人工智能聊天机器人在解读压力损伤临床图像中的表现。

IF 3.8 3区医学 Q2 CELL BIOLOGY

Wound Repair and Regeneration Pub Date : 2024-09-01 Epub Date: 2024-05-15 DOI:10.1111/wrr.13189

Makoto Shiraishi, Koji Kanayama, Daichi Kurita, Yuta Moriwaki, Mutsumi Okazaki

{"title":"人工智能聊天机器人在解读压力损伤临床图像中的表现。","authors":"Makoto Shiraishi, Koji Kanayama, Daichi Kurita, Yuta Moriwaki, Mutsumi Okazaki","doi":"10.1111/wrr.13189","DOIUrl":null,"url":null,"abstract":"To evaluate the accuracy of AI chatbots in staging pressure injuries according to the National Pressure Injury Advisory Panel (NPIAP) Staging through clinical image interpretation, a cross-sectional design was conducted to assess five leading publicly available AI chatbots. As a result, three chatbots were unable to interpret the clinical images, whereas GPT-4 Turbo achieved a high accuracy rate (83.0%) in staging pressure injuries, notably outperforming BingAI Creative mode (24.0%) with statistical significance (p < 0.001). GPT-4 Turbo accurately identified Stages 1 (p < 0.001), 3 (p = 0.001), and 4 (p < 0.001) pressure injuries, and suspected deep tissue injuries (p < 0.001), while BingAI demonstrated significantly lower accuracy across all stages. The findings highlight the potential of AI chatbots, especially GPT-4 Turbo, in accurately diagnosing images and aiding the subsequent management of pressure injuries.","PeriodicalId":23864,"journal":{"name":"Wound Repair and Regeneration","volume":" ","pages":"652-654"},"PeriodicalIF":3.8000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Performance of artificial intelligence chatbots in interpreting clinical images of pressure injuries.\",\"authors\":\"Makoto Shiraishi, Koji Kanayama, Daichi Kurita, Yuta Moriwaki, Mutsumi Okazaki\",\"doi\":\"10.1111/wrr.13189\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To evaluate the accuracy of AI chatbots in staging pressure injuries according to the National Pressure Injury Advisory Panel (NPIAP) Staging through clinical image interpretation, a cross-sectional design was conducted to assess five leading publicly available AI chatbots. As a result, three chatbots were unable to interpret the clinical images, whereas GPT-4 Turbo achieved a high accuracy rate (83.0%) in staging pressure injuries, notably outperforming BingAI Creative mode (24.0%) with statistical significance (p < 0.001). GPT-4 Turbo accurately identified Stages 1 (p < 0.001), 3 (p = 0.001), and 4 (p < 0.001) pressure injuries, and suspected deep tissue injuries (p < 0.001), while BingAI demonstrated significantly lower accuracy across all stages. The findings highlight the potential of AI chatbots, especially GPT-4 Turbo, in accurately diagnosing images and aiding the subsequent management of pressure injuries.\",\"PeriodicalId\":23864,\"journal\":{\"name\":\"Wound Repair and Regeneration\",\"volume\":\" \",\"pages\":\"652-654\"},\"PeriodicalIF\":3.8000,\"publicationDate\":\"2024-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Wound Repair and Regeneration\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1111/wrr.13189\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/5/15 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"CELL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Wound Repair and Regeneration","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/wrr.13189","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/15 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"CELL BIOLOGY","Score":null,"Total":0}

引用次数: 0

摘要

为了评估人工智能聊天机器人根据国家压力伤害顾问团（NPIAP）通过临床图像判读进行压力伤害分期的准确性，我们采用横断面设计评估了五款领先的公开人工智能聊天机器人。结果发现，有三个聊天机器人无法解读临床图像，而 GPT-4 Turbo 在压力损伤分期方面达到了很高的准确率（83.0%），明显优于 BingAI Creative 模式（24.0%），且具有统计学意义（p＜0.05）。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Performance of artificial intelligence chatbots in interpreting clinical images of pressure injuries.

To evaluate the accuracy of AI chatbots in staging pressure injuries according to the National Pressure Injury Advisory Panel (NPIAP) Staging through clinical image interpretation, a cross-sectional design was conducted to assess five leading publicly available AI chatbots. As a result, three chatbots were unable to interpret the clinical images, whereas GPT-4 Turbo achieved a high accuracy rate (83.0%) in staging pressure injuries, notably outperforming BingAI Creative mode (24.0%) with statistical significance (p < 0.001). GPT-4 Turbo accurately identified Stages 1 (p < 0.001), 3 (p = 0.001), and 4 (p < 0.001) pressure injuries, and suspected deep tissue injuries (p < 0.001), while BingAI demonstrated significantly lower accuracy across all stages. The findings highlight the potential of AI chatbots, especially GPT-4 Turbo, in accurately diagnosing images and aiding the subsequent management of pressure injuries.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Wound Repair and Regeneration 医学-皮肤病学

CiteScore

5.90

自引率

3.40%

发文量

审稿时长

6-12 weeks

期刊介绍： Wound Repair and Regeneration provides extensive international coverage of cellular and molecular biology, connective tissue, and biological mediator studies in the field of tissue repair and regeneration and serves a diverse audience of surgeons, plastic surgeons, dermatologists, biochemists, cell biologists, and others. Wound Repair and Regeneration is the official journal of The Wound Healing Society, The European Tissue Repair Society, The Japanese Society for Wound Healing, and The Australian Wound Management Association.