Direct application of an ECG-based sleep staging algorithm on reflective photoplethysmography data decreases performance.

OBJECTIVE: The maturation of neural network-based techniques in combination with the availability of large sleep datasets has increased the interest in alternative methods of sleep monitoring. For unobtrusive sleep staging, the most promising algorithms are based on heart rate variability computed from inter-beat intervals (IBIs) derived from ECG-data. The practical application of these algorithms is even more promising when alternative ways of obtaining IBIs, such as wrist-worn photoplethysmography (PPG) can be used. However, studies validating sleep staging algorithms directly on PPG-based data are limited. RESULTS: We applied an automatic sleep staging algorithm trained and validated on ECG-data directly on inter-beat intervals derived from a wrist-worn PPG sensor, in 389 polysomnographic recordings of patients with a variety of sleep disorders. While the algorithm reached moderate agreement with gold standard polysomnography, the performance was significantly lower when applied on PPG- versus ECG-derived heart rate variability data (kappa 0.56 versus 0.60, p < 0.001; accuracy 73.0% versus 75.9% p < 0.001). These results show that direct application of an algorithm on a different source of data may negatively affect performance. Algorithms need to be validated using each data source and re-training should be considered whenever possible.

Novel use of repolarization parameters in electrocardiographic imaging to uncover arrhythmogenic substrate.

BACKGROUND: Measuring repolarization characteristics is challenging and has been reserved for experienced physicians. In electrocardiographic imaging (ECGI), activation-recovery interval (ARI) is used as a measure of local cardiac repolarization duration. We hypothesized that repolarization characteristics, such as local electrogram morphology and local and global dispersion of repolarization timing and duration could be of significance in ECGI. OBJECTIVE: To further explore their potential in arrhythmic risk stratification we investigated the use of novel repolarization parameters in ECGI. MATERIALS AND METHODS: We developed and compared methods for T-peak and T-end detection in reconstructed potentials. All methods were validated on annotated reconstructed electrograms (EGMs). Characteristics of the reconstructed EGMs and epicardial substrate maps in IVF patients were analyzed by using data recorded during sinus rhythm. The ECGI data were analyzed for EGM morphology, conduction, and repolarization. RESULTS: We acquired ECGI data from 8 subjects for this study. In all patients we evaluated four repolarization parameters: Repolarization time, T-wave area, Tpeak-Tend interval, and T-wave alternans. Most prominent findings were steep repolarization time gradients in regions with flat EGMs. These regions were also characterized by low T-wave area and large differences in Tpeak-Tend interval. CONCLUSIONS: Measuring novel repolarization parameters in reconstructed electrograms acquired with ECGI is feasible, can be done in a fully automated manner and may provide additional information on underlying arrhythmogenic substrate for risk stratification. Further studies are needed to investigate their potential use and clinical application.