Heartbeat-aware convolutional neural network for R-peak detection of wearable device ECG data / 南方医科大学学报

OBJECTIVE@#To develop a method for R-peak detection of ECG data from wearable devices to allow accurate estimation of the physiological parameters including heart rate and heart rate variability.@*METHODS@#A fully convolutional neural network was applied to predict the R-peak heatmap of ECG data and locate the R-peak positions. The heartbeat-aware (HA) module was introduced to enable the model to learn to predict the heartbeat number and R-peak heatmap simultaneously, thereby improving the capability of the model for extraction of the global context. The R-R interval estimated by the predicted heartbeat number was adopted to calculate the minimum horizontal distance for peak positioning. To achieve real-time R-peak detection on mobile devices, the deep separable convolution was adopted to reduce the number of parameters and the computational complexity of the model.@*RESULTS@#The proposed model was trained only with ECG data from wearable devices. At a tolerance window interval of 150 ms, the proposed method achieved R peak detection sensitivities of 100% for both wearable device ECG dataset and a public dataset (i.e. LUDB), and the true positivity rates exceeded 99.9%. As for the ECG signal of a 10 s duration, the CPU time of the proposed method for R-peak detection was about 23.2 ms.@*CONCLUSION@#The proposed method has good performance for R-peak detection of both wearable device ECG data and routine ECG data and also allows real-time R-peak detection of the ECG data.

Associations Between Knowledge on Optimal Control of Serum Phosphate, Perceived Social Support, Dietary Phosphorus Intake and Phosphate Compliance Among Hemodialysis Patients

@#Introduction: Hyperphosphatemia is common among hemodialysis patients, often accompanies with unfavourable clinical outcomes. Several factors affect phosphate compliance among hemodialysis patients, with lack of such information at the local context. Thus, this cross-sectional study aimed to determine the associations of sociodemographic factors, knowledge on optimal control of serum phosphate, perceived social support from family, dietary phosphorus intake and phosphate compliance among hemodialysis patients. Methods: Structured questionnaire was used to obtain information on socioeconomic factors, knowledge, family social support and dietary phosphorus intakes of hemodialysis patients, with serum phosphate level was used as the surrogate marker for phosphate compliance. Results: A total of 76 patients (Mean age of 52 years old) were recruited. Hyperphosphatemia was prevalent with approximately 60% of the patients failed to achieve the target. Approximately 90% of the patients perceived low level of family social support. Young patients had significant higher serum phosphate compared to their older counterparts (r = -0.297, p =0.009). Serum phosphate was positively correlated with dietary intake of phosphorus, dialysis vintage (r = 0.301, p = 0.006) and comorbidity score (r = 0.325, p = 0.008) while negatively correlated with dialysis dose (r = -0.582, p = 0.002) and family social support (r = -0.263, p = 0.024). Conclusion: The promising role of dietary phosphorus intake in managing hyperphosphatemia deserves further attention. Innovative approaches are needed to promote self-adherence on serum phosphate especially the younger patients. It is imperative to promote family social support in the management of hyperphosphatemia among hemodialysis patients.