Objective To explore the distribution characteristics of allergen positivity rates and related influencing factors among children with allergic rhinitis in Shanxi Province, and to provide a scientific basis for the prevention, diagnosis, and treatment of allergic rhinitis in children in this area. Methods A total of 1 376 pediatric patients from Shanxi Province, who visited the Department of Otolaryngology of Shanxi Children's Hospital and underwent serum-specific immunoglobulin E (IgE) testing between March 2024 and March 2025, were selected. The positive rates of common allergens were analyzed, and the sensitization differences of allergens among different age cohorts were compared. The risk factors influencing the occurrence of allergic rhinitis in children were explored. Results The test results showed that 1,258 cases were positive for inhalant allergens, with a positive rate of 91.42%, while 855 cases tested positive for ingested allergens, with a positive rate of 62.14%. The top four inhalant allergens with the highest positive rates were Artemisia (38.01%), short ragweed (33.94%), willow/beech/oak/walnut (23.26%), and cat dander (18.82%). The top four ingested allergens with the highest positive rates were milk (24.56%), egg white (22.89%), peanut/soybean (22.60%), and cashew/pistachio/hazelnut/almond/walnut (18.60%). Among the inhalant allergens in children aged ≤ 16 years old, household dust mites had the highest sensitivity, followed by dust mites. Chicken protein and pistachios/cashews/almonds/hazelnuts/walnuts were more common among food allergens in children aged ≤ 5 years old, while milk and egg white were more common among food allergens in children aged 6-16 years old. The results of the multivariate logistic regression analysis showed that urban residence (OR=1.260, 95%CI: 1.009-1.574), a meat-based diet (OR=1.525, 95%CI: 1.218-1.908), presence of smoking/passive smoking (OR=2.033, 95%CI: 1.625-2.543), history of asthma (OR=4.122, 95%CI: 2.655-6.400), history of allergies (OR=2.016, 95%CI: 1.568-2.592), comorbid adenoid hypertrophy (OR=2.248, 95%CI: 1.529-3.304), and parental allergic rhinitis (OR=1.723, 95%CI: 1.298-2.289) were risk factors for allergic rhinitis in children. Conclusion The allergen spectrum of allergic rhinitis in children in Shanxi region is predominantly inhalant. Mugwort, short ragweed, willow/beech/oak/walnut, and cat dander are the main inhalant allergens, while milk, egg white, peanut/soybean, and cashew/pistachio/hazelnut/almond/walnut are the primary ingested allergens. The allergen positivity rate exhibits characteristic changes with age. Factors such as residing in urban areas, a meat-based diet, and a history of asthma are influential factors in the prevalence of allergic rhinitis among children in the Shanxi region.

The differentiation between benign and malignant thyroid nodules is pivotal in clinical practice. However, current diagnostic systems face challenges, such as heterogeneity in ultrasound interpretation, the invasiveness of fine-needle aspiration cytology and indeterminate of results. Artificial intelligence (AI) has evolved from traditional machine learning to deep learning, enabling advances in image recognition, feature extraction, and multimodal data integration. Nevertheless, AI applications remain constrained by limitations, including the insufficiency of high-quality annotated data and inadequate cross-center generalizability. Future progress will focus on algorithm refinement, multimodal data fusion, and multicenter clinical validation to enhance model generalizability and diagnostic accuracy.

The differentiation between benign and malignant thyroid nodules is pivotal in clinical practice. However, current diagnostic systems face challenges, such as heterogeneity in ultrasound interpretation, the invasiveness of fine-needle aspiration cytology and indeterminate of results. Artificial intelligence (AI) has evolved from traditional machine learning to deep learning, enabling advances in image recognition, feature extraction, and multimodal data integration. Nevertheless, AI applications remain constrained by limitations, including the insufficiency of high-quality annotated data and inadequate cross-center generalizability. Future progress will focus on algorithm refinement, multimodal data fusion, and multicenter clinical validation to enhance model generalizability and diagnostic accuracy.