基于人工智能的心血管疾病预测模型研究现状  

The current state of research on cardiovascular disease prediction models based on artificial intelligence

作　　者：彭石娟 王小满 高琴 陈厚早[4] PENG Shijuan;WANG Xiaoman;GAO Qin;CHEN Houzao(School of Health Management,Bengbu Medical University,Bengbu Anhui,233030;Department of Physiology,School of Basic Medicine,Bengbu Medical University,Bengbu Anhui,233030;Key Laboratory of Basic and Clinical Research on Cardio-and Cerebrovascular Diseases,Bengbu Medical University,Bengbu Anhui,233030;State Key Laboratory of Common Mechanism Research for Major Diseases,Department of Biochemistry and Molecular Biology,Institute of Basic Medical Sciences,Chinese Academy of Medical Sciences and Peking Union Medical College,Beijing 100005,China)

机构地区：[1]蚌埠医科大学卫生管理学院,安徽蚌埠233030 [2]蚌埠医科大学基础医学院生理学教研室,安徽蚌埠233030 [3]蚌埠医科大学心脑血管疾病基础与临床重点实验室,安徽蚌埠233030 [4]中国医学科学院基础医学研究所暨北京协和医学院生物化学与分子生物学系重大疾病共性机制研究国家重点实验室,北京100005

出　　处：《蚌埠医科大学学报》2025年第1期6-13,共8页Journal of Bengbu Medical University

摘　　要：心血管疾病(CVD)是全球的主要死因,早期预测对CVD.预防、诊断和治疗至关重要。二十世纪末,研究者根据不同权重将多种危险因素组成风险评分来预测CVD风险,以便确定最有可能从预防性干预措施中获益的人群,为一些国家带来重大利益。然而,传统的风险模型通常无法捕捉危险因素之间的非线性关系。人工智能(AI)技术,特别是监督式机器学习和深度学习,为CVD预测提供了新视角和工具。近几年,基于电子病历、多模态影像等临床数据和衰老大数据可以准确地预测CVD的发病和死亡风险,因此,本文将从传统评分、基于AI的临床数据和衰老大数据的CVD预测模型研究现状分别进行阐述,为促进AI结合CVD提供思路。Cardiovascular diseases(CVD)are the leading cause of death worldwide,and early prediction is crucial for CVD prevention,diagnosis,and treatment.At the end of the twentieth century,researchers combined multiple risk factors into risk scores according to different weights to predict CVD risk,so as to identify the population most likely to benefit from preventive interventions,bringing significant benefits to some countries.However,traditional risk models usually fail to capture the non-linear relationships between risk factors.Artificial intelligence(AI)technologies,especially supervised machine learning and deep learning,provide new perspectives and tools for CVD prediction.In recent years,the risk of CVD morbidity and death can be accurately predicted based on clinical data such as electronic medical records and multimodal imaging,as well as big data on aging.Therefore,this paper will elaborate on the research status of traditional scoring,CVD prediction models based on AI clinical data and big data on aging respectively,so as to provide ideas for promoting the combination of AI and CVD.

关 键 词：心血管疾病 人工智能 预测模型 衰老 生物学年龄 

分 类 号：R540.4[医药卫生—心血管疾病]