AI's deep dive into complex pediatric inguinal hernia issues: a challenge to traditional guidelines?

作者全名："Wang, G.; Liu, Q.; Chen, G.; Xia, B.; Zeng, D.; Chen, G.; Guo, C."

作者地址："[Wang, G.; Liu, Q.; Chen, G.; Xia, B.; Zeng, D.; Guo, C.] Chongqing Med Univ, Womens & Childrens Hosp, Dept Pediat, 120 Longshan Rd, Chongqing 401147, Peoples R China; [Wang, G.] Chongqing Med Univ, Childrens Hosp, Dept Pediat, Chongqing, Peoples R China; [Liu, Q.; Chen, G.; Xia, B.; Zeng, D.; Guo, C.] Chongqing Hlth Ctr Women & Children, Dept Fetus & Pediat, Chongqing, Peoples R China; [Wang, G.; Chen, G.; Guo, C.] Chongqing Med Univ, Chongqing Maternal & Child Hlth Hosp, Dept Pediat Gen Surg, Chongqing, Peoples R China; [Chen, G.] Chongqing Med Univ, Women & Childrens Hosp, Chongqing Hlth Ctr Women & Children, Dept Obstet & Gynecol, 120 Longshan Rd, Chongqing 401147, Peoples R China"

通信作者："Guo, C (通讯作者)，Chongqing Med Univ, Womens & Childrens Hosp, Dept Pediat, 120 Longshan Rd, Chongqing 401147, Peoples R China.; Guo, C (通讯作者)，Chongqing Hlth Ctr Women & Children, Dept Fetus & Pediat, Chongqing, Peoples R China.; Chen, G; Guo, C (通讯作者)，Chongqing Med Univ, Chongqing Maternal & Child Hlth Hosp, Dept Pediat Gen Surg, Chongqing, Peoples R China.; Chen, G (通讯作者)，Chongqing Med Univ, Women & Childrens Hosp, Chongqing Hlth Ctr Women & Children, Dept Obstet & Gynecol, 120 Longshan Rd, Chongqing 401147, Peoples R China."

来源：HERNIA

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001086719400002

JCR分区：Q1

影响因子：2.6

年份：2023

卷号：　

期号：　

开始页：　

结束页：　

文献类型：Article; Early Access

关键词：ChatGPT/ChatGPT 4.0; Inguinal hernia; Controversial issues; Systematic reviews; Guidelines

摘要："Objective This study utilized ChatGPT, an artificial intelligence program based on large language models, to explore controversial issues in pediatric inguinal hernia surgery and compare its responses with the guidelines of the European Association of Pediatric Surgeons (EUPSA).Methods Six contentious issues raised by EUPSA were submitted to ChatGPT 4.0 for analysis, for which two independent responses were generated for each issue. These generated answers were subsequently compared with systematic reviews and guidelines. To ensure content accuracy and reliability, a content analysis was conducted, and expert evaluations were solicited for validation. Content analysis evaluated the consistency or discrepancy between ChatGPT 4.0's responses and the guidelines. An expert scoring method assess the quality, reliability, and applicability of responses. The TF-IDF model tested the stability and consistency of the two responses.Results The responses generated by ChatGPT 4.0 were mostly consistent with the guidelines. However, some differences and contradictions were noted. The average quality score was 3.33, reliability score was 2.75, and applicability score was 3.46 (out of 5). The average similarity between the two responses was 0.72 (out of 1), Content analysis and expert ratings yielded consistent conclusions, enhancing the credibility of our research.Conclusion ChatGPT can provide valuable responses to clinical questions, but it has limitations and requires further improvement. It is recommended to combine ChatGPT with other reliable data sources to improve clinical practice and decision-making."

基金机构："National Natural Science Foundation of China [30973440, 30770950]; Ministry of Key Laboratory of Child Development and Disorders [YBRP-2021XX]; Chongqing Natural Science Foundation [cstc2020jcyj-msxmX0326, CSTB2022NSCQ-MSX0819]"

基金资助正文："The research was supported by the National Natural Science Foundation of China (No: 30973440, 30770950), the Youth Basic Research Project from the Ministry of Key Laboratory of Child Development and Disorders (No. YBRP-2021XX) for collection, analysis and interpretation of data and the key project of the Chongqing Natural Science Foundation (cstc2020jcyj-msxmX0326, CSTB2022NSCQ-MSX0819) in writing the manuscript. The funding agency paid for the scholarships of the students involved in the research."