Multi-lead QRS detection using window pairs

We designed a novel approach for multi-lead QRS detection. The algorithm uses one equation with two different window widths to generate a feature signal and a detection threshold. This enables it to adapt to various changes in QRS morphology and noise levels, resulting in a detection error rate of just 0.29% on the MIT-BIH Arrhythmia Database. The algorithm is also computationally efficient and capable of resolving differences between multiple leads by automatically attaching a confidence value to each QRS detection.