Jiming Zhang

Hepatic encephalopathy (HE) is an independent risk factor for mortality in patients with hepatitis B virus‐related acute‐on‐chronic liver failure (HBV‐ACLF). We aim to assess the effectiveness of 3D deep learning based on CT imaging in predicting HE in HBV‐ACLF patients. A retrospective study was conducted on 222 HBV‐ACLF patients who underwent CT scans at two medical centers. The cohort from Huashan Hospital, consisting of 146 patients, was randomly divided into a training cohort ( n = 102) and a validation cohort ( n = 44). An external test cohort ( n = 76) was sourced from Shanghai Public Health Clinical Center. We employed two architectures, ResNet50 and DenseNet201, to extract 3D deep learning features related to HE. Classical radiomics features were extracted from liver CT images and modeled using three machine learning algorithms. Clinical features associated with HE were analyzed via multivariate logistic regression. The 3D deep learning model demonstrated strong performance in predicting HE in ACLF patients, particularly the ResNet50 model, which achieved AUC values of 0.844 (95% CI: 0.752–0.936) in the training cohort, 0.833 (95% CI: 0.671–0.996) in the validation cohort, and 0.833 (95% CI: 0.686–0.981) in the test cohort. Classical radiomics also demonstrated predictive potential, where XGBoost outperformed other algorithms. INR and ammonia levels were independently associated with HE. The nomogram model integrating 3D deep learning, radiomics features, and clinical predictors achieved the highest predictive accuracy across all cohorts. 3D deep learning performed excellently in predicting HE in ACLF patients, and its combination with radiomics and clinical features further enhanced predictive performance.

Neonicotinoid insecticides (NNIs) are globally pervasive, and toxicological evidence indicates potential adverse effects from low-dose exposure in non-targeted organisms. Humans may be exposed to NNIs through multiple pathways, such as ingestion and inhalation, with dietary intake recognized as the dominant exposure route. However, longitudinal evidence characterizing evolving exposure patterns in rural children remains scarce. We evaluated temporal trends and dietary determinants of NNI exposure among 643 children at ages 7, 10, and 14 years in the Sheyang Mini Birth Cohort Study. Twelve NNIs and six metabolites in urine samples were measured using UPLC-HRMS; estimated daily exposure doses and hazard index (HI) were calculated, and linear mixed models were used to evaluate dietary determinants of NNI exposure. Widespread exposure was observed (ΣNNIs detection: 98.8–100%), and although cumulative risks remained below safety thresholds, both medians and upper bounds of HI increased with age (0.0007 to 0.0074; 0.2045 to 0.4054). Notably, exposure composition shifted, with declining imidacloprid and emerging dominance of clothianidin (CLO) and thiamethoxam (THM). Fruit and vegetable intakes were positively associated with ΣNNIs, whereas cereals, poultry, and eggs showed inverse associations, with more pronounced effects observed in boys. These findings indicated persistent yet evolving exposure risks in school-aged children, highlighting fruits and vegetables as major contributors. Although current toxicological risk appears low, the transition toward CLO and THM—compounds with limited chronic toxicity data—underscores the need for continued biomonitoring and targeted exposure mitigation.