Driver fatigue poses a significant safety risk in road transport, prompting heightened public awareness. Electroencephalography (EEG), a key physiological signal for fatigue characterization, has garnered substantial interest and served as de facto gold standard. Existing EEG-based fatigue detection methods often utilize limited forehead lobe channels or the entire brain’s EEG signals, potentially leading to information loss or redundancy. This oversight neglects the crucial aspect of optimizing channels. Moreover, many studies prioritize augmenting model performance through additional sub-networks, neglecting refined features, deepening network and creating overfitting. To address these gaps, this paper introduces an attention-guided multi-scale convolutional neural network for driving fatigue detection, comprising a multi-scale convolutional neural network (MSCNN) and a channel attention mechanism (CAM) module. The MSCNN optimizes network depth, capturing richer temporal and frequency features. The CAM module supplements the MSCNN by emphasizing valuable information, exploring channel contributions, and assessing the impact of feature refinement on model performance. The proposed method demonstrates promising results on the public SEED-VIG dataset with an average root mean square error (RMSE) of 0.051 and an average correlation coefficient (COR) of 0.966 across 23 subjects, outperforming alternative approaches in driving fatigue detection. These findings show that our proposed method perform more effectively for driving fatigue detection based on EEG.

Pulse wave analysis, a non-invasive and cuffless approach, holds promise for blood pressure (BP) measurement in precision medicine. In recent years, pulse wave learning for BP estimation has undergone extensive scrutiny. However, prevailing methods still encounter challenges in grasping comprehensive features from pulse waves and generalizing these insights for precise BP estimation. In this study, we propose a general pulse wave deep learning (PWDL) approach for BP estimation, introducing the OVAR-BPnet model to powerfully capture intricate pulse wave features and showcasing its effectiveness on multiple types of pulse waves. The approach involves constructing population pulse waves and employing a model comprising an omni-scale convolution subnet, a Vision Transformer subnet, and a multilayer perceptron subnet. This design enables the learning of both single-period and multi-period waveform features from multiple subjects. Additionally, the approach employs a data augmentation strategy to enhance the morphological features of pulse waves and devise a label sequence regularization strategy to strengthen the intrinsic relationship of the subnets' output. Notably, this is the first study to validate the performance of the deep learning approach of BP estimation on three types of pulse waves: photoplethysmography, forehead imaging photoplethysmography, and radial artery pulse pressure waveform. Experiments show that the OVAR-BPnet model has achieved advanced levels in both evaluation indicators and international evaluation criteria, demonstrating its excellent competitiveness and generalizability. The PWDL approach has the potential for widespread application in convenient and continuous BP monitoring systems.

The Internet has successfully been used for patient-oriented survey research. Internet-based translational research may also be possible. Our aim was to study the feasibility of collecting biospecimens from CCFA Partners, an Internet-based inflammatory bowel disease (IBD) cohort. From August 20, 2013, to January 4, 2014, we randomly sampled 412 participants, plus 179 from a prior validation study, and invited them to contribute a biospecimen. Participants were randomized to type (blood, saliva), incentive (none, US $20, or US $50), and collection method for blood. The first 82 contributors were also invited to contribute stool. We used descriptive statistics and t tests for comparisons. Of the 591 participants, 239 (40.4%) indicated interest and 171 (28.9%) contributed a biospecimen. Validation study participants were more likely to contribute than randomly selected participants (44% versus 23%, P<.001). The return rate for saliva was higher than blood collected by mobile phlebotomist and at doctors' offices (38%, 31%, and 17% respectively, P<.001). For saliva, incentives were associated with higher return rates (43-44% versus 26%, P=.04); 61% contributed stool. Fourteen IBD-associated single nucleotide polymorphisms were genotyped, and risk allele frequencies were comparable to other large IBD populations. Bacterial DNA was successfully extracted from stool samples and was of sufficient quality to permit quantitative polymerase chain reaction for total bacteria. Participants are willing to contribute and it is feasible to collect biospecimens from an Internet-based IBD cohort. Home saliva kits yielded the highest return rate, though mobile phlebotomy was also effective. All samples were sufficient for genetic testing. These data support the feasibility of developing a centralized collection of biospecimens from this cohort to facilitate IBD translational studies.

This study aimed to evaluate the relative validity and reproducibility of a semiquantitative food frequency questionnaire (SFFQ) in adult populations in China. Among the 49 recruited healthy participants (age range: 20–60 years), the relative validity of a 79-item SFFQ was assessed in two ways: (1) by comparing its dietary intake estimates with those from the average measurements of three inconsecutive 24 h dietary records (24-HDRs); and (2) by comparing its estimates of dietary fatty acids with the measured plasma levels of fatty acids. The reproducibility of the SFFQ was evaluated by a comparison of two SFFQ measurements from the same participants collected one year apart. In the relative validity study, the average Spearman correlation coefficient (r) was 0.27 among 18 prespecified food group intakes estimated from the SFFQ and the 24-HDRs; nevertheless, that of five food group intakes (e.g., red meat and seafood) was higher (all r_s > 0.40, p < 0.05). In addition, a moderate correlation between the SFFQ estimate of polyunsaturated fatty acid intakes (energy-adjusted percentage of total fatty acids) and its plasma level was observed (r = 0.42, p < 0.05). Regarding the one-year reproducibility of the SFFQ-assessed intakes, the average rank intraclass correlation coefficient (ICC) was 0.35 for the 18 food group estimates. In particular, moderately reproducible estimates of seven food group intakes (e.g., refined grains and red meat, all ICCs ≥ 0.40, p < 0.05) were observed. In conclusion, the SFFQ provides valid and reproducible estimates of dietary intakes for various food groups in general and performs well as a potential tool for estimating habitual dietary intakes of some unsaturated fatty acids.