Triglyceride-glucose (TyG) related indices, which serve as simple markers for insulin resistance, have been closely linked to metabolic dysfunction-associated steatotic liver disease (MASLD), cardiovascular disease (CVD), and mortality. However, the prognostic utility of TyG-related indices in predicting the risk of CVD and mortality among patients with MASLD remains unclear. Data of 97,331 MASLD patients, with a median age of 58.0 years and free of CVD at baseline, were obtained from the UK Biobank. The TyG index, along with its combination with adiposity parameters (i.e. body mass index [BMI], waist circumference [WC], and waist-to-height ratio [WHtR]), were calculated. Cox proportional hazards models and restricted cubic spline (RCS) were performed to evaluate the associations between TyG-related indices and the risk of overall CVD, coronary heart disease (CHD), stroke, all-cause mortality, and cardiovascular mortality. Additionally, Harrell’s C-index, net reclassification index (NRI), and integrated discrimination improvement index (IDI) were used to assess the predictive performance of these indices. Over a median follow-up of 13.56 years, we identified 13,256 cases of overall CVD, 10,980 CHD, 2,926 stroke, 8,809 all-cause mortality, and 1,796 cardiovascular mortality. Compared with the lowest quartile of TyG-related indices, participants with MASLD in the high quartile of TyG-related indices had a significantly increased risk of incident overall CVD, CHD, stroke, and mortality. Specifically, the hazard ratios of occurring overall CVD in the fourth versus the first quartiles were 1.19 (95% confidence interval: 1.13–1.25) for TyG, 1.35 (1.28–1.42) for TyG-BMI, 1.33 (1.26–1.40) for TyG-WC, and 1.39 (1.32–1.46) for TyG-WHtR. RCS analyses indicated a nonlinear association of TyG with CVD outcomes (all P values for nonlinearity < 0.05), whereas there exhibited linear trends in TyG-BMI, TyG-WC, and TyG-WHtR with CVD outcomes (all P values for nonlinearity > 0.05, except for TyG-WC with stroke). Furthermore, TyG-WC and TyG-WHtR demonstrated the significantly higher C-index, NRI, and IDI in predicting risk of CVD and mortality in MASLD patients. TyG-related indices, especially TyG-WC and TyG-WHtR, had significant predictive values for the risk of incident CVD and mortality in individuals with MASLD. TyG-related indices may serve as effective surrogate predictors of CVD and mortality in MASLD patients.

Background: The increasing prevalence of nonalcoholic fatty liver disease (NAFLD) in China presents a significant public health concern. Traditional ultrasound, commonly used for fatty liver screening, often lacks the ability to accurately quantify steatosis, leading to insufficient follow-up for patients with moderate-to-severe steatosis. Transient elastography (TE) provides a more quantitative diagnosis of steatosis and fibrosis, closely aligning with biopsy results. Moreover, machine learning (ML) technology holds promise for developing more precise diagnostic models for NAFLD using a variety of laboratory indicators. Objective: This study aims to develop a novel ML-based diagnostic model leveraging TE results for staging hepatic steatosis. The objective was to streamline the model’s input features, creating a cost-effective and user-friendly tool to distinguish patients with NAFLD requiring follow-up. This innovative approach merges TE and ML to enhance diagnostic accuracy and efficiency in NAFLD assessment. Methods: The study involved a comprehensive analysis of health examination records from Suzhou Municipal Hospital, spanning from March to May 2023. Patient data and questionnaire responses were meticulously inputted into Microsoft Excel 2019, followed by thorough data cleaning and model development using Python 3.7, with libraries scikit-learn and numpy to ensure data accuracy. A cohort comprising 978 residents with complete medical records and TE results was included for analysis. Various classification models, including logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost), were constructed and evaluated based on the area under the receiver operating characteristic curve (AUROC). Results: Among the 916 patients included in the study, 273 were diagnosed with moderate-to-severe NAFLD. The concordance rate between traditional ultrasound and TE for detecting moderate-to-severe NAFLD was 84.6% (231/273). The AUROC values for the RF, LightGBM, XGBoost, SVM, KNN, and LR models were 0.91, 0.86, 0.83, 0.88, 0.77, and 0.81, respectively. These models achieved accuracy rates of 84%, 81%, 78%, 81%, 76%, and 77%, respectively. Notably, the RF model exhibited the best performance. A simplified RF model was developed with an AUROC of 0.88, featuring 62% sensitivity and 90% specificity. This simplified model used 6 key features: waist circumference, BMI, fasting plasma glucose, uric acid, total bilirubin, and high-sensitivity C-reactive protein. This approach offers a cost-effective and user-friendly tool while streamlining feature acquisition for training purposes. Conclusions: The study introduces a groundbreaking, cost-effective ML algorithm that leverages health examination data for identifying moderate-to-severe NAFLD. This model has the potential to significantly impact public health by enabling targeted investigations and interventions for NAFLD. By integrating TE and ML technologies, the study showcases innovative approaches to advancing NAFLD diagnostics.

Background: This study aimed to determine sleep patterns and the prevalence and association factors of sleep disorders in a regionally representative sample in Mo Jiang, China.Methods: A total of 2,346 (participation rate 93.5%) Grade 7 students (aged 13–14 years) from 10 middle schools, including 1,213 (51.7%) boys and 1,133 (48.3%) girls, participated in the study. All the participants were invited to complete questionnaires that acquired information on sleep patterns, academic performance, academic stress, and sociodemographic factors. Sleep disorders were assessed using the Chinese version of the Children’s Sleep Habits Questionnaire. Logistic regression models were used to investigate factors associated with sleep disorders.Results: The prevalence of sleep disorders among rural adolescents was 76.4%, which is higher than that among urban adolescents. Compared with previous findings in urban areas, our results indicate that sleep loss is much more severe in rural adolescents. Sleep disorders were positively associated with factors, such as watching TV [odds ratio (OR) = 1.22, p = 0.001], academic performance (OR = 1.80, p < 0.001), and academic stress (OR = 1.38, p = 0.04). In addition, girls were more likely to suffer from sleep disorders than boys (OR = 1.36, p = 0.01).Conclusion: Insufficient sleep and sleep disorders have become common health problems in rural Chinese adolescents.

Objective Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic.Methods Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC).Results LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models.Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: While metabolic-associated fatty liver disease (MAFLD) has been associated with individual cardiometabolic diseases (CMDs), its role in the dynamic progression to cardiometabolic multimorbidity (CMM) remains unclear. We investigated the association of MAFLD, its severity and subtypes with CMM in individuals with no or one CMD at baseline. Methods: This prospective cohort study involved 386,651 individuals (344,415 without and 42,236 with a single CMD at baseline) from the UK Biobank. MAFLD was defined as the presence of hepatic steatosis plus overweight/obesity, type 2 diabetes (T2D), or metabolic abnormalities. CMM was defined as the coexistence of two or more CMDs in the same person, including T2D, coronary heart disease (CHD) and stroke. Cox proportional hazard models and multistate models were performed to estimate the hazard ratios (HRs) and 95% confidence intervals (95% CIs). Results: During a median follow-up of 13.85 years, 4,622 new-onset CMM cases emerged among participants free of CMD at baseline. MAFLD was significantly associated with an increased risk of incident CMM (adjusted HR: 2.78, 95% CI: 2.60-2.96). Multistate models showed that MAFLD adversely affected most transitions from baseline to single CMDs and then to CMM. Among the single-CMD participants, the adjusted HRs of incident CMM in the MAFLD group were 1.21 (95% CI: 1.13-1.31) for T2D patients, 1.90 (1.75-2.05) for CHD patients, and 1.65 (1.45-1.87) for stroke patients, respectively. Conclusion: MAFLD independently elevated the risk of incident CMM, regardless of the baseline CMD status. These findings emphasize the necessity of targeted MAFLD interventions for CMM prevention.