Objective: The aim of this study was to establish a risk prediction model for sleep quality in patients with obstructive sleep apnea (OSA) based on machine learning algorithms with optimal predictive performance. Methods: A total of 400 OSA patients were included in this study. A LightGBM model was constructed and compared with other machine learning models, in terms of performance metrics such as the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). The SHapley Additive exPlanation (SHAP) analysis was used to interpret the model and identify key predictors of sleep quality. Results: The LightGBM model demonstrated the best predictive performance, with an AUC of 0.910 in the validation set, outperforming support vector machine and random forest. SHAP analysis identified six key predictors of sleep quality: depressive symptoms, OSA duration, oxygen desaturation index (ODI), anxiety symptoms, exercise frequency, and coffee consumption. The model’s calibration curve indicated a high degree of agreement between predicted and observed outcomes, and DCA confirmed its clinical utility. Conclusion: The LightGBM model is the best choice for predicting sleep quality in patients with OSA. Depressive symptoms and ODI were the most influential factors negatively associated with sleep quality. This study not only deepens understanding of the factors affecting sleep quality in OSA patients, but also provides a powerful predictive tool for clinical doctors. Future research can explore the potential of incorporating these predictive factors into comprehensive treatment strategies to improve patient prognosis and overall quality of life.

Objective. Circulating miRNAs are acclaimed biomarkers to predict the occurrence and progression of type 2 diabetes mellitus (T2DM). This study is aimed at analyzing the correlation of circulating miR-210 level and obesity-associated T2DM and then investigating the underlying mechanism of circulating miR-210 in T2DM. Methods. Totally, 137 serum samples from patients with T2DM were collected; meanwhile, the demographic, general, and clinical hematological characteristics, disease history, and dietary patterns were recorded. The miR-210 level in exosomes from serum was detected by qRT-PCR. Then, the correlations of BMI or miR-210 level with patients’ clinical characteristics were analyzed. Furthermore, the miR-210 level was detected in T2DM related various cells under high glucose condition. Meanwhile, the expression of carbohydrate responsive element binding protein (ChREBP) and hypoxia-inducible factor 1α (HIF-1α) was measured by western blotting. Results. The miR-210 level in exosomes from serum was obviously elevated in the group compared with the group. Higher BMI was correlated with abnormal lipid metabolism and impaired liver function as well as higher miR-210 level. Notably, higher miR-210 level was also correlated with abnormal lipid metabolism, disease history, and dietary patterns. In addition, compared with normal cells, high glucose increased the miR-210 level in exosomes from cell culture supernatants as well as cells in HUVEC, VSMC, RAW 264.7, 3 T3-L1, SMC, and Beta-TC-6 cells, while it reduced the expression of ChREBP and HIF-1α. Conclusions. Circulating miR-210 level was closely correlated with obesity-associated T2DM. Furthermore, higher miR-210 level might be implicated in the occurrence and development of T2DM and its complications.

Cognitive impairment and depressive symptoms are prevalent and closely interrelated mental health issues in the elderly. Traditional methods for identifying depressive symptoms in this population often lack effectiveness. Machine learning provides a promising alternative for developing predictive models that can facilitate early identification and intervention. This study utilized data from 945 participants aged 60 years and older with cognitive impairment, sourced from National Health and Nutrition Examination Surveys (2011–2014). Depressive symptoms were assessed using the Patient Health Questionnaire-9. Lasso regression was applied for feature selection, ensuring consistency across models. Several machine learning models, including XGBoost, Logistic Regression, Random Forest, and SVM, were trained and evaluated. Model performance was assessed using accuracy, precision, recall, F1 score, and AUC. The incidence of depressive symptoms in older adults with cognitive impairment was 14.07%. Key predictors identified by lasso included general health, memory difficulties, and age, among others. Notably, general health emerged as a novel and significant predictor in this population, underscoring the interplay between physical and mental health. XGBoost was the best model for comprehensively comparing discrimination, calibration, and clinical utility. Machine learning models, particularly XGBoost, effectively predict depressive symptoms in cognitively impaired older adults. The findings highlight the importance of physical, cognitive, and social factors in depressive symptoms risk. These models have the potential to assist in early screening and intervention, improving patient outcomes. Future research should explore ways to enhance model generalizability, including the use of clinically diagnosed depressive symptoms data and alternative feature selection approaches.

Purpose: Synthesis and characterization of silver (Ag)/titanium dioxide (TiO₂) nanocomposite (ATA) to investigate its antiviral activity against the H1N1 influenza virus and antiviral mechanisms. Materials and Methods: A water-dispersible ATA was prepared by a photocatalytic reduction process from AgNO₃ and TiO₂. The characterization of ATA was performed by ultraviolet-visible spectroscopy, X-ray diffraction, high-resolution transmission electron microscopy and energy-dispersive X-ray spectroscopy. The antiviral activities and the antiviral mechanism of ATA were investigated in detail by light microscopy, transmission electron microscopy and biological techniques such as cell cytotoxicity, 50% tissue culture infectious dose detection, western blot and reverse transcription-polymerase chain reaction. Results: These results showed the successful synthesis of ATA nanocomposite with uniform particle size and distribution. It demonstrated the highly efficient antiviral activity of ATA in a dose- and time-dependent manner, as indicated by the reduction of viral titer and the reduction of cytopathic effects caused by viral infection. In the presence of ATA, the structure of the H1N1 influenza virus is directly destroyed and even disintegrated, with the damaged surface membrane proteins and fuzzy contour. It reduces the infection efficiency of influenza by suppressing the activity and expression of hemagglutinin and neuraminidase. The results of mechanistic studies suggested that ATA nanocomposite primarily interferes with virus attachment to viral receptors on the cell surface. Conclusion: Our study suggests that ATA may be a good antiviral candidate against the influenza virus. Compared with AgNPs alone, our synthesized ATA nanocomposites can achieve similar viral inactivation rates using only a much smaller concentration of AgNPs, greatly reducing the amount of AgNPs and their potential side effects. It has great practical value for attaching ATA to the high-efficiency particulate air network in the air purifier, which can kill the virus attached to it and limit its spread.

Background: Myocardial infarction (MI) patients often experience fear of recurrence, which affects their psychological well-being and quality of life. This study aimed to explore the relationship between illness perception, psychological flexibility, and fear of recurrence, as well as to investigate the demographic factors associated with fear of recurrence in MI patients. Methods: A cross-sectional survey was conducted, enrolling 466 MI patients to complete questionnaires assessing general information, disease-related factors, illness perception, psychological flexibility, and fear of recurrence. Correlation analysis, analysis of variance, and mediation effect analysis were used to explore the relationships between these factors and fear of recurrence. Results: Gender, monthly income, marital status, alcohol consumption, New York Heart Association functional classification (NYHA classification), and number of chronic diseases were significantly associated with fear of recurrence. Illness perception was positively correlated with patients’ fear of recurrence. Psychological flexibility was negatively correlated with fear of recurrence and played a mediating role between illness perception and fear of recurrence, mediating the negative impact of illness perception on fear. Conclusion: The findings of this study emphasize the critical role of psychological flexibility in mitigating the fear of recurrence among myocardial infarction survivors. By targeting modifiable factors such as psychological flexibility and illness perceptions, healthcare providers can develop more effective interventions aimed at improving mental health and overall quality of life for these patients.