Obstructive sleep apnea classification based on spectrogram patterns in the electrocardiogram

Describes the findings of an exploratory study of the effect of obstructive sleep apnea (OSA) on the electrocardiogram (ECG) signal. Episodes of sleep apnea are characterized by periodic cycles of breathing cessation find restoration. The authors' analysis was guided by the hypothesis that these cycles synchronously alter the ECG. They discovered several characteristic indicators of apnea in the ECG signal. Their study focused on data sets provided for the Computers in Cardiology (CINC) 2000 apnea classification competition. After careful QRS detection, artifact removal, and preprocessing, the authors found that they could recognize sleep apnea by visually inspecting spectrograms of various features of the ECG such as the heart rate (HR), S-pulse amplitude, and pulse energy. As part of this study the authors entered both CINC competitions. They were able to correctly classify 28 out of 30 subjects in their initial competition entry and 30 out of 30 in their third entry. Once each signal was classified as a whole, the authors were able to correctly classify each minute in 13,626 out of 17,268 cases in their initial entry and 15,994 cases in their fourth entry.