A principal component analysis based data fusion method for ECG-derived respiration from single-lead ECG

An ECG-derived respiration (EDR) algorithm based on principal component analysis (PCA) is presented and applied to derive the respiratory signals from single-lead ECG. The respiratory-induced variabilities of ECG features, P-peak amplitude, Q-peak amplitude, R-peak amplitude, S-peak amplitude, T-peak amplitude and RR-interval, are fused by PCA to yield a better surrogate respiratory signal than other methods. The method is evaluated on data from the MIT-BIH polysomnographic database and validated against a “gold standard” respiratory obtained from simultaneously recorded respiration data. The performance of fusion algorithm is assessed by comparing the EDR signals to a reference respiratory signal, using the quantitative evaluation indexes that include true positive (TP), false positive (FP), false negative (FN), sensitivity (SE) and positive predictivity (PP). The statistically difference is significant among the PCA data fusion method and the EDR methods based on the RR intervals and the RS amplitudes, showing that PCA data fusion algorithm outperforms the others in the extraction of respiratory signals from single-lead ECGs.