capillaries and blood cells, and the importance and potential of the multi-scale hemodynarnic modeling.展开更多
AIM To investigate the incidence and the determinants of cardiovascular morbidity in Greek renal transplant recipients(RTRs) expressed as major advance cardiac event(MACE) rate. METHODS Two hundred and forty-two adult...AIM To investigate the incidence and the determinants of cardiovascular morbidity in Greek renal transplant recipients(RTRs) expressed as major advance cardiac event(MACE) rate. METHODS Two hundred and forty-two adult patients with a functioning graft for at least three months and availabledata that were followed up on the August 31, 2015 at two transplant centers of Western Greece were included in this study. Baseline recipients' data elements included demographics, clinical characteristics, history of comorbid conditions and laboratory parameters. Follow-up data regarding MACE occurrence were collected retrospectively from the patients' records and MACE risk score was calculated for each patient. RESULTS The mean age was 53 years(63.6% males) and 47 patients(19.4%) had a pre-existing cardiovascular disease(CVD) before transplantation. The mean estimated glomerular filtration rate was 52 ± 17 mL /min per 1.73 m2. During follow-up 36 patients(14.9%) suffered a MACE with a median time to MACE 5 years(interquartile range: 2.2-10 years). Recipients with a MACE compared to recipients without a MACE had a significantly higher mean age(59 years vs 52 years, P < 0.001) and a higher prevalence of pre-existing CVD(44.4% vs 15%, P < 0.001). The 7-year predicted mean risk for MACE was 14.6% ± 12.5% overall. In RTRs who experienced a MACE, the predicted risk was 22.3% ± 17.1% and was significantly higher than in RTRs without an event 13.3% ± 11.1%(P = 0.003). The discrimination ability of the model in the Greek database of RTRs was good with an area under the receiver operating characteristics curve of 0.68(95%CI: 0.58-0.78).CONCLUSION In this Greek cohort of RTRs, MACE occurred in 14.9% of the patients, pre-existing CVD was the main risk factor, while MACE risk model was proved a dependable utility in predicting CVD post RT.展开更多
目的通过构建并验证中老年人群颈动脉斑块的预测模型及对应用价值探讨。方法回顾性收集2017—2019年于上海交通大学医学院附属仁济医院内分泌科门诊完成颈动脉超声检查患者的临床资料,性别不限,年龄≥45岁。共纳入1416例样本,训练集993...目的通过构建并验证中老年人群颈动脉斑块的预测模型及对应用价值探讨。方法回顾性收集2017—2019年于上海交通大学医学院附属仁济医院内分泌科门诊完成颈动脉超声检查患者的临床资料,性别不限,年龄≥45岁。共纳入1416例样本,训练集993例,验证集423例。按照7∶3的比例随机分为训练集和验证集,在训练集中比较颈动脉斑块组与非颈动脉斑块组各临床指标差异,并将特征指标变量采用多因素Logistic回归分析确定颈动脉斑块发生的独立危险素,依次构建中老年人群颈动脉斑块发生风险的可视化列线图模型。通过校准曲线和受试者操作特征曲线(receiver operator characteristic curve,ROC曲线)验证模型的区分度、一致性和准确性,最后采用决策曲线分析法确定模型的临床实用性,并通过外部验证进行评估。结果最终本研究纳入1416例患者,有483例(34.11%)有颈动脉斑块。多因素Logistic回归分析结果显示,年龄、收缩压、γ-谷氨酰转肽酶、糖化血红蛋白是颈动脉斑块发生的危险因素,而相较于男性,女性是颈动脉斑块发生的保护因素。依此构建可视化列线图模型,训练集ROC曲线下面积(area under the curve,AUC)为0.75(95%CI:0.72~0.78),验证集ROC曲线的AUC为0.71(95%CI:0.66~0.76)。训练集与验证集校准曲线Hosmer-Lemeshow拟合优度检验显示P值均>0.05(训练集P=0.7501,验证集P=0.9872)。决策曲线结果显示预测模型在训练集和验证集的阈值概率分别为5%~98%和1%~81%。结论基于指标(性别、年龄、收缩压、谷氨酰转肽酶、糖化血红蛋白),成功建立了中老年人群颈动脉斑块发生风险的预测模型,该模型预测效能较好,可用于社区或者农村等偏远地区居民普查,有助于颈动脉斑块的早期识别,进而改善预后。展开更多
目的:在中国鄞州电子健康档案研究(Chinese electronic health records research in Yinzhou,CHERRY)的队列人群中,评价启动降压药物治疗的不同策略预防心血管病的健康收益与干预效率。方法:采用马尔科夫模型模拟评价的不同策略包括:策...目的:在中国鄞州电子健康档案研究(Chinese electronic health records research in Yinzhou,CHERRY)的队列人群中,评价启动降压药物治疗的不同策略预防心血管病的健康收益与干预效率。方法:采用马尔科夫模型模拟评价的不同策略包括:策略1,对收缩压≥140 mmHg的人群启动降压药物治疗(根据2020年《中国心血管病一级预防指南》);策略2,对收缩压≥130 mmHg的人群启动降压药物治疗;策略3,对收缩压≥140 mmHg以及130~140 mmHg且心血管病高风险人群启动降压药物治疗(根据2017年美国心脏病学会/美国心脏协会《成年人高血压预防、检测、评估和管理指南》);策略4,对收缩压≥160 mmHg以及140~160 mmHg且心血管病高风险人群启动降压药物治疗(根据2019年英国国家卫生与临床优化研究所《成年人高血压诊断与管理指南》)。采用2019年世界卫生组织心血管病风险评估模型进行风险分层。马尔科夫模型的循环周期设为1年,模拟10个周期后计算质量调整生命年(quality-adjusted life year,QALY)、心血管病发病数、全因死亡数等结局事件数以评价策略的健康收益,并计算每预防一例心血管病事件或全因死亡的需治疗人数(number needed to treat,NNT)以评价策略的干预效率。马尔科夫模型的参数主要来源于CHERRY队列与公开发表的文献。采用单因素敏感性分析探讨心血管病发病率对结果的影响,采用概率敏感性分析探讨干预措施效应参数的不确定性对结果的影响。结果:共纳入213987名35~79岁基线无心血管病史的人群。相比于策略1,单纯下调降压起始值的策略2可预防的心血管病发病数增加666(95%UI:334~975)例,但每预防一例心血管病发病的NNT增加10(95%UI:7~20)人;而考虑定量风险评估的策略3可预防的心血管病发病数增加388(95%UI:194~569)例,且每预防一例心血管病发病的NNT减少6(95%UI:4~12)人,提示策略3可增加健康收益并具有更高的干预效率。策略4相比于策略1,可预防的心血管病发病数虽然减少193(95%UI:98~281)例,但每预防一例心血管病事件的NNT减少18(95%UI:13~37)人,效率更高。单因素敏感性分析及概率敏感性分析结果与主分析结果一致。结论:在中国发达地区的社区人群中选择降压药物治疗目标人群时,结合心血管病定量风险评估的策略优于单纯将起始值从140 mmHg降至130 mmHg的策略,前者可提升健康收益且兼顾干预效率;不同地区需因地制宜选择降压起始值并结合定量风险评估的策略,以权衡健康收益与干预效率。展开更多
目的:系统评价心血管疾病病人衰弱发生风险预测模型。方法:系统检索中国知网、中国生物医学文献数据库、万方数据库、维普数据库、PubMed、Embase、the Cochrane Library、Web of Science数据库中关于心血管疾病病人衰弱发生风险预测模...目的:系统评价心血管疾病病人衰弱发生风险预测模型。方法:系统检索中国知网、中国生物医学文献数据库、万方数据库、维普数据库、PubMed、Embase、the Cochrane Library、Web of Science数据库中关于心血管疾病病人衰弱发生风险预测模型的研究,同时对检索到的文献进行溯源,检索时限为建库至2024年2月29日。由2名研究员独立筛选文献、提取资料并评价纳入研究的偏倚风险。结果:共纳入8项研究,共8个心血管疾病病人衰弱发生风险预测模型,研究总样本量为346~1654例,发生衰弱事件数为98~560例。8个模型均未行外部验证,6个模型仅行内部验证,模型受试者工作特征曲线下面积为0.781~0.991。所纳入预测模型中常见的心血管疾病病人衰弱发生易感因素和速发因素分别为合并症、年龄、日常生活能力、失眠以及营养不良。结论:当前心血管疾病病人衰弱发生风险的预测模型在效能上表现优异,展现出较高的区分度及适用性。然而,模型质量仍有提升空间。在未来的研究中,研究者们需重点关注数据来源的可靠性、预测因素选择的精确性及其测量的标准性,同时妥善处理缺失数据,并全面评价模型性能。此外,对现有模型进行外部验证至关重要,以确保模型的可移植性和可泛化性,使其能够更有效地指导临床实践。展开更多
文摘Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of traditional Machine Learning (ML) and Deep Learning (DL) models in predicting CVD risk, utilizing a meticulously curated dataset derived from health records. Rigorous preprocessing, including normalization and outlier removal, enhances model robustness. Diverse ML models (Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Gradient Boosting) are compared with a Long Short-Term Memory (LSTM) neural network for DL. Evaluation metrics include accuracy, ROC AUC, computation time, and memory usage. Results identify the Gradient Boosting Classifier and LSTM as top performers, demonstrating high accuracy and ROC AUC scores. Comparative analyses highlight model strengths and limitations, contributing valuable insights for optimizing predictive strategies. This study advances predictive analytics for cardiovascular health, with implications for personalized medicine. The findings underscore the versatility of intelligent systems in addressing health challenges, emphasizing the broader applications of ML and DL in disease identification beyond cardiovascular health.
基金supported by the National Science Fund for Distinguished Young Scholars(Grant No.82125004).
文摘Cardiovascular disease is a significant cause of death in humans. Various models are necessary for the study ofcardiovascular diseases, but once cellular and animal models have some defects, such as insufficient fidelity. As anew technology, organoid has certain advantages and has been used in many applications in the study of cardiovasculardiseases. This article aims to summarize the application of organoid platforms in cardiovasculardiseases, including organoid construction schemes, modeling, and application of cardiovascular organoids. Advancesin cardiovascular organoid research have provided many models for different cardiovascular diseases in avariety of areas, including myocardium, blood vessels, and valves. Physiological and pathological models ofdifferent diseases, drug research models, and methods for evaluating and promoting the maturation of differentkinds of organ tissues are provided for various cardiovascular diseases, including cardiomyopathy, myocardialinfarction, and atherosclerosis. This article provides a comprehensive overview of the latest research progress incardiovascular organ tissues, including construction protocols for cardiovascular organoid tissues and theirevaluation system, different types of disease models, and applications of cardiovascular organoid models invarious studies. The problems and possible solutions in organoid development are summarized.
文摘Aortic valve calcification disease (CAVD) is the most prevalent degenerative valve disease in humans, leading to significant morbidity and mortality. Despite its common occurrence, our understanding of the underlying mechanisms remains incomplete, and available treatment options are limited and risky. A more comprehensive understanding of the biology of CAVD is essential to identify new therapeutic strategies. Animal models have played a crucial role in advancing our knowledge of CAVD and exploring potential treatments. However, these models have inherent limitations as they cannot fully replicate the complex physiological mechanisms of human CAVD. In this review, we examine various CAVD models ranging from pigs to mice, highlighting the unique characteristics of each model to enhance our understanding of CAVD. While these models offer valuable insights, they also have limitations and shortcomings. We propose that the guide wire model shows promise for future CAVD research, and streamlining the methodology could enhance our understanding and expand the research scope in this field.
基金supported by Grant-in-Aid for Scientifi Research(Grant(B)17300141)the Development and Use of the Next Generation Supercomputer Project of the MEXT,Japan+4 种基金Fuyou Liang was supported by the National Natural Science Foundation of China(Grant 81370438)the SJTU Medical Engineering Cross-cutting Research Foundation(Grant YG2012MS24)Ken-iti Tsubota was partly funded by a Grant-in-Aid for Challenging Exploratory Research(Grant 25630046),JSPSsupporting the computing facilities essential for the completion of this studyFinancial support provided by HKUST to JW is acknowledged
文摘The human cardiovascular system is a closed- loop and complex vascular network with multi-scaled het- erogeneous hemodynamic phenomena. Here, we give a selective review of recent progress in macro-hemodynamic modeling, with a focus on geometrical multi-scale model- ing of the vascular network, micro-hemodynamic modeling of microcirculation, as well as blood cellular, subcellular, endothelial biomechanics, and their interaction with arter- ial vessel mechanics. We describe in detail the methodology of hemodynamic modeling and its potential applications in cardiovascular research and clinical practice. In addition, we present major topics for future study： recent progress of patient-specific hemodynamic modeling in clinical applica- tions, micro-hemodynamic modeling in capillaries and blood cells, and the importance and potential of the multi-scale hemodynarnic modeling.
文摘AIM To investigate the incidence and the determinants of cardiovascular morbidity in Greek renal transplant recipients(RTRs) expressed as major advance cardiac event(MACE) rate. METHODS Two hundred and forty-two adult patients with a functioning graft for at least three months and availabledata that were followed up on the August 31, 2015 at two transplant centers of Western Greece were included in this study. Baseline recipients' data elements included demographics, clinical characteristics, history of comorbid conditions and laboratory parameters. Follow-up data regarding MACE occurrence were collected retrospectively from the patients' records and MACE risk score was calculated for each patient. RESULTS The mean age was 53 years(63.6% males) and 47 patients(19.4%) had a pre-existing cardiovascular disease(CVD) before transplantation. The mean estimated glomerular filtration rate was 52 ± 17 mL /min per 1.73 m2. During follow-up 36 patients(14.9%) suffered a MACE with a median time to MACE 5 years(interquartile range: 2.2-10 years). Recipients with a MACE compared to recipients without a MACE had a significantly higher mean age(59 years vs 52 years, P < 0.001) and a higher prevalence of pre-existing CVD(44.4% vs 15%, P < 0.001). The 7-year predicted mean risk for MACE was 14.6% ± 12.5% overall. In RTRs who experienced a MACE, the predicted risk was 22.3% ± 17.1% and was significantly higher than in RTRs without an event 13.3% ± 11.1%(P = 0.003). The discrimination ability of the model in the Greek database of RTRs was good with an area under the receiver operating characteristics curve of 0.68(95%CI: 0.58-0.78).CONCLUSION In this Greek cohort of RTRs, MACE occurred in 14.9% of the patients, pre-existing CVD was the main risk factor, while MACE risk model was proved a dependable utility in predicting CVD post RT.
文摘目的通过构建并验证中老年人群颈动脉斑块的预测模型及对应用价值探讨。方法回顾性收集2017—2019年于上海交通大学医学院附属仁济医院内分泌科门诊完成颈动脉超声检查患者的临床资料,性别不限,年龄≥45岁。共纳入1416例样本,训练集993例,验证集423例。按照7∶3的比例随机分为训练集和验证集,在训练集中比较颈动脉斑块组与非颈动脉斑块组各临床指标差异,并将特征指标变量采用多因素Logistic回归分析确定颈动脉斑块发生的独立危险素,依次构建中老年人群颈动脉斑块发生风险的可视化列线图模型。通过校准曲线和受试者操作特征曲线(receiver operator characteristic curve,ROC曲线)验证模型的区分度、一致性和准确性,最后采用决策曲线分析法确定模型的临床实用性,并通过外部验证进行评估。结果最终本研究纳入1416例患者,有483例(34.11%)有颈动脉斑块。多因素Logistic回归分析结果显示,年龄、收缩压、γ-谷氨酰转肽酶、糖化血红蛋白是颈动脉斑块发生的危险因素,而相较于男性,女性是颈动脉斑块发生的保护因素。依此构建可视化列线图模型,训练集ROC曲线下面积(area under the curve,AUC)为0.75(95%CI:0.72~0.78),验证集ROC曲线的AUC为0.71(95%CI:0.66~0.76)。训练集与验证集校准曲线Hosmer-Lemeshow拟合优度检验显示P值均>0.05(训练集P=0.7501,验证集P=0.9872)。决策曲线结果显示预测模型在训练集和验证集的阈值概率分别为5%~98%和1%~81%。结论基于指标(性别、年龄、收缩压、谷氨酰转肽酶、糖化血红蛋白),成功建立了中老年人群颈动脉斑块发生风险的预测模型,该模型预测效能较好,可用于社区或者农村等偏远地区居民普查,有助于颈动脉斑块的早期识别,进而改善预后。
文摘目的:在中国鄞州电子健康档案研究(Chinese electronic health records research in Yinzhou,CHERRY)的队列人群中,评价启动降压药物治疗的不同策略预防心血管病的健康收益与干预效率。方法:采用马尔科夫模型模拟评价的不同策略包括:策略1,对收缩压≥140 mmHg的人群启动降压药物治疗(根据2020年《中国心血管病一级预防指南》);策略2,对收缩压≥130 mmHg的人群启动降压药物治疗;策略3,对收缩压≥140 mmHg以及130~140 mmHg且心血管病高风险人群启动降压药物治疗(根据2017年美国心脏病学会/美国心脏协会《成年人高血压预防、检测、评估和管理指南》);策略4,对收缩压≥160 mmHg以及140~160 mmHg且心血管病高风险人群启动降压药物治疗(根据2019年英国国家卫生与临床优化研究所《成年人高血压诊断与管理指南》)。采用2019年世界卫生组织心血管病风险评估模型进行风险分层。马尔科夫模型的循环周期设为1年,模拟10个周期后计算质量调整生命年(quality-adjusted life year,QALY)、心血管病发病数、全因死亡数等结局事件数以评价策略的健康收益,并计算每预防一例心血管病事件或全因死亡的需治疗人数(number needed to treat,NNT)以评价策略的干预效率。马尔科夫模型的参数主要来源于CHERRY队列与公开发表的文献。采用单因素敏感性分析探讨心血管病发病率对结果的影响,采用概率敏感性分析探讨干预措施效应参数的不确定性对结果的影响。结果:共纳入213987名35~79岁基线无心血管病史的人群。相比于策略1,单纯下调降压起始值的策略2可预防的心血管病发病数增加666(95%UI:334~975)例,但每预防一例心血管病发病的NNT增加10(95%UI:7~20)人;而考虑定量风险评估的策略3可预防的心血管病发病数增加388(95%UI:194~569)例,且每预防一例心血管病发病的NNT减少6(95%UI:4~12)人,提示策略3可增加健康收益并具有更高的干预效率。策略4相比于策略1,可预防的心血管病发病数虽然减少193(95%UI:98~281)例,但每预防一例心血管病事件的NNT减少18(95%UI:13~37)人,效率更高。单因素敏感性分析及概率敏感性分析结果与主分析结果一致。结论:在中国发达地区的社区人群中选择降压药物治疗目标人群时,结合心血管病定量风险评估的策略优于单纯将起始值从140 mmHg降至130 mmHg的策略,前者可提升健康收益且兼顾干预效率;不同地区需因地制宜选择降压起始值并结合定量风险评估的策略,以权衡健康收益与干预效率。
文摘目的:系统评价心血管疾病病人衰弱发生风险预测模型。方法:系统检索中国知网、中国生物医学文献数据库、万方数据库、维普数据库、PubMed、Embase、the Cochrane Library、Web of Science数据库中关于心血管疾病病人衰弱发生风险预测模型的研究,同时对检索到的文献进行溯源,检索时限为建库至2024年2月29日。由2名研究员独立筛选文献、提取资料并评价纳入研究的偏倚风险。结果:共纳入8项研究,共8个心血管疾病病人衰弱发生风险预测模型,研究总样本量为346~1654例,发生衰弱事件数为98~560例。8个模型均未行外部验证,6个模型仅行内部验证,模型受试者工作特征曲线下面积为0.781~0.991。所纳入预测模型中常见的心血管疾病病人衰弱发生易感因素和速发因素分别为合并症、年龄、日常生活能力、失眠以及营养不良。结论:当前心血管疾病病人衰弱发生风险的预测模型在效能上表现优异,展现出较高的区分度及适用性。然而,模型质量仍有提升空间。在未来的研究中,研究者们需重点关注数据来源的可靠性、预测因素选择的精确性及其测量的标准性,同时妥善处理缺失数据,并全面评价模型性能。此外,对现有模型进行外部验证至关重要,以确保模型的可移植性和可泛化性,使其能够更有效地指导临床实践。
