[Interpretation of the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis based on regression or machine learning methods (TRIPOD+AI)]

M H Yan; Y Y Zhao; X Liu; W Li; Y Wang

doi:10.3760/cma.j.cn112138-20240926-00609

[Interpretation of the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis based on regression or machine learning methods (TRIPOD+AI)]

Zhonghua Nei Ke Za Zhi. 2025 Jan 1;64(1):4-10. doi: 10.3760/cma.j.cn112138-20240926-00609.

[Article in Chinese]

Authors

M H Yan¹, Y Y Zhao¹, X Liu¹, W Li¹, Y Wang¹

Affiliation

¹ Chinese Academy of Medical Sciences, Peking Union Medical College, National Center for Cardiovascular Diseases, National Clinical Medical Research Center for Cardiovascular Diseases, Fu Wai Hospital Medical Research and Statistics Center, Beijing100037, China.

PMID: 39788590
DOI: 10.3760/cma.j.cn112138-20240926-00609

Abstract

随着人工智能（AI）和机器学习方法在预测模型开发中的广泛应用，个体预后或诊断的多变量预测模型的透明报告（TRIPOD）2015指南已无法全面适应当下研究需求。本文旨在介绍和解析新版报告规范基于回归或机器学习方法的TRIPOD（TRIPOD+AI），通过详尽剖析27项清单条目，帮助研究者在比较TRIPOD 2015与TRIPOD+AI的基础上，更好地理解和应用这一更新的指南，以提高预测模型研究的报告质量、透明性和可重复性。.

MeSH terms

Artificial Intelligence*
Diagnosis
Humans
Machine Learning*
Prognosis
Reproducibility of Results