Background: The COVID-19 pandemic, caused by the SARS-CoV-2 virus, has necessitated reliable and authoritative information for public guidance. The World Health Organization (WHO) has been a primary source of such information, disseminating it through a question and answer format on its official website. Concurrently, ChatGPT 3.5 and 4.0, a deep learning-based natural language generation system, has shown potential in generating diverse text types based on user input. Objective: This study evaluates the accuracy of COVID-19 information generated by ChatGPT 3.5 and 4.0, assessing its potential as a supplementary public information source during the pandemic. Methods: We extracted 487 COVID-19–related questions from the WHO’s official website and used ChatGPT 3.5 and 4.0 to generate corresponding answers. These generated answers were then compared against the official WHO responses for evaluation. Two clinical experts scored the generated answers on a scale of 0-5 across 4 dimensions—accuracy, comprehensiveness, relevance, and clarity—with higher scores indicating better performance in each dimension. The WHO responses served as the reference for this assessment. Additionally, we used the BERT (Bidirectional Encoder Representations from Transformers) model to generate similarity scores (0-1) between the generated and official answers, providing a dual validation mechanism. Results: The mean (SD) scores for ChatGPT 3.5–generated answers were 3.47 (0.725) for accuracy, 3.89 (0.719) for comprehensiveness, 4.09 (0.787) for relevance, and 3.49 (0.809) for clarity. For ChatGPT 4.0, the mean (SD) scores were 4.15 (0.780), 4.47 (0.641), 4.56 (0.600), and 4.09 (0.698), respectively. All differences were statistically significant (P<.001), with ChatGPT 4.0 outperforming ChatGPT 3.5. The BERT model verification showed mean (SD) similarity scores of 0.83 (0.07) for ChatGPT 3.5 and 0.85 (0.07) for ChatGPT 4.0 compared with the official WHO answers. Conclusions: ChatGPT 3.5 and 4.0 can generate accurate and relevant COVID-19 information to a certain extent. However, compared with official WHO responses, gaps and deficiencies exist. Thus, users of ChatGPT 3.5 and 4.0 should also reference other reliable information sources to mitigate potential misinformation risks. Notably, ChatGPT 4.0 outperformed ChatGPT 3.5 across all evaluated dimensions, a finding corroborated by BERT model validation.

Venous malformations are prevalent vascular anomalies. Recent clinical studies have explored the use of sirolimus for these conditions, particularly in patients who are not candidates for, or have shown limited response to, traditional treatments such as sclerotherapy and surgery. This meta-analysis systematically evaluates the efficacy and safety of sirolimus in treating venous malformations. We conducted searches in PubMed, Cochrane Library, Web of Science, and the Cochrane Database of Systematic Reviews until August 10, 2024. The quality of the included prospective studies (including both randomized and single-arm pre-post trials) was assessed using the Cochrane risk of bias tool. Statistical analyses were performed with Review Manager (Version 5.4). Our analysis included eight prospective studies involving 74 patients. Primary outcomes measured changes in the volume and size of the malformations. Secondary outcomes assessed were functional disability scores, hemoglobin levels, coagulation indices, transfusion requirements, patient quality of life, and radiologic responses. Sirolimus demonstrated significant therapeutic benefits, with an odds ratio of 0.02 (95% confidence interval, 0.00-0.08) across six studies evaluating dichotomous variables. Results for continuous variables were consistent. Sirolimus showed safety in short-to medium-term use, with reversible mild to moderate side effects such as oral ulcers and liver function abnormalities. No severe adverse events (grade 3-5) were reported. Sirolimus is effective and safe for treating venous malformations, especially in patients unresponsive to conventional therapies. Future studies should explore long-term effects, optimal dosages, and administration techniques.

This research meticulously explores the diverse factors influencing the occurrence of Hirschsprung‐associated enterocolitis (HAEC) subsequent to surgical interventions for congenital megacolon. Considering that Hirschsprung's Disease (HSCR) management predominantly necessitates excision of the aganglionic intestinal segment, the study specifically delineates the correlation between the extent of the excised intestinal segment and the HAEC risk post‐surgery. An analysis of clinical data from 505 patients spanning 2012–2022 enabled a comparison of clinical attributes between patients with and without postoperative HAEC, the application of statistical analyses to identify factors significantly correlating with HAEC, and the determination of independent risk factors via a Logistic regression model. Findings indicate a significant association between preoperative conditions, HSCR variants, and the excised intestinal segment's length with HAEC risk, identifying resection length and albumin levels as independent risk factors. Notably, an increase in resection length by 1 cm correlates with a 9.8% rise in postoperative HAEC risk, whereas a 1 g/L elevation in albumin levels corresponds to a 5.6% risk reduction. Subgroup analyses reaffirm that, across all HSCR variants, an extended resection length significantly elevates HAEC risk. This study underscores the critical roles of albumin levels and the length of the resected intestinal segment as independent risk factors for HAEC post‐congenital megacolon surgery, providing essential insights for clinical strategies aimed at mitigating HAEC risk and enhancing patient care outcomes.

Background: This study examines the capability of large language models (LLMs) in detecting medical rumors, using hemangioma-related information as an example. It compares the performances of ChatGPT-4o and DeepSeek-R1. Objective: This study aimed to evaluate and compare the accuracy, stability, and expert-rated reliability of 2 LLMs, ChatGPT-4o and DeepSeek-R1, in classifying medical information related to hemangiomas as either “rumors” or “accurate information.” Methods: We collected 82 publicly available texts from social media platforms, medical education websites, international guidelines, and journals. Of the 82 items, 47/82 (57%) were labeled as “rumors,” and 35/82 (43%) were labeled as “accurate information.” Three vascular anomaly specialists with extensive clinical experience independently annotated the texts in a double-blinded manner, and disagreements were resolved by arbitration to ensure labeling reliability. Subsequently, these texts were input into ChatGPT-4o and DeepSeek-R1, with each model generating 2 rounds of results under identical instructions. Output stability was assessed using bidirectional encoder representations from transformers–based semantic similarity scores. Classification accuracy, precision, recall, and F ₁ -score were calculated to evaluate the performance. Additionally, 2 medical experts independently rated the model outputs using a 5-point scale based on clinical guidelines. Statistical analyses included paired t tests, Wilcoxon signed-rank tests, and bootstrap resampling to compute confidence intervals. Results: In terms of semantic stability, the similarity distributions for the 2 models largely overlapped, with no statistically significant difference observed (mean difference=−0.003, 95% CI −0.011 to 0.005; P =.30). Regarding classification performance, DeepSeek-R1 achieved higher accuracy (0.963) compared to ChatGPT-4o (0.910), and also performed better in terms of precision (0.978 vs 0.940), recall (0.957 vs 0.894), and F ₁ -score (0.967 vs 0.916). Expert evaluations revealed that DeepSeek-R1 significantly outperformed ChatGPT-4o on both “rumor” items (mean difference=0.431; P <.001; Cohen d _z =0.594) and “accurate information” items (mean difference=0.264; P =.045; Cohen d _z =0.352), with a particularly pronounced advantage in rumor detection. Conclusions: DeepSeek-R1 demonstrated greater accuracy and rationale in detecting medical rumors compared with ChatGPT-4o. This study provides empirical support for the application of LLMs and recommends optimizing accuracy and incorporating real-time verification mechanisms to mitigate the harmful impact of misleading information on patient health.

BACKGROUND The COVID-19 pandemic, caused by the SARS-CoV-2 virus, has necessitated reliable and authoritative information for public guidance. The World Health Organization (WHO) has been a primary source of such information, disseminating it through a question and answer format on its official website. Concurrently, ChatGPT 3.5 and 4.0, a deep learning-based natural language generation system, has shown potential in generating diverse text types based on user input. OBJECTIVE This study evaluates the accuracy of COVID-19 information generated by ChatGPT 3.5 and 4.0, assessing its potential as a supplementary public information source during the pandemic. METHODS We extracted 487 COVID-19–related questions from the WHO’s official website and used ChatGPT 3.5 and 4.0 to generate corresponding answers. These generated answers were then compared against the official WHO responses for evaluation. Two clinical experts scored the generated answers on a scale of 0-5 across 4 dimensions—accuracy, comprehensiveness, relevance, and clarity—with higher scores indicating better performance in each dimension. The WHO responses served as the reference for this assessment. Additionally, we used the BERT (Bidirectional Encoder Representations from Transformers) model to generate similarity scores (0-1) between the generated and official answers, providing a dual validation mechanism. RESULTS The mean (SD) scores for ChatGPT 3.5–generated answers were 3.47 (0.725) for accuracy, 3.89 (0.719) for comprehensiveness, 4.09 (0.787) for relevance, and 3.49 (0.809) for clarity. For ChatGPT 4.0, the mean (SD) scores were 4.15 (0.780), 4.47 (0.641), 4.56 (0.600), and 4.09 (0.698), respectively. All differences were statistically significant (P<.001), with ChatGPT 4.0 outperforming ChatGPT 3.5. The BERT model verification showed mean (SD) similarity scores of 0.83 (0.07) for ChatGPT 3.5 and 0.85 (0.07) for ChatGPT 4.0 compared with the official WHO answers. CONCLUSIONS ChatGPT 3.5 and 4.0 can generate accurate and relevant COVID-19 information to a certain extent. However, compared with official WHO responses, gaps and deficiencies exist. Thus, users of ChatGPT 3.5 and 4.0 should also reference other reliable information sources to mitigate potential misinformation risks. Notably, ChatGPT 4.0 outperformed ChatGPT 3.5 across all evaluated dimensions, a finding corroborated by BERT model validation.