Investigation of Pressure Injuries With Visual ChatGPT Integration: A Descriptive Cross-Sectional Study

IF 3.4 3区医学 Q1 NURSING Journal of Advanced Nursing Pub Date : 2025-03-14 DOI:10.1111/jan.16905

Pelin Karaçay, Polat Goktas, Özgen Yaşar, Burak Uyanik, Sinem Uzlu, Kübra Coşkun, Mesut Benk

{"title":"Investigation of Pressure Injuries With Visual ChatGPT Integration: A Descriptive Cross-Sectional Study","authors":"Pelin Karaçay, Polat Goktas, Özgen Yaşar, Burak Uyanik, Sinem Uzlu, Kübra Coşkun, Mesut Benk","doi":"10.1111/jan.16905","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Aim</h3>\n \n <p>This study aimed to assess the performance of Visual ChatGPT in staging pressure injuries using real patient images, compare it to manual staging by expert nurses, and evaluate its applicability as a supportive tool in wound care management.</p>\n </section>\n \n <section>\n \n <h3> Design</h3>\n \n <p>This study used a descriptive and comparative cross-sectional design.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>The study analysed 155 patient pressure injury images from a hospital database, staged by expert nurses and Visual ChatGPT using the National Pressure Injury Advisory Panel guidelines. Visual ChatGPT's performance was tested in two scenarios: with images only and with images plus wound characteristics. Diagnostic performance was evaluated, including sensitivity, specificity, accuracy, and inter-rater agreement (Kappa).</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>Expert nurses demonstrated superior accuracy and specificity across most pressure injury stages. Visual ChatGPT performed comparably in early-stage pressure injuries, especially when wound characteristics were included, but struggled with unstageable and deep-tissue pressure injuries.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>Visual ChatGPT shows potential as an artificial intelligence tool for pressure injury staging and wound management in nursing. However, improvements are necessary for complex cases, ensuring that artificial intelligence complements clinical judgement.</p>\n </section>\n \n <section>\n \n <h3> Implications for Profession and/or Patient Care</h3>\n \n <p>Visual ChatGPT can serve as an innovative artificial intelligence tool in clinical settings, assisting less experienced nurses and those in areas with limited wound care specialists in staging and managing pressure injuries.</p>\n </section>\n \n <section>\n \n <h3> Reporting Method</h3>\n \n <p>The STROBE checklist was followed for reporting cross-sectional studies in line with the relevant EQUATOR guidelines.</p>\n </section>\n \n <section>\n \n <h3> Patient Contribution</h3>\n \n <p>No patient or public contribution.</p>\n </section>\n </div>","PeriodicalId":54897,"journal":{"name":"Journal of Advanced Nursing","volume":"82 1","pages":"479-492"},"PeriodicalIF":3.4000,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/jan.16905","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Advanced Nursing","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jan.16905","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NURSING","Score":null,"Total":0}

引用次数: 0

Abstract

Aim

This study aimed to assess the performance of Visual ChatGPT in staging pressure injuries using real patient images, compare it to manual staging by expert nurses, and evaluate its applicability as a supportive tool in wound care management.

Design

This study used a descriptive and comparative cross-sectional design.

Methods

The study analysed 155 patient pressure injury images from a hospital database, staged by expert nurses and Visual ChatGPT using the National Pressure Injury Advisory Panel guidelines. Visual ChatGPT's performance was tested in two scenarios: with images only and with images plus wound characteristics. Diagnostic performance was evaluated, including sensitivity, specificity, accuracy, and inter-rater agreement (Kappa).

Results

Expert nurses demonstrated superior accuracy and specificity across most pressure injury stages. Visual ChatGPT performed comparably in early-stage pressure injuries, especially when wound characteristics were included, but struggled with unstageable and deep-tissue pressure injuries.

Conclusion

Visual ChatGPT shows potential as an artificial intelligence tool for pressure injury staging and wound management in nursing. However, improvements are necessary for complex cases, ensuring that artificial intelligence complements clinical judgement.

Implications for Profession and/or Patient Care

Visual ChatGPT can serve as an innovative artificial intelligence tool in clinical settings, assisting less experienced nurses and those in areas with limited wound care specialists in staging and managing pressure injuries.

Reporting Method

The STROBE checklist was followed for reporting cross-sectional studies in line with the relevant EQUATOR guidelines.

Patient Contribution

No patient or public contribution.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

压力损伤与视觉ChatGPT整合的调查：一项描述性横断面研究

本研究旨在评估Visual ChatGPT在使用真实患者图像进行压伤分期中的表现，将其与专家护士手动分期进行比较，并评估其作为伤口护理管理辅助工具的适用性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Journal of Advanced Nursing 医学-护理

CiteScore

6.40

自引率

7.90%

发文量

369

审稿时长

3 months

期刊介绍： The Journal of Advanced Nursing (JAN) contributes to the advancement of evidence-based nursing, midwifery and healthcare by disseminating high quality research and scholarship of contemporary relevance and with potential to advance knowledge for practice, education, management or policy. All JAN papers are required to have a sound scientific, evidential, theoretical or philosophical base and to be critical, questioning and scholarly in approach. As an international journal, JAN promotes diversity of research and scholarship in terms of culture, paradigm and healthcare context. For JAN’s worldwide readership, authors are expected to make clear the wider international relevance of their work and to demonstrate sensitivity to cultural considerations and differences.