Asthma is the most common chronic disease of childhood, characterized by symptoms such as wheezing, shortness of breath, and coughing. With the advancement of technology, artificial intelligence applications are increasingly being used in various fields, among which ChatGPT is one of the most widely utilized. The aim of this study is to evaluate the reliability, quality, and readability of the answers provided by the ChatGPT-4o application to questions related to pediatric asthma. The ChatGPT-4o application was used to record answers to 25 of the most frequently asked questions about asthma in children. To determine the reliability of the answers, we used the Global Quality Scale and modified DISCERN tool. We tested readability using seven indices: Automated Readability Index, Flesch Reading Ease Score, Flesch-Kincaid Grade Level, Gunning Fog Readability Index, Simple Measure of Gobbledygook, Coleman-Liau Readability Index, and Linsear Write Formula. The answers provided by the ChatGPT-4o application to questions about childhood asthma were found to have good reliability (88% by the first evaluator and 84% by the second evaluator) and high quality (88% by both evaluators). The application scored 10.77 ± 1.58 on the Flesch-Kincaid Grade Level scale, and in conjunction with the other indices, the results indicated that the answers required a high level of reading proficiency. Artificial intelligence can be a reliable tool for parents in providing information about pediatric asthma. However, these findings suggest that readability issues may hinder the clinical application of artificial intelligence-generated content in asthma diagnosis and treatment.

The prevalence of childhood hypertension is steadily increasing, and there is growing evidence that dysbiosis of the gut microbiota plays a role in this process. This study compares the gut microbiota of children with primary hypertension to that of normotensive controls.This case-control study included 20 children with primary hypertension and 20 normotensive children matched for age, gender, and BMI. Exclusion criteria were the presence of chronic diseases other than hypertension, recent antibiotic use, and active infection. Stool samples were analyzed using 16S rRNA sequencing. Statistical analyses included Student’s t-test, Mann-Whitney U test, and FDR correction.Microbial richness was significantly reduced at all taxonomic levels in hypertensive patients. However, there were no significant differences in alpha and beta diversity indices between the groups. Levels of Bacteroidetes and Firmicutes were lower in patients, while the Firmicutes/Bacteroidetes ratio was increased (p<0.05).Changes in gut microbiota composition were observed in children with hypertension compared to the control group. These findings may enable the development of microbiota-based diagnostics and personalized treatments, and open the way for preventive approaches by identifying individuals at risk for chronic diseases.

Background/Objectives: Inborn errors of immunity (IEI) are rare and complex pediatric disorders that create significant information gaps for families and non-specialist healthcare professionals. Large language models (LLMs) such as ChatGPT are increasingly used as on-demand health information resources; however, evidence on their performance in rare pediatric diseases remains limited. This study aimed to evaluate the reliability, quality, readability, understandability, reproducibility, and safety-related concerns of ChatGPT-4o responses to frequently searched questions about pediatric IEI posed by healthcare professionals and patients/caregivers. Methods: This cross-sectional evaluation used the publicly accessible ChatGPT-4o interface to generate responses to 20 frequently searched questions about pediatric IEI, equally distributed between healthcare professional (n = 10) and patient/caregiver queries (n = 10). Three pediatric allergy-immunology specialists independently evaluated response quality using the modified DISCERN (mDISCERN) and Global Quality Scale (GQS) tools, supplemented by a structured expert-based assessment of misinformation, safety-related concerns, suspected factual issues, missing disclaimers, and clinically meaningful inter-iteration inconsistency. Text readability was assessed using four validated indices (ARI, FRES, FKGL, GFR), comprehensibility using the Patient Education Materials Assessment Tool (PEMAT), and reproducibility using natural language processing methods. Results: ChatGPT-4o demonstrated strong overall performance, with median mDISCERN and GQS scores of 4 (IQR: 3–5) for both query types. Readability scores substantially exceeded recommended thresholds, with FKGL scores of 12.96 ± 0.69 and 10.83 ± 0.67 for professional and patient/caregiver queries, respectively. Mean PEMAT understandability scores were 71.80 ± 5.75% for professional queries and 80.80 ± 4.73% for patient/caregiver queries (p = 0.001). Reproducibility was high, with semantic similarity rates of 86.10 ± 3.84% and 87.30 ± 3.68%, respectively. Suspected factual issues were identified in 4 of 20 responses (20%), safety-related concerns in 3 (15%), clinically meaningful inter-iteration inconsistencies in 3 (15%), and missing medical disclaimers in all 20 responses (100%). Conclusions: ChatGPT-4o showed strong performance across validated quality metrics for pediatric IEI information support; however, its high reading level, universal absence of medical disclaimers, and occasional clinically meaningful inconsistencies limit its suitability as a standalone source for clinically sensitive guidance. These findings underscore the need for AI-driven patient education tools with improved readability, adaptive complexity adjustment, and safety-oriented communication.