Background: Fatty liver disease (FLD) is an important risk factor for liver cancer and cardiovascular disease and can lead to significant social and economic burden. However, there is currently no nationwide epidemiological survey for FLD in China, making early FLD screening crucial for the Chinese population. Unfortunately, liver biopsy and abdominal ultrasound, the preferred methods for FLD diagnosis, are not practical for primary medical institutions. Therefore, the aim of this study was to develop machine learning (ML) models for screening individuals at high risk of FLD, and to provide a new perspective on early FLD diagnosis. Methods: This study included a total of 30,574 individuals between the ages of 18 and 70 who completed abdominal ultrasound and the related clinical examinations. Among them, 3474 individuals were diagnosed with FLD by abdominal ultrasound. We used 11 indicators to build eight classification models to predict FLD. The model prediction ability was evaluated by the area under the curve, sensitivity, specificity, positive predictive value, negative predictive value, and kappa value. Feature importance analysis was assessed by Shapley value or root mean square error loss after permutations. Results: Among the eight ML models, the prediction accuracy of the extreme gradient boosting (XGBoost) model was highest at 89.77%. By feature importance analysis, we found that the body mass index, triglyceride, and alanine aminotransferase play important roles in FLD prediction. Conclusion: XGBoost improves the efficiency and cost of large-scale FLD screening.
Background: Non-alcoholic fatty liver disease (NAFLD) is currently the major cause of chronic liver disease globally. Bile acids (BAs) have emerged as relevant signaling molecules that are associated with NAFLD development. This study was aimed to examine the association of serum total bile acids (TBAs) with NAFLD in a large population of Chinese subjects. Methods: This cross sectional study recruited 152,336 participants from the Second Xiangya Hospital, China. NAFLD was diagnosed based on the presence of hepatic steatosis on ultrasonography, without significant alcohol consumption and other known causes for chronic liver disease. A multivariate logistic regression model was used to test for the association of serum TBAs with NAFLD, adjusting for conventional risk factors of NAFLD. Results: A total of 27.4% of the participants had NAFLD. Patients with NAFLD had slightly higher TBA levels than those without, 3.4 vs. 3.0 μmol/L (p < 0.001). However, TBA levels were not associated with NAFLD in the multivariate logistic regression model, which adjusted for age, gender and other acknowledged risk factors for NAFLD (OR = 1.00. 95% CI: 1.00–1.00, p = 0.797). Conclusions: We found that the serum TBA levels were not associated with NAFLD. Future studies in a large population, focusing on serum BA composition may improve the understating of the role of BAs in NAFLD.
Intraoperative hypothermia, defined as a core temperature < 36.0 °C, is a common complication during gastrointestinal surgery, potentially affecting patient outcomes. This study aimed to develop a predictive model for intraoperative hypothermia based on clinical features. In this retrospective, single-center study, we analyzed data from 418 patients who underwent gastrointestinal surgery between January and March 2024 at the First Hospital of Putian City, China. Core temperature was measured intraoperatively using a deep nasal probe every 15 min. Five machine learning models (logistic regression, random forest, support vector machine, XGBoost, and multilayer perceptron) were evaluated to develop a prediction model for hypothermia. Logistic regression (LR) was identified as the optimal model and used to develop a nomogram based on key features. Among 25 clinical features, 12 showed significant differences between the two groups. The LR model demonstrated the best predictive performance [accuracy = 0.808, area under the curve (AUC) = 0.872] and identified six key predictors: temperature at surgery start, surgery duration, cisatracurium use, preoperative temperature, anesthesia time, and preoperative red blood cell count. A nomogram constructed with these features exhibited excellent predictive ability (AUC = 0.877) and clinical utility, as confirmed by decision curve analysis. This study highlights key predictors of intraoperative hypothermia and presents a reliable nomogram for risk prediction in patients undergoing gastrointestinal surgery. These findings can inform targeted interventions and improve perioperative care. Further validation with diverse cohorts is warranted to enhance generalizability.
30 October 2025 in Frontiers in Cardiovascular Medicine
Background: Deep vein thrombosis (DVT) is a common and potentially life-threatening complication after gastrointestinal surgery. Traditional risk assessment tools rely on static variables and may not effectively capture dynamic perioperative changes. Methods: Clinical data from 596 Chinese patients undergoing gastrointestinal surgery were retrospectively collected. Patients were randomly divided into training and validation sets (7:3 ratio). Five machine learning algorithms—logistic regression (LR), Extreme Gradient Boosting (XGBoost), multilayer perceptron (MLP), random forest (RF), and elastic net (ENet)—were applied to identify key predictive features and build risk prediction models. The optimal model was visualized using a nomogram and validated through calibration curves, receiver operating characteristic (ROC) curves, and decision curve analysis (DCA). Results: Among the five models, the RF model achieved the best predictive performance. Postoperative Day-7 D-dimer, Day-1 D-dimer, and Day-5 D-dimer were identified as the most important predictive features. The calibration curve and DCA further confirmed the nomogram's predictive accuracy and clinical utility. Conclusion: We developed a novel machine learning–based model for predicting postoperative DVT in Chinese patients after gastrointestinal surgery. Integrating dynamic biomarkers and nonlinear modeling, the tool enhances early identification of high-risk individuals. Multicenter validation is warranted to further strengthen the model's applicability.
Non‐alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease globally, and diet plays a crucial role in its progression. While dietary fats impact NAFLD, the specific effect of cheese consumption remains unclear. This study employs a two‐sample Mendelian randomization (MR) approach to explore the causal relationship between cheese intake and NAFLD, liver fat content, and liver fat proportion. Using summary‐level data from large genome‐wide association studies, we applied a two‐sample MR approach. Genetic variants linked to cheese consumption served as instrumental variables, selected under strict criteria, including genome‐wide significance and exclusion of pleiotropy. Robustness was ensured through various MR methods, including Inverse Variance Weighted (IVW) and MR‐Egger. MR analysis indicated that increased cheese consumption is negatively associated with NAFLD risk (OR = 0.589, 95% CI: 0.387–0.896, p = 0.014). This inverse relationship also extended to liver fat content (OR = 0.814, 95% CI: 0.689–0.960, p = 0.015) and liver fat proportion (OR = 0.830, 95% CI: 0.695–0.992, p = 0.04). No significant link was found between cheese intake and liver volume (OR = 0.976, 95% CI: 0.846–1.126, p = 0.737). Cheese intake may have a protective effect against NAFLD, potentially informing dietary management strategies. Further research is needed to confirm these findings across diverse populations.