人工智能赋能肾病研究：机制探索与治疗优化

孟令章<sup>1; 2</sup>; 杨明月<sup>1; 2; 3</sup>; 熊礼佳<sup>1</sup>; 韦所苏<sup>1</sup>; 黄笑媛<sup>1</sup>; 梁华谦<sup>1</sup>; 毛秀丽<sup>1; 2; 4</sup>; 张霞敏<sup>1; 2; 4</sup>; 林文贤<sup>1</sup>; 叶　琨<sup>1</sup>

引用本文:

【打印本页】【下载PDF全文】【View/Add Comment】【EndNote】【RefMan】【BibTex】

←前一篇|后一篇→

过刊浏览高级检索

本文已被：浏览 188次下载 392次	码上扫一扫！
分享到：微信更多字体:加大+\|默认\|缩小-
人工智能赋能肾病研究：机制探索与治疗优化
孟令章^1，2，杨明月^1，2，3，熊礼佳¹，韦所苏¹，黄笑媛¹，梁华谦¹，毛秀丽^1，2，4，张霞敏^1，2，4，林文贤¹，叶　琨¹
1.广西壮族自治区人民医院（广西医学科学院）广西慢性肾病临床医学研究中心，南宁 530021；2.广西壮族自治区人民医院（广西医学科学院）心血管疾病研究所，南宁 530021；3.右江民族医学院药学院，百色 533000；4.右江民族医学院研究生学院，百色 533000

摘要:

［摘要］　肾脏疾病作为全球公共卫生重大负担之一，其发病率和死亡率持续上升。人工智能（AI）的迅猛发展为肾病机制探索与临床治疗优化提供了革命性工具。该文概述肾病主要类型及其复杂发病机制，并指出了传统研究方法的局限性。阐述AI在多组学数据分析、肾脏病理图像识别、大数据驱动的风险预测以及罕见肾病机制解析中的应用。在临床治疗方面，AI辅助早期筛查、个体化营养与透析优化、预后管理以及肾移植匹配，显著提升了诊断准确率和改善患者预后。该文还分析了AI面临的挑战，并展望未来多模态融合、联邦学习和大语言模型在肾病精准医疗中的前景。

关键词: 肾病人工智能发病机制临床治疗

DOI：10.3969/j.issn.1674-3806.2025.12.05

分类号:R 692

基金项目:广西科技计划项目（编号：桂科AB24010219）；广西自然科学基金项目（编号：2023GXNSFAA026059）

Artificial intelligence empowers kidney disease research: mechanism exploration and treatment optimization

MENG Lingzhang^1,2, YANG Mingyue^1,2,3, XIONG Lijia¹, WEI Suosu¹, HUANG Xiaoyuan¹, LIANG Huaqian¹, MAO Xiuli^1,2,4, ZHANG Xiamin^1,2,4, LIN Wenxian¹, YE Kun¹

1.Guangxi Clinical Research Center for Chronic Kidney Diseases, the People′s Hospital of Guangxi Zhuang Autonomous Region(Guangxi Academy of Medical Sciences), Nanning 530021, China; 2.Institute of Cardiovascular Diseases, the People′s Hospital of Guangxi Zhuang Autonomous Region(Guangxi Academy of Medical Sciences), Nanning 530021, China; 3.School of Pharmacy, Youjiang Medical University for Nationalities, Baise 533000, China; 4.Graduate School, Youjiang Medical University for Nationalities, Baise 533000, China

Abstract:

［Abstract］　Kidney diseases pose one of the major burdens on global public health, and their incidence and mortality continue to rise. The rapid development of artificial intelligence(AI) provides revolutionary tools for exploring the mechanisms of kidney diseases and optimizing clinical treatments. This review summarizes the main types of kidney diseases and their complex pathogenic mechanisms, and points out the limitations of traditional research methods, and elaborates on the applications of AI in multi-omics data analysis, pathological image recognition in kidney diseases, big data-driven risk prediction, and mechanism analysis of rare kidney diseases. In clinical treatments, AI assists early screening, optimizations of individualized nutrition and dialysis, management of prognosis, and kidney transplant matching, significantly improving diagnostic accuracy and patient prognosis. This review also analyzes the challenges faced by AI and looks forward to the future prospects of multimodal fusion, federated learning, and large language models in precision medicine for kidney diseases.

Key words: Kidney diseases Artificial intelligence(AI) Pathogenesis Clinical treatment