Mechanical ventilation is an essential life-support treatment for patients who cannot breathe independently. Patient–ventilator asynchrony (PVA) occurs when ventilatory support does not match the needs of the patient and is associated with a series of adverse clinical outcomes. Deep learning methods have shown a strong discriminative ability for PVA detection, but they require a large number of annotated data for model training, which hampers their application to this task. We developed a transfer learning architecture based on pretrained convolutional neural networks (CNN) and used it for PVA recognition based on small datasets. The one-dimensional signal was converted to a two-dimensional image, and features were extracted by the CNN using pretrained weights for classification. A partial dropping cross-validation technique was developed to evaluate model performance on small datasets. When using large datasets, the performance of the proposed method was similar to that of non-transfer learning methods. However, when the amount of data was reduced to 1%, the accuracy of transfer learning was approximately 90%, whereas the accuracy of the non-transfer learning was less than 80%. The findings suggest that the proposed transfer learning method can obtain satisfactory accuracies for PVA detection when using small datasets. Such a method can promote the application of deep learning to detect more types of PVA under various ventilation modes.
16 November 2022 in IEEE Transactions on Cognitive Communications and Networking
WiFi-based person identification has been made possible by the widespread deployment of WiFi devices. However, most existing methods rely on the person’s gait characters, which need several minutes of walking to extract the wireless signature of an individual for training and testing, and thus limit the speed and size of the identification of people. In this work, to address the aforementioned challenges, we propose a novel WiFi-based Device-Free Fast Identification (WiDFF-ID) approach. In particular, we first use RF-based biometrics to derive the personal Channel State Information (CSI) fingerprint. Using such posture information instead of original gait action could effectively enable quick identification for more people. Then a set of methods including data augmentation are employed to process the fused RF-biometric signals to greatly reduce training time and storage resources. In the following, a novel multi-layer deep convolutional neural network is proposed for reusing prior calculated features and uniquely identifying individuals. Finally, we implement WiDFF-ID on commodity off-the-shelf WiFi devices. Experimental results show that the proposed scheme can reach 98% of average identification accuracy with a total of 42 volunteers, implying that the proposed WiDFF-ID can be used in scenarios involving a larger group of people for access authentication.
31 March 2020 in Computational and Mathematical Methods in Medicine
Objective. The deceleration capacity (DC) and acceleration capacity (AC) of heart rate, which are recently proposed variants to the heart rate variability, are calculated from unevenly sampled RR interval signals using phase-rectified signal averaging. Although uneven sampling of these signals compromises heart rate variability analyses, its effect on DC and AC analyses remains to be addressed. Approach. We assess preprocessing (i.e., interpolation and resampling) of RR interval signals on the diagnostic effect of DC and AC from simulation and clinical data. The simulation analysis synthesizes unevenly sampled RR interval signals with known frequency components to evaluate the preprocessing performance for frequency extraction. The clinical analysis compares the conventional DC and AC calculation with the calculation using preprocessed RR interval signals on 24-hour data acquired from normal subjects and chronic heart failure patients. Main Results. The assessment of frequency components in the RR intervals using wavelet analysis becomes more robust with preprocessing. Moreover, preprocessing improves the diagnostic ability based on DC and AC for chronic heart failure patients, with area under the receiver operating characteristic curve increasing from 0.920 to 0.942 for DC and from 0.818 to 0.923 for AC. Significance. Both the simulation and clinical analyses demonstrate that interpolation and resampling of unevenly sampled RR interval signals improve the performance of DC and AC, enabling the discrimination of CHF patients from healthy controls.
Background and objectives: Patient–ventilator asynchronies (PVAs) are common in mechanically ventilated patients. However, the epidemiology of PVAs and its impact on clinical outcome remains controversial. The current study aims to evaluate the epidemiology and risk factors of PVAs and their impact on clinical outcomes using big data analytics.Methods: The study was conducted in a tertiary care hospital; all patients with mechanical ventilation from June to December 2019 were included for analysis. Negative binomial regression and distributed lag non-linear models (DLNM) were used to explore risk factors for PVAs. PVAs were included as a time-varying covariate into Cox regression models to investigate its influence on the hazard of mortality and ventilator-associated events (VAEs).Results: A total of 146 patients involving 50,124 h and 51,451,138 respiratory cycles were analyzed. The overall mortality rate was 15.6%. Double triggering was less likely to occur during day hours (RR: 0.88; 95% CI: 0.85–0.90; p < 0.001) and occurred most frequently in pressure control ventilation (PCV) mode (median: 3; IQR: 1–9 per hour). Ineffective effort was more likely to occur during day time (RR: 1.09; 95% CI: 1.05–1.13; p < 0.001), and occurred most frequently in PSV mode (median: 8; IQR: 2–29 per hour). The effect of sedatives and analgesics showed temporal patterns in DLNM. PVAs were not associated mortality and VAE in Cox regression models with time-varying covariates.Conclusions: Our study showed that counts of PVAs were significantly influenced by time of the day, ventilation mode, ventilation settings (e.g., tidal volume and plateau pressure), and sedatives and analgesics. However, PVAs were not associated with the hazard of VAE or mortality after adjusting for protective ventilation strategies such as tidal volume, plateau pressure, and positive end expiratory pressure (PEEP).