Beatwise ECG Classification for the Detection of Atrial Fibrillation with Deep Learning.

Atrial fibrillation (AF) is the most common, sustained cardiac arrhythmia. Early intervention and treatment could have a much higher chance of reversing AF. An electrocardiogram (ECG) is widely used to check the heart's rhythm and electrical activity in clinics. The current manual processing of ECGs and clinical classification of AF types (paroxysmal, persistent and permanent AF) is ill-founded and does not truly reflect the seriousness of the disease. In this paper, we proposed a new machine learning method for beat-wise classification of ECGs to estimate AF burden, which was defined by the percentage of AF beats found in the total recording time. Both morphological and temporal features for categorizing AF were extracted via two combined classifiers: a 1D U-Net that evaluates fiducial points and segmentation to locate each heartbeat; and the other Recurrent Neural Network (RNN) to enhance the temporal classification of an individual heartbeat. The output of the classifiers had four target classes: Normal Sinus Rhythm (SN), AF, Noises (NO), and Others (OT). The approach was trained and validated on the Icentia11k dataset, with 1001 and 250 patients' ECGs, respectively. The testing accuracy for the four classes was found to be 0.86, 0.81, 0.79, and 0.75, respectively. Our study demonstrated the feasibility and superior performance of combing U-net and RNN to conduct a beat-wise classification of ECGs for AF burden. However, further investigation is warranted to validate this deep learning approach.Clinical relevance- This paper proposes a novel machine learning network for ECG beatwise classification, specifically for aiding AF burden determination.

Perceptions of workplace heat exposure and adaption behaviors among Chinese construction workers in the context of climate change.

BACKGROUND: Workplace heat exposure can cause a series of heat-related illnesses and injuries. Protecting workers especially those undertake work outdoors from the risk of heat strain is a great challenge for many workplaces in China under the context of climate change. The aim of this study is to investigate the perceptions and adaptation behaviors of heat exposure among construction workers and to provide evidence for the development of targeted heat adaptation strategies nationally and internationally. METHODS: In 2020, we conducted a cross-sectional online questionnaire survey via WeChat Survey Star in China, using a purposive snowball sampling approach. A total of 326 construction workers submitted completed questionnaires. The perceptions of workplace heat exposure were measured using seven indicators: concerns over high temperature, perception of high temperature injury, attitudes towards both heat-related training and regulations, adjustment of working habits during heat, heat prevention measures in the workplace, and reduction of work efficiency. Bivariate and multivariate regression analyses were used to identify the factors significantly associated with workers' heat perceptions and behavioral responses. RESULTS: 33.3% of the respondents were moderately or very concerned about heat exposure in the workplace. Less than half of the workers (43.8%) were worried about heat-related injuries. Workers who have either experienced work-related injuries (OR = 1.30, 95% CI 1.03-1.62) or witnessed injuries to others during high temperatures (OR = 1.12, 95% CI 1.02-1.27) were more concerned about heat exposure compared to other workers. Most respondents (63.5%) stated that their work efficiency declined during extremely hot weather. The factors significantly associated with a reduction of work efficiency included undertaking physically demanding jobs (OR = 1.28, 95% CI 1.07-1.54) and witnessing other workers' injuries during high temperatures (OR = 1.26, 95% CI 1.11-1.43). More than half of the workers were willing to adjust their work habits to adapt to the impact of high temperatures (81.6%). The internet was the most common method to obtain heat prevention information (44.7%), and the most frequently used heat prevention measure was the provision of cool drinking water (64.8%). CONCLUSIONS: Chinese construction workers lack heat risk awareness and are not well prepared for the likely increasing heat exposure in the workplace due to global warming. Therefore, there is a need to improve their awareness of heat-related injuries, strengthen high temperature related education and training, and update the current heat prevention policies to ensure compliance and implementation.

Additive Manufacturing of Wood Flour/PHA Composites Using Micro-Screw Extrusion: Effect of Device and Process Parameters on Performance.

Based on additive manufacturing of wood flour and polyhydroxyalkanoates composites using micro-screw extrusion, device and process parameters were evaluated to achieve a reliable printing. The results show that the anisotropy of samples printed by micro-screw extrusion is less obvious than that of filament extrusion fused deposition modeling. The type of micro-screw, printing speed, layer thickness, and nozzle diameter have significant effects on the performance of printed samples. The linear relationship between the influencing parameters and the screw speed is established, therefore, the performance of printed products can be controlled by the extrusion flow rate related to screw speed.

Motion Tracking of the Carotid Artery Wall From Ultrasound Image Sequences: a Nonlinear State-Space Approach.

The motion of the common carotid artery (CCA) wall has been established to be useful in early diagnosis of atherosclerotic disease. However, tracking the CCA wall motion from ultrasound images remains a challenging task. In this paper, a nonlinear state-space approach has been developed to track CCA wall motion from ultrasound sequences. In this approach, a nonlinear state-space equation with a time-variant control signal was constructed from a mathematical model of the dynamics of the CCA wall. Then, the unscented Kalman filter (UKF) was adopted to solve the nonlinear state transfer function in order to evolve the state of the target tissue, which involves estimation of the motion trajectory of the CCA wall from noisy ultrasound images. The performance of this approach has been validated on 30 simulated ultrasound sequences and a real ultrasound dataset of 103 subjects by comparing the motion tracking results obtained in this study to those of three state-of-the-art methods and of the manual tracing method performed by two experienced ultrasound physicians. The experimental results demonstrated that the proposed approach is highly correlated with (intra-class correlation coefficient ≥ 0.9948 for the longitudinal motion and ≥ 0.9966 for the radial motion) and well agrees (the 95% confidence interval width is 0.8871 mm for the longitudinal motion and 0.4159 mm for the radial motion) with the manual tracing method on real data and also exhibits high accuracy on simulated data (0.1161 ~ 0.1260 mm). These results appear to demonstrate the effectiveness of the proposed approach for motion tracking of the CCA wall.