METHODS: Continuous raw PPG waveforms were blindly allocated into segments with an equal length (5s) without leveraging any pulse location information and were normalized with Z-score normalization methods. A 1-D-CNN was designed to automatically learn the intrinsic features of the PPG waveform, and perform the required classification. Several training hyperparameters (initial learning rate and gradient threshold) were varied to investigate the effect of these parameters on the performance of the network. Subsequently, this proposed network was trained and validated with 30 subjects, and then tested with eight subjects, with our local dataset. Moreover, two independent datasets downloaded from the PhysioNet MIMIC II database were used to evaluate the robustness of the proposed network.
RESULTS: A 13 layer 1-D-CNN model was designed. Within our local study dataset evaluation, the proposed network achieved a testing accuracy of 94.9%. The classification accuracy of two independent datasets also achieved satisfactory accuracy of 93.8% and 86.7% respectively. Our model achieved a comparable performance with most reported works, with the potential to show good generalization as the proposed network was evaluated with multiple cohorts (overall accuracy of 94.5%).
CONCLUSION: This paper demonstrated the feasibility and effectiveness of applying blind signal processing and deep learning techniques to PPG motion artifact detection, whereby manual feature thresholding was avoided and yet a high generalization ability was achieved.
METHODS: GBS patients were consecutively recruited and the results were compared to age- and gender-matched healthy controls. A series of autonomic function tests including computation-dependent tests (power spectrum analysis of HRV and BRS at rest) and challenge maneuvers (deep breathing, eyeball compression, active standing, the Valsalva maneuver, sustained handgrip, and the cold pressor test) were performed.
RESULTS: Ten GBS patients (six men; mean age = 40.1 ± 13.9 years) and ten gender- and age-matched healthy controls were recruited. The mean GBS functional grading scale at disease plateau was 3.4 ± 1.0. No patients required intensive care unit admission or mechanical ventilation. Low-frequency HRV (p = 0.027), high-frequency HRV (p = 0.008), and the total power spectral density of HRV (p = 0.015) were significantly reduced in patients compared to controls. The mean up slope (p = 0.034), down slope (p = 0.011), and total slope (p = 0.024) BRS were significantly lower in GBS patients. The diastolic rise in blood pressure in the cold pressor test was significantly lower in GBS patients compared to controls (p = 0.008).
INTERPRETATION: Computation-dependent tests (HRV and BRS) were more useful for detecting autonomic dysfunction in GBS patients, whereas the cold pressor test was the only reliable challenge test, making it useful as a bedside measure of autonomic function in GBS patients.