ObjectiveElectrocardiogram (ECG) is essential for evaluating the autonomic nervous system. Ensuring the quality of real-world ECG datasets is critical, but manual control of large datasets is impractical. Thus, automated quality control is necessary. This paper introduces a new quality index, the peak-distance quality index (PDQI), based on the modulation spectrum approach. MethodsReal-life data from 1000 ECG recordings, each 600 s long, were collected at the stroke unit of the University Hospital Tulln. Each ECG was visually evaluated, including the duration of the signal, artefacts and noise, and the number of extrasystoles. The power-modulation spectrum, the percentage of ECG in each signal, and modulation spectrum-based quality index (MS-QI) and PDQI were calculated. The area under the curve (AUC) for the detection of high-quality ECGs was calculated for both quality indices, as well as the optimal threshold for each index. ResultsThe percentage of ECG signals in the recordings based on the modulation spectrum correlates with expert rating (r = 0.99, p < 0.001). The AUC for PDQI for the detection of extrasystoles is 0.96, and the AUC for MSQI for the detection of artefacts is 0.83. The optimal thresholds for PDQI and MSQI are 0.44 and 0.17, respectively ConclusionThe power modulation spectrum can be applied to large amounts of data to detect ECG signals within biosignals and calculate quality indices. MSQI can be used for artefact detection and PDQI for extrasystole detection in ECG signals. A combined approach using both quality indices can provide a picture of the underlying data quality.
Read full abstract