Objective: This study investigates the association between phenotypic age acceleration (PAA) and all-cause and cause-specific mortality in obese individuals.Methods: Data were drawn from the National Health and Nutrition Examination Survey (NHANES) between 1999 and 2018, including 9,925 obese adults (BMI ≥ 30 kg/m²). PAA, defined as phenotypic age exceeding chronological age, was assessed using clinical biomarkers. Kaplan-Meier survival analysis and Cox proportional hazards models were used to assess the relationship between PAA and all-cause, cardiovascular, and cancer mortality, adjusting for covariates such as age, gender, race, lifestyle, and health status. Subgroup and sensitivity analyses were performed to ensure the robustness of the findings.Results: During a median follow-up of 10.6 years, 1,537 deaths were recorded, including 419 from cardiovascular disease and 357 from cancer. PAA was significantly associated with all-cause mortality (HR = 1.84, 95% CI: 1.64–2.06), cardiovascular mortality (HR = 1.86, 95% CI: 1.50–2.31), and cancer mortality (HR = 1.47, 95% CI: 1.17–1.85). These associations remained significant after adjusting for multiple variables, and sensitivity analyses confirmed the robustness of the results.Conclusion: PAA is an independent predictor of all-cause, cardiovascular, and cancer mortality in obese individuals. This study highlights the importance of PAA in mortality risk assessment and health management in the obese population.

Objectives: Functional connectivity triggered by naturalistic stimuli (e.g., movie clips), coupled with machine learning techniques provide great insight in exploring brain functions such as fluid intelligence. However, functional connectivity is multi-layered while traditional machine learning is based on individual model, which is not only limited in performance, but also fails to extract multi-dimensional and multi-layered information from the brain network. Methods: In this study, inspired by multi-layer brain network structure, we propose a new method, namely weighted ensemble model and network analysis, which combines machine learning and graph theory for improved fluid intelligence prediction. Firstly, functional connectivity analysis and graphical theory were jointly employed. The functional connectivity and graphical indices computed using the preprocessed fMRI data were then all fed into an auto-encoder parallelly for automatic feature extraction to predict the fluid intelligence. In order to improve the performance, tree regression and ridge regression models were stacked and fused automatically with weighted values. Finally, layers of auto-encoder were visualized to better illustrate the connectome patterns, followed by the evaluation of the performance to justify the mechanism of brain functions. Results: Our proposed method achieved the best performance with a 3.85 mean absolute deviation, 0.66 correlation coefficient and 0.42 R-squared coefficient; this model outperformed other state-of-the-art methods. It is also worth noting that the optimization of the biological pattern extraction was automated though the auto-encoder algorithm. Conclusion: The proposed method outperforms the state-of-the-art reports, also is able to effectively capture the biological patterns of functional connectivity during a naturalistic movie state for potential clinical explorations.

Healthcare workers frequently encounter demanding schedules, shift work, and significant psychological stressors, all of which can contribute to gastrointestinal disturbances and sleep irregularities. Although research has established that stress and shift work are independent risk factors for gastrointestinal discomfort and insomnia, the direct link between these two conditions in healthcare workers remains insufficiently explored. In this cross-sectional study, we recruited 372 healthcare workers from 6 public hospitals in Quanzhou via an online survey. Gastrointestinal and insomnia symptoms were measured using the Gastrointestinal Symptom Rating Scale (GSRS) and the Insomnia Severity Index (ISI), respectively, and analyzed via univariate and multivariate logistic regression models. Overall, 40.6% of participants reported insomnia symptoms. The GSRS total score was positively associated with insomnia both before (OR 1.18, 95% CI 1.12–1.25) and after adjustment for confounders including age, gender, anxiety, depression, somatization, and weekly night shift count (adjusted OR 1.07, 95% CI 1.00–1.15). These findings underscore a significant relationship between gastrointestinal symptoms and insomnia among healthcare workers, highlighting the need for targeted interventions to improve both GI health and sleep quality, thereby enhancing work efficiency and the overall quality of patient care.

Manual heart disease diagnosis with the electrocardiogram (ECG) is intractable due to the intertwined signal features and lengthy diagnosis procedure, especially for the 24-hour dynamic ECG signals. Consequently, even experienced cardiologists may face difficulty in producing all accurate ECG reports. In recent years, neural network-based automatic ECG diagnosis methods have exhibited promising performance, suggesting a potential alternative to the labor-intensive examination conducted by cardiologists. However, many existing approaches failed to adequately consider the temporal and channel dimensions when assembling features and ignored interpretability. And clinical theory underscores the necessity of prolonged signal observations for diagnosing certain ECG conditions such as tachycardia. Moreover, specific heart diseases manifest primarily through distinct ECG leads represented as channels. In response to these challenges, this paper introduces a novel neural network architecture for ECG classification (diagnosis). The proposed model incorporates Lead Fusing blocks, transformer-XL encoder-based Encoder modules, and hierarchical temporal attentions. Importantly, this classifier operates directly on raw ECG time-series signals rather than cardiac cycles. Signal integration begins with the Lead Fusing blocks, followed by the Encoder modules and hierarchical temporal attentions, enabling the extraction of long-dependent features. Furthermore, we argue that existing convolution-based methods compromise interpretability, while our proposed neural network offers improved clarity in this regard. Experimental evaluation on a comprehensive public dataset confirms the superiority of our classifier over state-of-the-art methods. Moreover, visualizations reveal the enhanced interpretability provided by our approach. Highlights Our model extracts long-dependent features of ECG signals based on the Transformer-XL encoder. The proposed network offers the improved interpretability. Our classifier achieves superior performance over other state-of-the-art methods.

Adolescent major depressive disorder (MDD) exhibits complex and heterogeneous alterations of brain functional organization. To understand the neurobiological basis of adolescent MDD, we adopted resting-state functional MRI data and used various matrix decomposition approaches to obtain the organization gradients, temporal dynamics, and information streams. With clustering sensory-association gradient features in our exploratory sample ( N _MDD = 250 and N _Controls = 203), we identified two MDD subtypes. Subtype 1 was characterized by sensory contraction and subtype 2 was associated with association expansion. In addition, two subtypes showed divergent bottom-up and top-down information flows in sensory and association areas using temporal dynamics analysis. These subtypes exhibit distinct age-related changes and reorganization trajectories along sensory-association and auditory-visual axes, highlighting that cortical information flow patterns systematically vary and relate differently to sensory integration, cognitive complexity, and aging. These network distinctions are linked to clinical severity and molecular mechanisms. Subtype 1 is predominantly associated with early neurodevelopmental abnormalities and emotional regulation deficits, while Subtype 2 is more related to synaptic dysfunction and reduced neuronal excitability. These results could be largely replicated in another independent sample ( N _MDD = 73 and N _Controls = 28). We therefore construct a sensory-association dual functional framework to characterize MDD heterogeneity in adolescent MDD. Itl integrates cortical hierarchy, developmental trajectories, and genetic influences, offering novel insights into MDD pathophysiology and providing a theoretical foundation for precision psychiatry, facilitating personalized diagnosis and intervention strategies.

The electrocardiogram (ECG) records heart-beats and is potentially life-saving. However, the ECG signals (e.g., recorded by the standard ECG monitoring system or the Holter ECG monitoring system) heavily suffered from the noises. Thus, the recorded signals involve meaningful cardiac deflections, other biological waves (e.g., caused by the muscle or electrode movements), and even some noises from the monitoring devices (e.g., the power cables). These noise sources would result in inaccurate analyses of cardiac diseases, thus requiring the ECG de-noising methods in data pre-processing phase before the diagnoses. Previous work provided various ECG de-noising approaches, typically based on some filter algorithms or some wave decomposition algorithms. Most of these approaches did not profoundly consider the ECG signals’ specific data structure, and were not adaptive to the signals recorded by various devices or different skin electrodes. Inspired by the ECG recording theory, we find it available to extract noise information from noisy ECG signals directly. We propose a new ECG de-noising method implemented by the neural network, which de-noise the ECG signals without the supervision of the clean signals. The procedure in the self-supervision is straightforward: we first estimate and simulate the noise signals according to the given noisy ECG signals, and then “subtract” the simulated noises to obtain the de-noised ECG signals by the neural network. Experiments on a public dataset verify that our approach is adaptive to ECG signals from different patients and devices. Also, it is proven that the classification on the ECG signals de-noised by the proposed de-noising methods outperforms those with the traditional de-noising methods.