Use of ChatGPT in Urology and its Relevance in Clinical Practice: Is it useful?
ABSTRACT Purpouse: One of the many artificial intelligence based tools that has gained popularity is the Chat-Generative Pre-Trained Transformer (ChatGPT). Due to its popularity, incorrect information provided by ChatGPT will have an impact on patient misinformation. Furthermore, it may cause misco...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Sociedade Brasileira de Urologia
2024-04-01
|
Series: | International Brazilian Journal of Urology |
Subjects: | |
Online Access: | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1677-55382024000200192&tlng=en |
_version_ | 1797216781181386752 |
---|---|
author | Antonio Vitor Nascimento Martinelli Braga Noel Charlles Nunes Emanoel Nascimento Santos Maria Luiza Veiga Ana Aparecida Nascimento Martinelli Braga Glicia Estevam de Abreu José de Bessa Júnior Luis Henrique Braga Andrew J. Kirsch Ubirajara Barroso Júnior |
author_facet | Antonio Vitor Nascimento Martinelli Braga Noel Charlles Nunes Emanoel Nascimento Santos Maria Luiza Veiga Ana Aparecida Nascimento Martinelli Braga Glicia Estevam de Abreu José de Bessa Júnior Luis Henrique Braga Andrew J. Kirsch Ubirajara Barroso Júnior |
author_sort | Antonio Vitor Nascimento Martinelli Braga |
collection | DOAJ |
description | ABSTRACT Purpouse: One of the many artificial intelligence based tools that has gained popularity is the Chat-Generative Pre-Trained Transformer (ChatGPT). Due to its popularity, incorrect information provided by ChatGPT will have an impact on patient misinformation. Furthermore, it may cause misconduct as ChatGPT can mislead physicians on the decision-making pathway. Therefore, the aim of this study is to evaluate the accuracy and reproducibility of ChatGPT answers regarding urological diagnoses. Materials and Methods: ChatGPT 3.5 version was used. The questions asked for the program involved Primary Megaureter (pMU), Enuresis and Vesicoureteral Reflux (VUR). There were three queries for each topic. The queries were inserted twice, and both responses were recorded to examine the reproducibility of ChatGPT's answers. Afterwards, both answers were combined. Finally, those rwere evaluated qualitatively by a board of three specialists. A descriptive analysis was performed. Results and Conclusion: ChatGPT simulated general knowledge on the researched topics. Regarding Enuresis, the provided definition was partially correct, as the generic response allowed for misinterpretation. For VUR, the response was considered appropriate. For pMU it was partially correct, lacking essential aspects of its definition such as the diameter of the dilatation of the ureter. Unnecessary exams were suggested, for Enuresis and pMU. Regarding the treatment of the conditions mentioned, it specified treatments for Enuresis that are ineffective, such as bladder training. Therefore, ChatGPT responses present a combination of accurate information, but also incomplete, ambiguous and, occasionally, misleading details. |
first_indexed | 2024-04-24T11:51:25Z |
format | Article |
id | doaj.art-9ce7b63a0ddb4cb18d977e3346d4536d |
institution | Directory Open Access Journal |
issn | 1677-6119 |
language | English |
last_indexed | 2024-04-24T11:51:25Z |
publishDate | 2024-04-01 |
publisher | Sociedade Brasileira de Urologia |
record_format | Article |
series | International Brazilian Journal of Urology |
spelling | doaj.art-9ce7b63a0ddb4cb18d977e3346d4536d2024-04-09T07:41:22ZengSociedade Brasileira de UrologiaInternational Brazilian Journal of Urology1677-61192024-04-0150219219810.1590/s1677-5538.ibju.2023.0570Use of ChatGPT in Urology and its Relevance in Clinical Practice: Is it useful?Antonio Vitor Nascimento Martinelli Bragahttps://orcid.org/0000-0001-8240-7418Noel Charlles NunesEmanoel Nascimento SantosMaria Luiza VeigaAna Aparecida Nascimento Martinelli BragaGlicia Estevam de AbreuJosé de Bessa JúniorLuis Henrique BragaAndrew J. KirschUbirajara Barroso JúniorABSTRACT Purpouse: One of the many artificial intelligence based tools that has gained popularity is the Chat-Generative Pre-Trained Transformer (ChatGPT). Due to its popularity, incorrect information provided by ChatGPT will have an impact on patient misinformation. Furthermore, it may cause misconduct as ChatGPT can mislead physicians on the decision-making pathway. Therefore, the aim of this study is to evaluate the accuracy and reproducibility of ChatGPT answers regarding urological diagnoses. Materials and Methods: ChatGPT 3.5 version was used. The questions asked for the program involved Primary Megaureter (pMU), Enuresis and Vesicoureteral Reflux (VUR). There were three queries for each topic. The queries were inserted twice, and both responses were recorded to examine the reproducibility of ChatGPT's answers. Afterwards, both answers were combined. Finally, those rwere evaluated qualitatively by a board of three specialists. A descriptive analysis was performed. Results and Conclusion: ChatGPT simulated general knowledge on the researched topics. Regarding Enuresis, the provided definition was partially correct, as the generic response allowed for misinterpretation. For VUR, the response was considered appropriate. For pMU it was partially correct, lacking essential aspects of its definition such as the diameter of the dilatation of the ureter. Unnecessary exams were suggested, for Enuresis and pMU. Regarding the treatment of the conditions mentioned, it specified treatments for Enuresis that are ineffective, such as bladder training. Therefore, ChatGPT responses present a combination of accurate information, but also incomplete, ambiguous and, occasionally, misleading details.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1677-55382024000200192&tlng=enUrologyVesico-Ureteral RefluxCakut [Supplementary Concept] |
spellingShingle | Antonio Vitor Nascimento Martinelli Braga Noel Charlles Nunes Emanoel Nascimento Santos Maria Luiza Veiga Ana Aparecida Nascimento Martinelli Braga Glicia Estevam de Abreu José de Bessa Júnior Luis Henrique Braga Andrew J. Kirsch Ubirajara Barroso Júnior Use of ChatGPT in Urology and its Relevance in Clinical Practice: Is it useful? International Brazilian Journal of Urology Urology Vesico-Ureteral Reflux Cakut [Supplementary Concept] |
title | Use of ChatGPT in Urology and its Relevance in Clinical Practice: Is it useful? |
title_full | Use of ChatGPT in Urology and its Relevance in Clinical Practice: Is it useful? |
title_fullStr | Use of ChatGPT in Urology and its Relevance in Clinical Practice: Is it useful? |
title_full_unstemmed | Use of ChatGPT in Urology and its Relevance in Clinical Practice: Is it useful? |
title_short | Use of ChatGPT in Urology and its Relevance in Clinical Practice: Is it useful? |
title_sort | use of chatgpt in urology and its relevance in clinical practice is it useful |
topic | Urology Vesico-Ureteral Reflux Cakut [Supplementary Concept] |
url | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1677-55382024000200192&tlng=en |
work_keys_str_mv | AT antoniovitornascimentomartinellibraga useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT noelcharllesnunes useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT emanoelnascimentosantos useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT marialuizaveiga useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT anaaparecidanascimentomartinellibraga useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT gliciaestevamdeabreu useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT josedebessajunior useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT luishenriquebraga useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT andrewjkirsch useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful AT ubirajarabarrosojunior useofchatgptinurologyanditsrelevanceinclinicalpracticeisituseful |