基于人工智能的临床预测模型研究报告规范(TRIPOD+AI)中文解读  

A Chinese introduction to TRIPOD+AI statement:transparent reporting of multivariable prediction models for individual prognosis or diagnosis that use artificial intelligence

作　　者：李泽宇 詹正哲 程嘉仪 刘伟 汤炜[1] 刘畅 LI Zeyu;ZHAN Zhengzhe;CHENG Jiayi;LIU Wei;TANG Wei;LIU Chang(State Key Laboratory of Oral Diseases&National Center for Stomatology&National Clinical Research Center for Oral Diseases&Department of Oral and Maxillofacial Surgery,West China Hospital of Stomatology,Sichuan University,Chengdu 610041,P.R.China)

机构地区：[1]口腔疾病防治全国重点实验室,国家口腔医学中心,国家口腔疾病临床医学研究中心,四川大学华西口腔医院口腔颌面外科,成都610041

出　　处：《中国循证医学杂志》2025年第3期339-343,共5页Chinese Journal of Evidence-based Medicine

基　　金：四川省自然科学基金项目(编号:2024NSFSC0659);四川大学华西口腔医院探索与研发项目(编号:RD-03-202303)。

摘　　要：近年来,随着机器学习方法逐渐应用于开发和评估临床预测模型当中,已有的TRIPOD 2015报告规范清单表现出明显的局限性。因此,2024年TRIPOD 2015进行了更新,发表了基于人工智能的TRIPOD报告规范,即TRIPOD+AI,旨在促进全面、准确和透明地开发或评估预测模型研究的报告。本文对TRIPOD+AI的重点内容与条目进行解读,以期为临床研究者提供帮助。In recent years,the TRIPOD 2015 statement has shown significant limitations with the gradual application of machine learning methods in the development and evaluation of clinical prediction models.Therefore,TRIPOD 2015 statement has been updated in 2024 as the TRIPOD+AI statement entitled"TRIPOD+AI statement:updated guidance for reporting clinical prediction models that use regression or machine learning methods",aiming to promote the complete,accurate,and transparent reporting of studies that develop a prediction model or evaluate its performance.This article interprets the key contents and items of the TRIPOD+AI in order to provide aids for clinical researchers.

关 键 词：临床预测模型 预后模型 诊断模型 人工智能 机器学习 TRIPOD 报告规范 

分 类 号：G63[文化科学—教育学]