基于传统方法和机器学习的临床模型预测首次脑卒中:现状与前景  

Clinical Prediction Models Based on Traditional Methods and Machine Learning for Predicting First Stroke:Status and Prospects

作　　者：张子娇 丁顺晶[2] 赵地 梁俊[4] 雷健波[5] ZHANG Zijiao;DING Shunjing;ZHAO Di;LIANG Jun;LEI Jianbo(School of Public Health,Southwest Medical University,Luzhou,Sichuan 646000,China;International Medical Department,Beijing Tiantan Hospital,Capital Medical University,Beijing 100050,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;Department of AI and IT,Second Affiliated Hospital,School of Medicine,Zhejiang University,Hangzhou 310000,China;Center for Medical Informatics,Institute of Advanced Clinical Medicine,Peking University,Beijing 100191,China)

机构地区：[1]西南医科大学公共卫生学院,四川泸州646000 [2]首都医科大学附属北京天坛医院国际医疗部,北京100050 [3]中国科学院计算技术研究所,北京100190 [4]浙江大学医学院附属第二医院人工智能与信息化部,杭州310000 [5]北京大学临床医学高等研究院医学信息学中心,北京100191

出　　处：《协和医学杂志》2025年第2期292-299,共8页Medical Journal of Peking Union Medical College Hospital

基　　金：北京市自然科学基金面上项目(7222306)。

摘　　要：脑卒中是全球第3大致死疾病和第4大致残疾病,其较高的致残率和漫长的康复期不仅严重影响患者生存质量,还给家庭和社会带来沉重负担。一级预防是脑卒中防控的核心,通过早期干预危险因素可有效降低其发病率,因此脑卒中首发风险预测模型的构建具有重要临床价值。近年来,大数据与人工智能技术的发展为脑卒中风险的预测开辟了新路径。本文综述传统方法与机器学习模型在脑卒中首发风险预测中的研究现状,并从3个方面展望其未来发展趋势:首先,应注重技术创新,通过引入深度学习、大模型等先进算法,进一步提升预测模型的精确度;其次,需丰富数据类型和优化模型架构,以构建更加全面且精准的预测模型;最后,应强调模型在真实世界中的临床验证,其一方面可增强模型的鲁棒性和普适性,另一方面可促进医生对预测模型的理解,这对预测模型的应用与推广至关重要。Stroke ranks as the third leading cause of death and the fourth leading cause of disability worldwide.Its high disability rate and prolonged recovery period not only severely impact patientsquality of life but also impose a significant burden on families and society.Primary prevention is the cornerstone of stroke control,as early intervention on risk factors can effectively reduce its incidence.Therefore,the development of predictive models for first⁃ever stroke risk holds substantial clinical value.In recent years,advancements in big data and artificial intelligence technologies have opened new avenues for stroke risk prediction.This article re⁃views the current research status of traditional methods and machine learning models in predicting first⁃ever stroke risk and outlines future development trends from three perspectives:First,emphasis should be placed on technological innovation by incorporating advanced algorithms such as deep learning and large models to further enhance the accuracy of predictive models.Second,there is a need to diversify data types and optimize model architectures to construct more comprehensive and precise predictive models.Lastly,particular attention should be given to the clinical validation of models in real⁃world settings.This not only enhances the robustness and generalizability of the models but also promotes physiciansunderstanding of predictive models,which is crucial for their application and dissemination.

关 键 词：脑卒中 首次卒中 机器学习 临床预测模型 一级预防 

分 类 号：R543[医药卫生—心血管疾病] TP181[医药卫生—内科学]