首页|期刊导航|中国输血杂志|儿科医师/研究生输血医学知识认知现状与大语言模型辅助学习的可靠性研究

儿科医师/研究生输血医学知识认知现状与大语言模型辅助学习的可靠性研究OA

A survey of transfusion medicine knowledge among pediatricians/postgraduates and an evaluation of large language models for learning assistance

中文摘要英文摘要

目的 评估儿科医师/研究生对儿科输血医学的认知现状及大语言模型辅助学习的可靠性,并了解儿科医师在《儿科输血指南》(简称《指南》)实施前后的输血医学认知变化.方法 本研究于 2022 年 1 月(《指南》实施前)基于《指南》内容设计了问卷并对儿科医师展开调查.随后,于 2025 年 7 月(《指南》实施后)结合 2022 年 1 月的问卷内容设计了"儿科输血医学知识问卷"并对儿科医师/研究生及大语言模型进行调查.分析了儿科医师/研究生对输血医学知识掌握情况及大语言模型辅助学习的可靠性,并对比了儿科医师在《指南》实施前后的回答情况.结果《指南》实施后的调查结果显示,儿科医师/研究生在"患者血液管理"主题的回答正确率均高于 80%,但在"血液成分/制品的类型及适应证"和"输血疗效评价"主题的回答正确率均低于 30%.儿科医师在《指南》实施前后对相关题目的回答正确率范围分别为 14.7%~68.9%和 3%~38%,且各题正确率比较具有显著差异(P<0.001).大语言模型对问卷的回答正确率均小于 90%.其中,豆包(81.1%)和Kimi(86.4%)的回答正确率较高.腾讯元宝(混元 hunyuan)最低,仅为 59.5%.结论《指南》的实施可能提升了儿科医师对儿科输血医学的认知水平,但儿科医师/研究生对儿科输血医学的掌握仍不全面,大语言模型也无法提供完全可靠的指导,系统化儿科输血医学培训亟需开展.

Objective To investigate the current knowledge status of transfusion medicine among pediatricians/post-graduates and the reliability of large language models(LLMs)for assisted learning,and to assess changes in pediatricians'transfusion medicine knowledge before and after the implementation of the"Pediatric Transfusion Guideline"(hereafter re-ferred to as the"Guideline").Methods In January 2022(prior to the implementation of the"Guideline"),a question-naire was developed based on the"Guideline"content and distributed to pediatricians.Subsequently,in July 2025(after the implementation of the"Guideline"),the"Pediatric Transfusion Medicine Knowledge Questionnaire"was designed based on the content of the January 2022 questionnaire.This questionnaire survey was conducted on pediatricians/postgrad-uates and LLMs.We analyzed the level of transfusion medicine knowledge among pediatricians/postgraduates and the relia-bility of LLMs for assisted learning,and compared the accuracy of pediatricians'responses before and after"Guideline"im-plementation.Results The survey results after the implementation of the"Guidelines"revealed that pediatricians/post-graduates achieved response accuracy rates exceeding 80%on the topic of"Patient Blood Management".However,re-sponse accuracy rates were below 30%for topics including"Types and Indications of Blood Components/Products"and"E-valuation of Transfusion Efficacy".The pediatricians'accuracy rates for related questions before and after the implementa-tion of the"Guidelines"were 14.7%-68.9%and 3%-38%,respectively,and the comparison of accuracy rates for each question showed significant differences(P<0.001).The accuracy rates of the LLMs on the questionnaire were all below 90%.Among them,Doubao(81.1%)and Kimi(86.4%)achieved relatively higher accuracy rates,while Tencent Yuan-bao(Hunyuan)had the lowest accuracy rate at only 59.5%.Conclusion The implementation of the"Guideline"may have improved pediatricians'knowledge level of pediatric transfusion medicine.However,their knowledge level of pediatric transfusion remains low,and LLMs cannot yet provide absolutely reliable guidance.Systematic training in pediatric transfu-sion medicine is urgently needed.

刘海艇;黄雪原;杨明华;王秋实;黄蓉;桂嵘

中南大学湘雅三医院 输血科,湖南 长沙 410013中南大学湘雅三医院 输血科,湖南 长沙 410013中南大学湘雅三医院 儿科,湖南 长沙 410013中国医科大学附属盛京医院 输血科,辽宁 沈阳 110004中南大学湘雅三医院 输血科,湖南 长沙 410013中南大学湘雅三医院 输血科,湖南 长沙 410013

医药卫生

儿科输血医学大语言模型儿科输血指南问卷调查

pediatricstransfusion medicinelarge language modelspediatric transfusion guidelinequestionnaire survey

《中国输血杂志》 2026 (3)

329-338,10

10.13303/j.cjbt.issn.1004-549x.2026.03.004

评论