Comparative Analysis of ChatGPT and Google Gemini in the Creation of Patient Education Materials for Acute Appendicitis, Cholecystitis, and Hydrocele

被引:0
|
作者
Joseph, Thaimye [1 ]
Sanghavi, Neysa [2 ]
Kanyal, Shweta [3 ]
Majumder, Kaustav [4 ]
Seidu-Aroza, Hakeem [5 ]
Godavarthi, Arjun [6 ]
机构
[1] State Univ Haiti, Fac Med, Port Au Prince, Haiti
[2] St Georges Univ, True Blue, Grenada
[3] Lokmanya Tilak Municipal Med Coll & Govt Hosp, Mumbai, Maharashtra, India
[4] RG Kar Med Coll & Hosp, Kolkata, India
[5] Ho Teaching Hosp, Ho, Ghana
[6] Shadow Creek High Sch, Pearland, TX USA
关键词
Artificial intelligence; ChatGPT; Google Gemini; Educational tool; Acute appendicitis; Cholecystitis; Hydrocele; ARTIFICIAL-INTELLIGENCE;
D O I
10.1007/s12262-024-04112-y
中图分类号
R61 [外科手术学];
学科分类号
摘要
Patient education is essential for managing conditions like acute appendicitis, cholecystitis, and hydrocele, as it empowers patients to seek timely medical intervention, which can dramatically improve outcomes. Artificial intelligence tools are increasingly integral in healthcare, enhancing the delivery and accessibility of patient education. This study aims to compare the effectiveness of ChatGPT and Google Gemini in creating patient education guides on acute appendicitis, cholecystitis, and hydrocele. In this cross-sectional study, we generated patient education brochures for three diseases using two AI tools, ChatGPT and Google Gemini. The responses were evaluated based on several variables including word count, sentence length, readability (assessed with the Flesch-Kincaid Calculator), similarity (analyzed using Quillbot), and reliability (measured by the Modified DISCERN Score). Statistical analyses were performed using unpaired t-tests and Pearson's correlation coefficients. The analysis revealed that there were no significant differences in readability scores, word counts, sentence lengths, or reliability scores between the materials produced by ChatGPT and Google Gemini. Additionally, correlation analyses indicated a positive correlation for ease scores and a negative correlation for reliability scores between the tools, though these findings were not statistically significant. The study concludes that ChatGPT and Google Gemini are equally effective in producing patient education materials for acute appendicitis, cholecystitis, and hydrocele. The absence of significant differences between the two AI tools suggests their potential utility as educational resources in healthcare settings.
引用
收藏
页码:117 / 122
页数:6
相关论文
共 31 条
  • [1] Use of generative large language models for patient education on common surgical conditions: a comparative analysis between ChatGPT and Google Gemini
    El Senbawy, Omar Mahmoud
    Patel, Keval Bhavesh
    Wannakuwatte, Randev Ayodhya
    Thota, Akhila N.
    UPDATES IN SURGERY, 2025,
  • [2] Evaluation of the Usability of ChatGPT-4 and Google Gemini in Patient Education About Rhinosinusitis
    Becerik, Cagri
    Yildiz, Selcuk
    Karaca, Cigdem Tepe
    Toros, Sema Zer
    CLINICAL OTOLARYNGOLOGY, 2025,
  • [3] Google DeepMind's gemini AI versus ChatGPT: a comparative analysis in ophthalmology
    Masalkhi, Mouayad
    Ong, Joshua
    Waisberg, Ethan
    Lee, Andrew G.
    EYE, 2024, 38 (08) : 1412 - 1417
  • [4] ChatGPT versus Google Gemini: a comparison to evaluate patient education guide created on common neurological disorders
    Vidith Phillips
    Fadi Kiryakoza
    Shamsul Arefin
    Nishtha Choudhary
    Renat Garifullin
    Discover Artificial Intelligence, 4 (1):
  • [5] Patient education resources for oral mucositis: a google search and ChatGPT analysis
    Hunter, Nathaniel
    Allen, David
    Xiao, Daniel
    Cox, Madisyn
    Jain, Kunal
    EUROPEAN ARCHIVES OF OTO-RHINO-LARYNGOLOGY, 2025, 282 (03) : 1609 - 1618
  • [6] Political Bias in Large Language Models: A Comparative Analysis of ChatGPT-4, Perplexity, Google Gemini, and Claude
    Choudhary, Tavishi
    IEEE ACCESS, 2025, 13 : 11341 - 11379
  • [7] Comparative performance analysis of large language models: ChatGPT-3.5, ChatGPT-4 and Google Gemini in glucocorticoid-induced osteoporosis
    Tong, Linjian
    Zhang, Chaoyang
    Liu, Rui
    Yang, Jia
    Sun, Zhiming
    JOURNAL OF ORTHOPAEDIC SURGERY AND RESEARCH, 2024, 19 (01):
  • [8] Burn Patient Education in the Modern Age: A Comparative Analysis of ChatGPT and Google Performance Answering Common Questions on Burn Injury and Management
    Pandya, Sumaarg
    Bonetti, Mario Alessandri
    Liu, Hilary Y.
    Jeong, Tiffany
    Ziembicki, Jenny A.
    Egro, Francesco M.
    JOURNAL OF BURN CARE & RESEARCH, 2025,
  • [9] Evaluating the accuracy and reliability of AI chatbots in patient education on cardiovascular imaging: a comparative study of ChatGPT, gemini, and copilot
    Ahmed Marey
    Abdelrahman M. Saad
    Yousef Tanas
    Hossam Ghorab
    Julia Niemierko
    Hazif Backer
    Muhammad Umair
    Egyptian Journal of Radiology and Nuclear Medicine, 56 (1):
  • [10] Benchmarking the performance of large language models in uveitis: a comparative analysis of ChatGPT-3.5, ChatGPT-4.0, Google Gemini, and Anthropic Claude3
    Zhao, Fang-Fang
    He, Han-Jie
    Liang, Jia-Jian
    Cen, Jingyun
    Wang, Yun
    Lin, Hongjie
    Chen, Feifei
    Li, Tai-Ping
    Yang, Jian-Feng
    Chen, Lan
    Cen, Ling-Ping
    EYE, 2024,