Song Jinzhong, Yan Hong, Liu Guizhi, Kuang Hong
State Key Laboratory of Space Medicine Fundamentals and Application, China Astronaut Research and Training Center, Beijing 100094, China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2012 Feb;29(1):147-51, 156.
Electrocardiogram (ECG) is a convenient, economic, and non-invasive detecting tool in myocardial ischemia (MI). Its clinical appearance is mainly exhibited by ST-T complex change. MI events are usually instantaneous and asymptomatic in some cases, which cannot be forecasted to have a precautionary measure in time by doctors. The automatic detection of MI by computer and a cued warning of danger in real time play an important role in diagnosing heart disease. With the help of the medical staff, some quantitative approbatory indicators, such as ST-segment deviation, the amplitude of T-wave peak and the rate of ST and heart rate (HR), were combined to judge MI using fuzzy reasoning. After MIT-BIH database and the long-term ST database (LTST) verification, sensitivity and positive predictive values reached 75% and 78% respectively, and specificity and negative predictive values were 85% and 87% respectively. In addition, the proposed method was close to human way of thinking and understanding, and easy to apply in clinical detection and engineering fields.
心电图（ECG）是一种用于检测心肌缺血（MI）的便捷、经济且无创的工具。其临床表现主要通过ST-T复合波变化来体现。心肌梗死事件在某些情况下通常是瞬间发生且无症状的，医生无法及时预测并采取预防措施。利用计算机自动检测心肌梗死并实时发出危险提示，在心脏病诊断中起着重要作用。在医护人员的帮助下，结合了一些定量认可指标，如ST段偏差、T波峰值幅度以及ST与心率（HR）的比率，采用模糊推理来判断心肌梗死。经过麻省理工学院 - 贝斯以色列女执事医疗中心（MIT - BIH）数据库和长期ST数据库（LTST）验证，敏感性和阳性预测值分别达到75%和78%，特异性和阴性预测值分别为85%和87%。此外，所提出的方法接近人类的思维和理解方式，易于应用于临床检测和工程领域。
