大型语言模型对模拟肾脏病学患者收件箱消息分诊的数据表1

150条模拟肾内科门诊患者消息,由肾病专家标注分诊等级,用于评估ChatGPT-4分诊准确率。

NIAID Data Ecosystem
浏览 28
文本large language modelChatGPTinbox messagestriagepatient carepatient communicationartificial intelligence
Data Sheet 1: Large Language Model Triaging of Simulated Nephrology Patient Inbox Messages

基本信息

模态
文本
大小
0.000274659 GB
许可
CC BY 4.0
创建/更新时间
2026-10-07
版本
v1

资源简介

大型语言模型对模拟肾脏病学患者收件箱消息分诊的数据表1

【一句话概览】

本数据集是 figshare 公开的文本数据集,收录 1 个文件、合计 274.66 KB,主题涵盖 large language model、ChatGPT、inbox messages、triage、patient care,可用于医学自然语言处理(实体识别、信息抽取等),CC BY 4.0 许可开放获取。

【数据集背景】

本数据集源站标题为《Data Sheet 1_Large language model triaging of simulated nephrology patient inbox messages.pdf》。配套论文《ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health》发表于 Frontiers in Public Health(2023),DOI:10.3389/fpubh.2023.1166120。源站首次发布:2024-09-09。

【数据内容】

源站原始描述:BackgroundEfficient triage of patient communications is crucial for timely medical attention and improved care. This study evaluates ChatGPT’s accuracy in categorizing nephrology patient inbox messages, assessing its potential in outpatient settings. MethodsOne hundred and fifty simulated patient inbox messages were created based on cases typically encountered in everyday practice at a nephrology outpatient clinic. These messages were triaged as non-urgent, urgent, and emergent by two nephrologi…

中文译文(机器翻译,仅供快速理解,请以原文为准):背景 高效分诊患者沟通对于及时获得医疗关注和改善诊疗至关重要。本研究评估了ChatGPT对肾脏病学患者收件箱消息进行分类的准确性,并评估其在门诊环境中的潜力。 方法 基于肾脏病门诊日常实践中通常遇到的病例,创建了150条模拟患者收件箱消息。这些消息由两名肾脏病学家分诊为非紧急、紧急和危急。随后,将这些消息提交给ChatGPT-4,使其独立分诊到相同类别。询问过程进行两次,中间间隔两周。ChatGPT的回答被评为正确(与医生一致)、高估(优先级更高)或低估(优先级更低)。 结果 在第一次试验中,ChatGPT正确分诊了140条(93%)消息,高估了4条消息的优先级(3%),低估了6条消息的优先级(4%)。在第二次试验中,它正确分诊了140条(93%)消息,高估了9条(6%),低估了1条(1%)。准确性不取决于消息的紧急程度(p = 0.19)。ChatGPT回答的内部一致性为92%,评分者内Kappa评分为0.88。 结论 ChatGPT-4在对肾脏病患者消息进行分诊方面表现出高准确性,凸显了AI驱动的分诊系统在提高门诊运营效率和改善患者诊疗方面的潜力。

【数据结构与技术规格】

文件数 1 个,合计 274.66 KB。Data Sheet 1_Large language model triaging of simulated nephrology patient inbox messages.pdf:application/pdf,274.66 KB。数据集 DOI:10.3389/frai.2024.1452469.s001。

【主题与分类】

源站学科分类:Knowledge Representation and Machine Learning。主题标签:large language model、ChatGPT、inbox messages、triage、patient care、patient communication、artificial intelligence。

【适用方向】

文本类数据可用于医学自然语言处理,如命名实体识别、信息抽取与文本分类。

【获取与许可】

源站页面:https://frontiersin.figshare.com/articles/dataset/Data_Sheet_1_Large_language_model_triaging_of_simulated_nephrology_patient_inbox_messages_pdf/26967637

使用许可:CC BY 4.0(https://creativecommons.org/licenses/by/4.0/)。

规范引用:Pham, Justin H.; Thongprayoon, Charat; Miao, Jing; Suppadungsuk, Supawadee; Koirala, Priscilla; Craici, Iasmina M.; et al. (2024). Data Sheet 1_Large language model triaging of simulated nephrology patient inbox messages.pdf. Frontiers. Dataset

官方服务

专家保障全链路合规授权与标注交付

陕川双基地 × 超十家三甲医院直连

从合规授权、采集治理、专业标注到数据集交付,我们提供全链路闭环服务,让高质量临床数据即拿即用。

⚡️ 需要原始数据或标注支持?联系我们获取定制方案。

帮我联系

下载信息

注册下载

需要注册 Kaggle 账号并登录后下载,适合需要跟踪下载记录和使用 API 的用户。

暂未开放

公开下载

无需注册即可直接获取公开样本或文档,适合快速预览和评估数据集质量。

免登录

有偿下载

公开数据集受托下载与技术交付服务。

提供高速下载与技术交付服务(收技术服务费,非数据销售)

暂未开放

当前数据集主要来源为 Kaggle 公开托管,完整影像包建议通过原始链接或 Kaggle API 获取。

使用方式

数据集获取(Figshare)

命令行下载

curl -L -o "Data Sheet 1_Large language model triaging of simulated nephrology patient inbox messages.pdf" "https://ndownloader.figshare.com/files/49075357"

文件清单

  • Data Sheet 1_Large language model triaging of simulated nephrology patient inbox messages.pdf(274.66 KB)

文件总体积 274.66 KB(源站 API 实测)。

数据说明

BackgroundEfficient triage of patient communications is crucial for timely medical attention and improved care. This study evaluates ChatGPT’s accuracy in categorizing nephrology patient inbox messages, assessing its potential in outpatient settings.
MethodsOne hundred and fifty simulated patient inbox messages were created based on cases typically encountered in everyday practice at a nephrology outpatient clinic. These messages were triaged as non-urgent, urgent, and emergent by two nephrologists. The messages were then submitted to ChatGPT-4 for independent triage into the same categories. The inquiry process was performed twice with a two-week period in between. ChatGPT responses were graded as correct (agreement with physicians), overestimation (higher priority), or underestimation (lower priority).
ResultsIn the first trial, ChatGPT correctly triaged 140 (93%) messages, overestimated the priority of 4 messages (3%), and underestimated the priority of 6 messages (4%). In the second trial, it correctly triaged 140 (93%) messages, overestimated the priority of 9 (6%), and underestimated the priority of 1 (1%). The accuracy did not depend on the urgency level of the message (p = 0.19). The internal agreement of ChatGPT responses was 92% with an intra-rater Kappa score of 0.88.
ConclusionChatGPT-4 demonstrated high accuracy in triaging nephrology patient messages, highlighting the potential for AI-driven triage systems to enhance operational efficiency and improve patient care in outpatient clinics.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.3389/frai.2024.1452469.s001(source: https://frontiersin.figshare.com/articles/dataset/Data_Sheet_1_Large_language_model_triaging_of_simulated_nephrology_patient_inbox_messages_pdf/26967637)。

数据缺失?

依托陕西、四川两大基地,我们与超过十家三甲医院建立直接合作关系,覆盖合规授权、采集治理、专业标注、数据交付的全流程,为AI医疗团队提供即拿即用的高质量临床数据。

⚡️ 需要数据支持或标注服务?立即联系我们获取专业方案。

获取专属数据定制方案