急性缺血性脑卒中预后预测研究的应用进展：以机器学习预测模型为例

doi:10.12114/j.issn.1007-9572.2024.0090

中国全科医学 ›› 2025, Vol. 28 ›› Issue (05): 554-560.DOI: 10.12114/j.issn.1007-9572.2024.0090

所属专题：神经/行为/心理最新文章合辑；脑健康最新研究合辑

急性缺血性脑卒中预后预测研究的应用进展：以机器学习预测模型为例

杜慧杰, 刘星雨, 徐明欢, 杨学智, 张慧琴, 莫佳丽, 卢依, 况杰^*()

330006　江西省南昌市，南昌大学公共卫生学院流行病学教研室　江西省预防医学重点实验室

收稿日期:2024-03-10 修回日期:2024-05-20 出版日期:2025-02-15 发布日期:2024-11-25
通讯作者: 况杰
杜慧杰和刘星雨为共同第一作者

作者贡献：
杜慧杰、刘星雨负责文章的设计、构思及论文写作；徐明欢、杨学智、张慧琴、莫佳丽、卢依负责文献的收集、整理；况杰负责文章的修订、质量控制及审校并对文章整体负责；所有作者确认了论文的最终稿。
基金资助:
国家自然科学基金资助项目(82160645，82360667); 江西省自然科学基金(20212BAB206091); 南昌大学2023年科研训练项目(2023); 国家大学生创新创业训练计划项目(202210403017)

Advances in the Prognostic Prediction of Acute Ischemic Stroke: Using Machine Learning Predictive Models as an Example

DU Huijie, LIU Xingyu, XU Minghuan, YANG Xuezhi, ZHANG Huiqin, MO Jiali, LU Yi, KUANG Jie^*()

Department of Epidemiology, School of Public Health, Nanchang University/Jiangxi Provincial Key Laboratory of Preventive Medicine, Nanchang 330006, China

Received:2024-03-10 Revised:2024-05-20 Published:2025-02-15 Online:2024-11-25
Contact: KUANG Jie
About author:
DU Huijie and LIU Xingyu are co-first authors

摘要/Abstract

摘要： 急性缺血性脑卒中（AIS）具有高致残率、高病死率及高复发率等特点，给患者及社会造成沉重的负担。随着大数据时代的到来，预测模型在患者的诊治决策、预后管理以及卫生资源配置等方面的应用越来越多，其价值也愈发重要。机器学习方法是预测AIS患者预后的重要方法之一，且已广泛应用。本文以机器学习方法为重点，就AIS预后预测研究的最新进展予以综述，并提出机器学习预测模型目前所面临的问题与挑战，为AIS患者预后结局早期评估与预测在方法上提供新的思路和参考。

关键词: 缺血性卒中, 预后预测, 机器学习, 预测模型, 综述

Abstract:

Acute ischemic stroke (AIS) is characterized by high rates of disability, mortality, and recurrence, posing a significant burden on patients and society. In the era of big data, predictive models are increasingly used in patient diagnosis, treatment decisions, prognosis management, and healthcare resource allocation, highlighting their growing importance. Machine learning methods have become a crucial tool for predicting the prognosis of AIS patients and have been widely applied. This review explores recent advancements in the study of AIS prognosis prediction, focusing on machine learning methods. It discusses current issues and challenges faced by machine learning models, aiming to provide new insights and references for methods of early assessment and prediction of prognosis outcomes in AIS patients.

Key words: Ischemic stroke, Prognosis prediction, Machine learning, Prediction model, Review

中图分类号:

R 743.3

杜慧杰,刘星雨,徐明欢,等. 急性缺血性脑卒中预后预测研究的应用进展：以机器学习预测模型为例[J]. 中国全科医学, 2025, 28(05): 554-560. DOI: 10.12114/j.issn.1007-9572.2024.0090.
DU Huijie,LIU Xingyu,XU Minghuan, et al. Advances in the Prognostic Prediction of Acute Ischemic Stroke: Using Machine Learning Predictive Models as an Example[J]. Chinese General Practice, 2025, 28(05): 554-560. DOI: 10.12114/j.issn.1007-9572.2024.0090.

参考文献 60

[12]	DROZDOWSKA B A, SINGH S, QUINN T J. Thinking about the future：a review of prognostic scales used in acute stroke[J]. Front Neurol，2019，10:274. DOI：10.3389/fneur.2019.00274.
[13]	BAŞTANLAR Y, OZUYSAL M. Introduction to machine learning[J]. Methods Mol Biol，2014，1107:105-128. DOI：10.1007/978-1-62703-748-8_7.
[14]	OBERMEYER Z, EMANUEL E J. Predicting the future - big data，machine learning，and clinical medicine[J]. N Engl J Med，2016，375(13):1216-1219. DOI：10.1056/NEJMp1606181.
[15]	JANIESCH C, ZSCHECH P, HEINRICH K. Machine learning and deep learning[J]. Electron Mark，2021，31(3):685-695. DOI：10.1007/s12525-021-00475-2.
[16]	KOBAYASHI M, HUTTIN O, MAGNUSSON M, et al. Machine learning-derived echocardiographic phenotypes PredictHeartFailure incidence in asymptomatic individuals[J]. JACC Cardiovasc Imaging，2022，15(2):193-208. DOI：10.1016/j.jcmg.2021.07.004.
[17]	SHAO H, SHI L Z, FONSECA V. Comment on segar et Al. machine learning to predict the risk of incident heart failure hospitalization among patients with diabetes：the WATCH-DM risk score. diabetes care 2019；42：2298-2306[J]. Diabetes Care，2020，43(2):e25. DOI：10.2337/dc19-1891.
[18]	SEGAR M W, JAEGER B C, PATEL K V, et al. Development and validation of machine learning-based race-specific models to predict 10-year risk of heart failure：a multicohort analysis[J]. Circulation，2021，143(24):2370-2383. DOI：10.1161/CIRCULATIONAHA.120.053134.
[19]	KASHOU A H, MEDINA-INOJOSA J R, NOSEWORTHY P A, et al. Artificial intelligence-augmented electrocardiogram detection of left ventricular systolic dysfunction in the general population[J]. Mayo Clin Proc，2021，96(10):2576-2586. DOI：10.1016/j.mayocp.2021.02.029.
[20]	BRATT A, KIM J, POLLIE M, et al. Machine learning derived segmentation of phase velocity encoded cardiovascular magnetic resonance for fully automated aortic flow quantification[J]. J Cardiovasc Magn Reson，2019，21(1):1. DOI：10.1186/s12968-018-0509-0.
[21]	YANG F F, CHEN X T, LIN X X, et al. Automated analysis of Doppler echocardiographic videos as a screening tool for valvular heart diseases[J]. JACC Cardiovasc Imaging，2022，15(4):551-563. DOI：10.1016/j.jcmg.2021.08.015.
[22]	DEBAUN M R, CHAVEZ G, FITHIAN A, et al. Artificial neural networks predict 30-day mortality after hip fracture：insights from machine learning[J]. J Am Acad Orthop Surg，2021，29(22):977-983. DOI：10.5435/JAAOS-D-20-00429.
[23]	JU C S, ZHOU J D, LEE S R, et al. Derivation of an electronic frailty index for predicting short-term mortality in heart failure：a machine learning approach[J]. ESC Heart Fail，2021，8(4):2837-2845. DOI：10.1002/ehf2.13358.
[24]	OBERMEYER Z, EMANUEL E J. Predicting the future - big data，machine learning，and clinical medicine[J]. N Engl J Med，2016，375(13):1216-1219. DOI：10.1056/NEJMp1606181.
[25]	WANG X Y, LYU J H, MENG Z H, et al. Small vessel disease burden predicts functional outcomes in patients with acute ischemic stroke using machine learning[J]. CNS Neurosci Ther，2023，29(4):1024-1033. DOI：10.1111/cns.14071.
[1]	GBD Neurology Collaborators. Global，regional，and national burden of neurological disorders，1990-2016：a systematic analysis for the Global Burden of Disease Study 2016[J]. Lancet Neurol，2019，18(5):459-480. DOI：10.1016/S1474-4422(18)30499-X.
[2]	王拥军，李子孝，谷鸿秋，等. 中国卒中报告2020（中文版）（1）[J]. 中国卒中杂志，2022，17(5):433-447. DOI：10.3969/j.issn.1673-5765.2022.05.001.
[3]	HANKEY G J. Stroke [J]. Lancet，2017，389(10069):641-654. DOI：10.1016/S0140-6736(16)30962-X.
[4]	HANDELMAN G S, KOK H K, CHANDRA R V, et al. eDoctor：machine learning and the future of medicine[J]. J Intern Med，2018，284(6):603-619. DOI：10.1111/joim.12822.
[5]	MOONS K G M, ROYSTON P, VERGOUWE Y, et al. Prognosis and prognostic research：what，why，and how?[J]. BMJ，2009，338:b375. DOI：10.1136/bmj.b375.
[6]	GONG P Y, LIU Y K, GONG Y C, et al. The association of neutrophil to lymphocyte ratio，platelet to lymphocyte ratio，and lymphocyte to monocyte ratio with post-thrombolysis early neurological outcomes in patients with acute ischemic stroke[J]. J Neuroinflammation，2021，18(1):51. DOI：10.1186/s12974-021-02090-6.
[7]	FAINARDI E, BUSTO G, ROSI A, et al. Tmax volumes predict final infarct size and functional outcome in ischemic stroke patients receiving endovascular treatment[J]. Ann Neurol，2022，91(6):878-888. DOI：10.1002/ana.26354.
[8]	WANG K, SHI Q Q, SUN C, et al. A machine learning model for visualization and dynamic clinical prediction of stroke recurrence in acute ischemic stroke patients：a real-world retrospective study[J]. Front Neurosci，2023，17:1130831. DOI：10.3389/fnins.2023.1130831.
[26]	TONG L, SUN Y, ZHU Y Q, et al. Prognostic estimation for acute ischemic stroke patients undergoing mechanical thrombectomy within an extended therapeutic window using an interpretable machine learning model[J]. Front Neuroinform，2023，17:1273827. DOI：10.3389/fninf.2023.1273827.
[27]	BI Q, GOODMAN K E, KAMINSKY J, et al. What is machine learning? A primer for the epidemiologist[J]. Am J Epidemiol，2019，188(12):2222-2239. DOI：10.1093/aje/kwz189.
[28]	KRIEGESKORTE N, GOLAN T. Neural network models and deep learning[J]. Curr Biol，2019，29(7):R231-236. DOI：10.1016/j.cub.2019.02.034.
[29]	HEO J, YOON J G, PARK H, et al. Machine learning-based model for prediction of outcomes in acute stroke[J]. Stroke，2019，50(5):1263-1265. DOI：10.1161/STROKEAHA.118.024293.
[30]	JIANG B, ZHU G, XIE Y, et al. Prediction of clinical outcome in patients with large-vessel acute ischemic stroke：performance of machine learning versus SPAN-100[J]. AJNR Am J Neuroradiol，2021，42(2):240-246. DOI：10.3174/ajnr.A6918.
[31]	TEKKEŞIN A İ. Artificial intelligence in healthcare：past，present and future[J]. Anatol J Cardiol，2019，22(Suppl 2):8-9. DOI：10.14744/AnatolJCardiol.2019.28661.
[32]	BADILLO S, BANFAI B, BIRZELE F, et al. An introduction to machine learning[J]. Clin Pharmacol Ther，2020，107(4):871-885. DOI：10.1002/cpt.1796.
[33]	YANN L, YOSHUA B, GEOFFREY H. Deep learning[J].Nature，2015，521(7553):436-444. DOI：10.1038/nature14539
[34]	GREENER J G, KANDATHIL S M, MOFFAT L, et al. A guide to machine learning for biologists[J]. Nat Rev Mol Cell Biol，2022，23:40-55. DOI：10.1038/s41580-021-00407-0.
[35]	YANG Y, SHI Y Z, ZHANG N, et al. The disability rate of 5-year post-stroke and its correlation factors：a national survey in China[J]. PLoS One，2016，11(11):e0165341. DOI：10.1371/journal.pone.0165341.
[36]	PARK D, JEONG E, KIM H, et al. Machine learning-based three-month outcome prediction in acute ischemic stroke：a single cerebrovascular-specialty hospital study in South Korea[J]. Diagnostics，2021，11(10):1909. DOI：10.3390/diagnostics11101909.
[37]	JO H, KIM C, GWON D, et al. Combining clinical and imaging data for predicting functional outcomes after acute ischemic stroke：an automated machine learning approach[J]. Sci Rep，2023，13(1):16926. DOI：10.1038/s41598-023-44201-8.
[38]	OZKARA B B, KARABACAK M, HAMAM O, et al. Prediction of functional outcome in stroke patients with proximal middle cerebral artery occlusions using machine learning models[J]. J Clin Med，2023，12(3):839. DOI：10.3390/jcm12030839.
[39]	LI X, PAN X D, JIANG C L, et al. Predicting 6-month unfavorable outcome of acute ischemic stroke using machine learning[J]. Front Neurol，2020，11:539509. DOI：10.3389/fneur.2020.539509.
[9]	TONG L, SUN Y, ZHU Y Q, et al. Prognostic estimation for acute ischemic stroke patients undergoing mechanical thrombectomy within an extended therapeutic window using an interpretable machine learning model[J]. Front Neuroinform，2023，17:1273827. DOI：10.3389/fninf.2023.1273827.
[10]	SHEN B, YANG X, SUI R B, et al. The prognostic value of the THRIVE score，the iScore score and the ASTRAL score in Chinese patients with acute ischemic stroke[J]. J Stroke Cerebrovasc Dis，2018，27(10):2877-2886. DOI：10.1016/j.jstrokecerebrovasdis.2018.06.011.
[11]	COORAY C, MAZYA M, BOTTAI M, et al. External validation of the ASTRAL and DRAGON scores for prediction of functional outcome in stroke[J]. Stroke，2016，47(6):1493-1499. DOI：10.1161/STROKEAHA.116.012802.
[40]	LEE J, PARK K M, PARK S. Interpretable machine learning for prediction of clinical outcomes in acute ischemic stroke[J]. Front Neurol，2023，14:1234046. DOI：10.3389/fneur.2023.1234046.
[41]	《中国脑卒中防治报告2021》编写组，王陇德.《中国脑卒中防治报告2021》概要[J]. 中国脑血管病杂志，2023，20(11):783-793.
[42]	WANG K, GU L Y, LIU W C, et al. The predictors of death within 1 year in acute ischemic stroke patients based on machine learning[J]. Front Neurol，2023，14:1092534. DOI：10.3389/fneur.2023.1092534.
[43]	LEHMANN A L C F, ALFIERI D F, DE ARAÚJO M C M, et al. Immune-inflammatory，coagulation，adhesion，and imaging biomarkers combined in machine learning models improve the prediction of death 1year after ischemic stroke[J]. Clin Exp Med，2022，22(1):111-123. DOI：10.1007/s10238-021-00732-w.
[44]	ZHANG J, YUAN T, WEI S X, et al. New strategy for clinical etiologic diagnosis of acute ischemic stroke and blood biomarker discovery based on machine learning[J]. RSC Adv，2022，12(23):14716-14723. DOI：10.1039/d2ra02022j.
[45]	GBD Lifetime Risk of Stroke Collaborators, FEIGIN V L, NGUYEN G, et al. Global，regional，and country-specific lifetime risks of stroke，1990 and 2016[J]. N Engl J Med，2018，379(25):2429-2437. DOI：10.1056/NEJMoa1804492.
[46]	DING L L, MANE R, WU Z Z, et al. Data-driven clustering approach to identify novel phenotypes using multiple biomarkers in acute ischaemic stroke：a retrospective，multicentre cohort study[J]. EClinicalMedicine，2022，53:101639. DOI：10.1016/j.eclinm.2022.101639.
[47]	MA L, FU G P, LIU R R, et al. Phenylacetyl glutamine：a novel biomarker for stroke recurrence warning[J]. BMC Neurol，2023，23(1):74. DOI：10.1186/s12883-023-03118-5.
[48]	CHOI J M, SEO S Y, KIM P J, et al. Prediction of hemorrhagic transformation after ischemic stroke using machine learning[J]. J Pers Med，2021，11(9):863. DOI：10.3390/jpm11090863.
[49]	REN H H, SONG H J, WANG J J, et al. A clinical-radiomics model based on noncontrast computed tomography to predict hemorrhagic transformation after stroke by machine learning：a multicenter study[J]. Insights Imaging，2023，14(1):52. DOI：10.1186/s13244-023-01399-5.
[50]	LEE M, YEO N Y, AHN H J, et al. Prediction of post-stroke cognitive impairment after acute ischemic stroke using machine learning[J]. Alzheimers Res Ther，2023，15(1):147. DOI：10.1186/s13195-023-01289-4.
[51]	JI W C, WANG C J, CHEN H Q, et al. Predicting post-stroke cognitive impairment using machine learning：a prospective cohort study[J]. J Stroke Cerebrovasc Dis，2023，32(11):107354. DOI：10.1016/j.jstrokecerebrovasdis.2023.107354.
[52]	RAJPURKAR P, CHEN E, BANERJEE O, et al. AI in health and medicine[J]. Nat Med，2022，28(1):31-38. DOI：10.1038/s41591-021-01614-0.
[53]	BELTRAMIN D, LAMAS E, BOUSQUET C. Ethical issues in the utilization of black boxes for artificial intelligence in medicine[J]. Stud Health Technol Inform，2022，295:249-252. DOI：10.3233/SHTI220709.
[54]	REYES M, MEIER R, PEREIRA S, et al. On the interpretability of artificial intelligence in radiology：challenges and opportunities[J]. Radiol Artif Intell，2020，2(3):e190043. DOI：10.1148/ryai.2020190043.
[55]	杨丰春，郑思，李姣. 可解释机器学习方法在疾病预测中的应用：脓毒血症患者死亡风险研究[J]. 首都医科大学学报，2022，43(4):610-617. DOI：10.3969/j.issn.1006-7795.2022.04.015.
[56]	LUNDBERG S M, ERION G, CHEN H, et al. From local explanations to global understanding with explainable AI for trees[J]. Nat Mach Intell，2020，2(1):56-67. DOI：10.1038/s42256-019-0138-9.
[57]	HAGENDORFF T. Linking human and machine behavior：a new approach to evaluate training data quality for beneficial machine learning[J]. Minds Mach，2021，31(4):563-593. DOI：10.1007/s11023-021-09573-8.
[58]	WANG M Y, LI S Y, ZHENG T, et al. Big data health care platform with multisource heterogeneous data integration and massive high-dimensional data governance for large hospitals：design，development，and application[J]. JMIR Med Inform，2022，10(4):e36481. DOI：10.2196/36481.
[59]	高景宏，李明原，王琳，等. 健康医疗大数据在精准医疗领域的应用与挑战[J]. 医学信息学杂志，2022，43(5):15-20. DOI：10.3969/j.issn.1673-6036.2022.05.003.
[60]	WU Y F, FANG Y. Stroke prediction with machine learning methods among older Chinese[J]. Int J Environ Res Public Health，2020，17(6):1828. DOI：10.3390/ijerph17061828.

急性缺血性脑卒中预后预测研究的应用进展：以机器学习预测模型为例

Advances in the Prognostic Prediction of Acute Ischemic Stroke: Using Machine Learning Predictive Models as an Example

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 60

相关文章 15

编辑推荐

Metrics

留言

[1]	李静, 刘子琦, 钱莉, 姚瑞芹. 微生物-肠-脑轴在癫痫中的作用研究进展[J]. 中国全科医学, 2026, 29(32): 4821-4826.
[2]	胡健, 刘民, 焦增涛, 景文展, 梁万年. 呼吸道传染病传播风险等级评估研究：以新型冠状病毒感染的公共场所为例[J]. 中国全科医学, 2026, 29(32): 4738-4744.
[3]	李姣, 向庆伟, 刘进进, 彭朗, 周剑杰, 杨琼, 梅应兵, 柳慧, 方英嵩, 谭子虎. 阿尔茨海默病患者跌倒相关住院风险预测模型的构建与验证研究[J]. 中国全科医学, 2026, 29(32): 4721-4729.
[4]	王诗怡, 范小静, 司亚飞, 周忠良. 健康老龄化背景下老年人内在能力关键测量技术的研究进展[J]. 中国全科医学, 2026, 29(31): 4662-4666.
[5]	贺洋, 杨荣, 沈灿, 易珊烨, 刘力滴, 赵茜, 万智, 廖晓阳. 衰弱轨迹及其影响因素研究进展[J]. 中国全科医学, 2026, 29(30): 4372-4378.
[6]	赵家义, 樊剑, 于德华. 1秒率正常的肺功能受损人群现状、挑战及应对策略[J]. 中国全科医学, 2026, 29(30): 4366-4371.
[7]	李喜玲, 张帆, 杨欣月, 杨姮. "零食式锻炼"在慢性病管理中应用的范围综述[J]. 中国全科医学, 2026, 29(30): 4472-4479.
[8]	李姣, 周剑杰, 彭朗, 梅应兵, 谭子虎. 阿尔茨海默病合并社区获得性肺炎发生不良预后风险预测模型的构建与验证研究[J]. 中国全科医学, 2026, 29(29): 4248-4257.
[9]	陈毓婧, 王岩, 李光, 董本超, 杨培川, 马剑雄. 数字技术在亚洲地区老年人肌少症干预中应用的范围综述[J]. 中国全科医学, 2026, 29(29): 4200-4210.
[10]	解霄芸, 刘晨曦, 柳羽姝, 周艺涵. 中国基层医疗卫生机构人工智能研究实践及潜在数据贫困问题：一项范围综述[J]. 中国全科医学, 2026, 29(28): 4067-4077.
[11]	冯雅晨, 刘乐伟, 薛金月, 孙先林, 刘寰忠. 可穿戴技术在精神障碍诊疗中的研究进展[J]. 中国全科医学, 2026, 29(27): 4016-4025.
[12]	刘阳, 冯小洁, 陈洁瑜, 罗仁, 赵晓山, 毕建璐. 基于机器学习揭示生活方式与亚健康之间的关系：一项在中国广东省的横断面研究[J]. 中国全科医学, 2026, 29(26): 3829-3837.
[13]	刘雅慧, 徐雅楠, 袁玲, 武丽桂, 周玉洁, 康玉彪. 基于优先级决策的安宁疗护患者分诊研究范围综述[J]. 中国全科医学, 2026, 29(24): 3538-3544.
[14]	王睿, 罗说明, 杨靓, 王鹏, 赵洋, 王淇, 周智广. 中国老年人糖尿病患病率：一项系统综述和Meta分析[J]. 中国全科医学, 2026, 29(24): 3500-3508.
[15]	吴礼云, 孙华婧, 顾艺卿, 梅紫琦, 金胜姬, 张素菊, 诸赟, 张瑶, 李琴, 刘小苗, 王庆, 柏亚妹, 徐桂华. 数智化技术用于急性心肌梗死心电监测的范围综述[J]. 中国全科医学, 2026, 29(24): 3545-3552.