ECG-Based Detection of Early Myocardial Ischemia in a Computational Model: Impact of Additional Electrodes, Optimal Placement, and a New Feature for ST Deviation

Table 1

Clinical studies concerning the detection of acute myocardial ischemia. Ranges for [4] represent validation against troponin/creatine kinase MB.

Sensitivity	Specificity	Detection method
12-lead ECG
45%	92%	Physician, ST elevation [1]
45%	92%	Physician, modified AHA/ESC guidelines [41], in [5]
45%	94%	Physician, ST elevation [2]
65.9%	86.3%	Artificial neural network, six ST-T features [3]
60.7–72.7%	96.4–97.1%	Physician, ST elevation [4]
80-channel BSPM
64%	94%	Rule-based, QRST features [2]
76%	92%	Physician, computed QRST features [5]
80%	92%	Physician, computed ST features [6]
92.9–100%	94.9–96.5%	Physician, computed QRST features [4]