Feasibility and validity of using deep learning to reconstruct 12-lead ECG from three­lead signals.

BACKGROUND: In the field of mobile health, portable dynamic electrocardiogram (ECG) monitoring devices often have a limited number of lead electrodes due to considerations, such as portability and battery life. This situation leads to a contradiction between the demand for standard 12­lead ECG information and the limited number of leads collected by portable devices. METHODS: This study introduces a composite ECG vector reconstruction network architecture based on convolutional neural network (CNN) combined with recurrent neural network by using leads I, II, and V2. This network is designed to reconstruct three­lead ECG signals into 12­lead ECG signals. A 1D CNN abstracts and extracts features from the spatial domain of the ECG signals, and a bidirectional long short-term memory network analyzes the temporal trends in the signals. Then, the ECG signals are inputted into the model in a multilead, single-channel manner. RESULTS: Under inter-patient conditions, the mean reconstructed Root mean squared error (RMSE) for precordial leads V1, V3, V4, V5, and V6 were 28.7, 17.3, 24.2, 36.5, and 25.5 µV, respectively. The mean overall RMSE and reconstructed Correlation coefficient (CC) were 26.44 µV and 0.9562, respectively. CONCLUSION: This paper presents a solution and innovative approach for recovering 12­lead ECG information when only three­lead information is available. After supplementing with comprehensive leads, we can analyze the cardiac health status more comprehensively across 12 dimensions.

Comparison and optimization of extraction protocol for intracellular phosphorus and its polyphosphate in enhanced biological phosphorus removal (EBPR) sludge.

Intracellular polyphosphate (poly-P) plays important roles in Enhanced biological phosphorus removal (EBPR) process, but an effective and reliable protocol for extracting intracellular P and its poly-P in EBPR sludge without hydrolysis of poly-P has not been setup yet. In the study, it was revealed that the severe hydrolysis of intracellular poly-P occurred during the different extraction processes, such as acid (i.e., HClO4, H2SO4 and HCl), basic (i.e., NaOH and KOH) and freezing-grind (under different solid-liquid ratios), but it did not occur during ultrasonic extraction process. The optimal extraction process of the ultrasonic protocol was 10 w/mL of ultrasonic power density and 15 min of ultrasonic time, when the extraction efficiency of intracellular P was 88.24 ±â€¯1.56%. In addition, the extraction efficiency of intracellular P could be furtherly improved by that the 0.75 mol/L LiCl solution was used to resuspend the bacterial cell before ultrasonic extraction (i.e., LiCl-ultrasonic protocol). The ultrasonic protocol was more suitable to extract the intracellular P and its poly-P of EBPR sludge than the other 4 protocols (i.e., PCA-NaOH, EDTA-NaOH, freezing-grind and LiCl-ultrasonic), which had the technical characteristics of (i) with relatively high extraction efficiency of intracellular P, (ii) without hydrolysis of intracellular poly-P, (iii) with weak noise signal in 31P NMR spectrum and (iv) with simple extraction process and short extraction time. It was founded by the ultrasonic protocol that there was the high content (82.88%-89.79% of intracellular P content) of intracellular poly-P with long average chain length (376.4-383.2) in the EBPR sludges. Importantly, it was confirmed that the EBPR process was related to the combined action of extracellular and intracellular poly-P using a new fractionation method of P in EBPR sludge, which included the ultrasonic protocol at high power density for extracting the intracellular P and its poly-P.