论文发表
2026
AG-STDF: Anatomy-Guided ECG Spatiotemporal Dynamical Fusion for Screening Coronary Microvascular Dysfunction
IEEE Transactions on Biomedical Engineering · 2026
IF 4.4
CAS Zone 2
顶刊
冠脉慢血流(CSF)无创检测AUROC=0.9467,可定量预测冠脉血流速度(CTFC R²=0.5951)。发表于生物医学工程旗舰期刊。
CDG-MACE评分模型:面向急诊胸痛但心电图正常患者的风险分层
Physiological Measurement · 2026
IF 2.5
CAS Zone 4
将CDG技术转化为临床可用风险分层评分系统,推动CDG从辅助诊断工具向临床风险量化评分工具转化。
DOI: 待发表
2025
A multi-lead group network for myocardial infarction detection and localization based on clinical knowledge-driven and dynamic-static feature fusion
Expert Systems with Applications · 2025
IF 9.4
JCR Q1
CAS Zone 1
知识驱动多导联网络(FEC-KML),融合12导联解剖分区与CDG动力学,PTB-XL上MI检测>94%、定位>87%。
2024
Multiscale Joint Recurrence Quantification Analysis Integrating ECG Spatiotemporal and Dynamic Information for Cardiopathy Detection
IEEE Transactions on Instrumentation and Measurement · 2024
IF 7.0
JCR Q1
CAS Zone 2
多尺度联合递归量化分析(MSJRQA)融合时空与动态特征,MI检测准确率94.50%,区分MI与非MI但伴ST-T异常患者90.78%。
Concurrent Analysis of Dynamic and Static Features for Classifying Cardiac Rhythms
IEEE Transactions on Instrumentation and Measurement · 2024
IF 7.0
JCR Q1
CAS Zone 2
动静特征融合的心律失常分类,DS证据理论融合CDG动态特征与QT间期静态特征,4类心律91.71%、7类88.93%。
Multi-phase ECG dynamic features for detecting myocardial ischemia and identifying its etiology using deterministic learning
Biomedical Signal Processing and Control · 2024
IF 5.7
JCR Q2
CAS Zone 2
首次实现基于心电图的心肌缺血病因鉴别——区分冠脉狭窄(COAS)和冠脉慢血流(CSF)。缺血检测AUROC=0.9126,病因鉴别AUROC=0.9238。
An interpretable ensemble trees method with joint analysis of static and dynamic features for myocardial infarction detection
Physiological Measurement · 2024
IF 2.5
CAS Zone 4
StackTree可解释集成树,简化随机森林,保持97.1%准确率(PTB)的同时生成可理解的决策规则。
An interpretable shapelets-based method for myocardial infarction detection using dynamic learning and deep learning
Physiological Measurement · 2024
IF 2.5
CAS Zone 4
将深度学习shapelets引入CDG动力学信号进行局部模式提取,准确率94.11%。
Early and Accurate Detection of Radiation-induced Heart Damage by Cardiodynamicsgram
Journal of Cardiovascular Translational Research · 2024
IF 2.6
JCR Q2
将CDG跨域拓展到肿瘤治疗相关心脏损伤(RIHD)检测。动物模型中CDG变化早于组织病理学改变,为临床转化提供实验依据。
2023
ECG-based cardiodynamicsgram can reflect anomalous functional information in coronary artery disease
Clinical Cardiology · 2023
IF 2.8
JCR Q2
利用CCTA和CT-FFR验证CDG诊断价值,456例患者,准确率79.56%,AUC=0.836;CDG与CT-FFR显著相关(r=-0.395)。
2022
Early detection of myocardial ischemia in 12-lead ECG using deterministic learning and ensemble learning
Computer Methods and Programs in Biomedicine · 2022
IF 6.4
JCR Q1
CAS Zone 2
CDG+集成学习三中心499例非诊断性心电图患者,Bagging异构集成,准确率89.10%,PTB泛化91.11%。
A dynamic learning-based ECG feature extraction method for myocardial infarction detection
Physiological Measurement · 2022
IF 2.5
CAS Zone 4
多尺度分解和混合特征选择的CDG动态特征提取,PTB数据集MI检测94.75%,齐鲁医院200例独立验证84.96%。
动态学习赋能心电图评估急性冠脉综合征患者经皮冠脉介入术疗效的研究
中华急诊医学杂志 · 2022
CSCD核心
203例ACS患者,CDG在PCI术后由散乱变规整,90.28%术后无残余狭窄患者CDG指标显著降低(P<0.001)。
2020
基于确定学习及心电动力学图的心肌缺血早期检测研究
自动化学报 · 2020
EI / CSCD / 北大核心
CDG大规模临床验证,781例冠脉造影患者,灵敏度90.1%、特异度85.2%、AUC 0.93;发现假阳性患者多存在冠脉慢血流(临床漏诊的真实心肌缺血)。
