数字健康技术在卒中一级预防中的应用与挑战

doi:10.3969/j.issn.1673-5765.2025.01.006

摘要/Abstract

摘要： 一级预防是降低卒中发病率最直接且有效的手段。近年来，数字健康技术在卒中一级预防领域展现出巨大的应用潜力。本文综述了数字健康技术在卒中风险因素识别、风险评估与筛查、健康宣教及健康管理与干预等方面的应用现状，并指出了技术在实际应用中所面临的数据质量、模型泛化能力、临床实践整合及隐私保护等挑战，以期为我国未来有效利用数字健康技术加强卒中一级预防、优化卒中预防策略提供参考。

文章导读： 数字健康技术在卒中风险因素识别、风险评估筛查、高危人群健康宣教、健康行为管理和干预等领域被广泛应用，然而在实践中也面临着进一步改善数字健康训练数据的质量与可用性、提高模型的泛化能力与鲁棒性、完善法律与伦理方面的管理规范等挑战。

关键词: 卒中; 一级预防; 数字健康; 应用; 挑战

Abstract: Primary prevention is the most direct and effective means to reduce the incidence of stroke. In recent years, digital health technology has shown great potential in the field of primary prevention for stroke. This paper reviews the current application of digital health technology in stroke risk factor identification, risk assessment and screening, health education, as well as health management and intervention. It also points out the challenges faced by the technology in practical application, including data quality, model generalization ability, integration into clinical practice, and privacy protection. The aim is to provide a reference for effectively utilizing digital health technology to strengthen primary prevention of stroke and optimizing stroke prevention and treatment strategies of stroke in China in the future.

Key words: Stroke; Primary prevention; Digital health; Application; Challenge

中图分类号:

R74
R318

熊维清, 赵一霖, 邱月. 数字健康技术在卒中一级预防中的应用与挑战[J]. 中国卒中杂志, 2025, 20(1): 48-54.

XIONG Weiqing, ZHAO Yilin, QIU Yue. The Application and Challenges of Digital Health Technology in Primary Prevention of Stroke[J]. Chinese Journal of Stroke, 2025, 20(1): 48-54.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.chinastroke.org.cn/CN/10.3969/j.issn.1673-5765.2025.01.006

https://www.chinastroke.org.cn/CN/Y2025/V20/I1/48

参考文献

[1] GBD 2019 Stroke Collaborators. Global，regional，and national burden of stroke and its risk factors，1990—2019：a systematic analysis for the global burden of disease study 2019[J]. Lancet Neurol，2021，20（10）：795-820.
[2] SILVA G S，SCHWAMM L H. Advances in stroke：digital health[J]. Stroke，2022，53（3）：1004-1007.
[3] 吴菊华，张烁，陶雷，等. 基于神经网络的脑卒中风险预测模型研究[J]. 数据分析与知识发现，2019，3（12）：70-75.
WU J H，ZHANG S，TAO L，et al. Predicting stroke risks with neural network[J]. Data Analysis and Knowledge Discovery，2019，3（12）：70-75.
[4] 罗一夫，何健，赵会晶，等. 基于Apriori关联规则的脑卒中危险因素分析[J]. 中国数字医学，2017，12（11）：85-88.
LUO Y F，HE J，ZHAO H J，et al. Analysis on stroke risk factors based on the Apriori association rules[J]. China Digital Medicine，2017，12（11）：85-88.
[5] MORRIS M C，MORADI H，ASLANI M，et al. Predicting incident cardiovascular disease among African-American adults：a deep learning approach to evaluate social determinants of health in the Jackson heart study[J/OL]. PLoS One，2023，18（11）：e0294050[2024-11-09]. https://doi.org/10.1371/journal.pone.0294050.
[6] BUSHNELL C，KERNAN W N，SHARRIEF A Z，et al. 2024 guideline for the primary prevention of stroke：a guideline from the American Heart Association/American Stroke Association[J/OL]. Stroke，2024，55（12）：e344-e424[2024-11-09]. https://doi.org/10.1161/STR.0000000000000475.
[7] 许薇，江京洲，张龙江. 基于心脏CT指导心房颤动病人缺血性脑卒中防治的研究进展[J]. 国际医学放射学杂志，2023，46（4）：436-441.
XU W，JIANG J Z，ZHANG L J. Research progress in prevention and treatment of ischemic stroke in patients with atrial fibrillation guided by cardiac CT[J]. International Journal of Medical Radiology，2023，46（4）：436-441.
[8] BISWAS M，SABA L，OMERZU T，et al. A review on joint carotid intima-media thickness and plaque area measurement in ultrasound for cardiovascular/stroke risk monitoring：artificial intelligence framework[J]. J Digit Imaging，2021，34（3）：581-604.
[9] 刘洁，欧阳烽，吕联江，等. 人工智能在头颈动脉粥样硬化斑块高分辨磁共振血管壁成像中的应用进展[J]. 磁共振成像，2024，15（7）：179-183.
LIU J，OUYANG F，LYU L J，et al. Progress of artificial intelligence application in high-resolution magnetic resonance angiography of head and neck atherosclerotic plaque[J]. Chin J Magn Reson Imaging，2024，15（7）：179-183.
[10] SILVA G S，DE ANDRADE J B C. Digital health in stroke：a narrative review[J]. Arq Neuropsiquiatr，2024，82（8）：1-10.
[11] MANNINI A，TROJANIELLO D，CEREATTI A，et al. A machine learning framework for gait classification using inertial sensors：application to elderly，post-stroke and Huntington’s disease patients[J/OL]. Sensors（Basel），2016，16（1）：134[2024-11-09]. https://doi.org/10.3390/s16010134.
[12] PEREZ M V，MAHAFFEY K W，HEDLIN H，et al. Large-scale assessment of a smartwatch to identify atrial fibrillation[J]. N Engl J Med，2019，381（20）：1909-1917.
[13] 赵洁，常红，李佩佩，等. 可穿戴设备在脑卒中危险因素监测及风险预测中的研究进展[J]. 中华护理杂志，2022，57（9）：1141-1146.
ZHAO J，CHANG H，LI P P，et al. A review of wearable devices in the monitoring of stroke risk factors and risk prediction[J]. Chin J Nurs，2022，57（9）：1141-1146.
[14] 周腾，白璐，陈轶戈，等. 人工智能驱动下的脑卒中高危人群早期筛查和预防工作模式研究[J]. 中国医药导报，2019，16（11）：165-168，181.
ZHOU T，BAI L，CHEN Y G，et al. Early screening and prevention work mode of high-risk stroke patients driven by artificial intelligence[J]. China Medical Herald，2019，16（11）：165-168，181.
[15] 范达英，邓仁丽，缪睿，等. 大数据在脑卒中领域的应用研究进展[J]. 实用心脑肺血管病杂志，2023，31（6）：137-140.
FAN D Y，DENG R L，MIAO R，et al. Research progress on the application of big data in the field of stroke[J]. Pract J Cardiac Cereb Pneum Vasc Dis，2023，31（6）：137-140.
[16] 冯雅靖，方利文，王卓群，等. 在中国农村地区妇女人群中整合开展主要慢性病与“两癌”筛查的可行性分析[J]. 中国慢性病预防与控制，2016，24（6）：466-469.
FENG Y J，FANG L W，WANG Z Q，et al. Feasibility analysis of integrating major chronic disease and“two cancers”screening among women in rural China[J]. Chin J Prev Contr Chron Dis，2016，24（6）：466-469.
[17] 李芬，朱碧帆，陈玉倩，等. 基于个案管理的社区慢性病智慧防治策略：以脑卒中为例[J]. 中国卫生资源，2021，24（5）：542-546.
LI F，ZHU B F，CHEN Y Q，et al. Community-based chronic disease smart prevention and control strategy based on case management：a case study of stroke[J]. Chinese Health Resources，2021，24（5）：542-546.
[18] NWOSU C S，DEV S，BHARDWAJ P，et al. Predicting stroke from electronic health records[J/OL]. Annu Int Conf IEEE Eng Med Biol Soc，2019，2019：5704-5707[2024-11-09]. https://doi.org/10.1109/EMBC.2019.8857234.
[19] SABER H，SOMAI M，RAJAH G B，et al. Predictive analytics and machine learning in stroke and neurovascular medicine[J]. Neurol Res，2019，41（8）：681-690.
[20] 刘婷，朱琴，徐琳，等. 基于机器学习的原发性高血压并发脑梗死的风险预测模型[J]. 海军军医大学学报，2022，43（3）：258-265.
LIU T，ZHU Q，XU L，et al. Risk prediction models of essential hypertension complicated with cerebral infarction based on machine learning algorithm[J]. Academic Journal of Naval Medical University，2022，43（3）：258-265.
[21] CHAO C J，AGASTHI P，BARRY T，et al. Using artificial intelligence in predicting ischemic stroke events after percutaneous coronary intervention[J/OL]. J Invasive Cardiol，2023，35（6）：E297-E311[2024-11-09]. https://doi.org/10.25270/jic/23.00045.
[22] ZHENG J，XIONG Y，ZHENG Y M，et al. Evaluating the stroke risk of patients using machine learning：a new perspective from Sichuan and Chongqing[J]. Eval Rev，2024，48（2）：346-369.
[23] YANG C Q，HU R L，XIONG S L，et al. Development of machine learning-based models for predicting risk factors in acute cerebral infarction patients：a clinical retrospective study[J/OL]. BMC Neurol，2024，24（1）：306[2024-11-09]. https://doi.org/10.1186/s12883-024-03818-6.
[24] ORFANOUDAKI A，CHESLEY E，CADISCH C，et al. Machine learning provides evidence that stroke risk is not linear：the non-linear Framingham stroke risk score[J/OL]. PLoS One，2020，15（5）：e0232414[2024-11-09]. https://doi.org/10.1371/journal.pone.0232414.
[25] 郭铁旦，王灵杰，石彩云，等. 颈动脉全斑块自动分割的影像组学模型对缺血性脑卒中的预测价值[J]. 中西医结合心脑血管病杂志，2024，22（12）：2269-2275.
GUO T D，WANG L J，SHI C Y，et al. The predictive value of the radiomics model for ischemic stroke using automatic carotid plaque segmentation[J]. Chinese Journal of Integrative Medicine on Cardio-Cerebrovascular Disease，2024，22（12）：2269-2275.
[26] ZACCAGNA F，GANESHAN B，ARCA M，et al. CT texture-based radiomics analysis of carotid arteries identifies vulnerable patients：a preliminary outcome study[J]. Neuroradiology，2021，63（7）：1043-1052.
[27] SHAN D Z，WANG S Y，WANG J J，et al. Computed tomography angiography-based radiomics model for predicting carotid atherosclerotic plaque vulnerability[J/OL]. Front Neurol，2023，14：1151326[2024-11-09]. https://doi.org/10.3389/fneur.2023.1151326.
[28] BENTO M，SOUZA R，SALLUZZI M，et al. Automatic identification of atherosclerosis subjects in a heterogeneous MR brain imaging data set[J/OL]. Magn Reson Imaging，2019，62：18-27[2024-11-09]. https://doi.org/10.1016/j.mri.2019.06.007.
[29] 侯玉梅，曾慧，张晨阳，等. 基于数据挖掘的缺血性脑卒中患病风险预测[J]. 中国老年学杂志，2021，41（1）：177-181.
HOU Y M，ZENG H，ZHANG C Y，et al. Risk prediction of ischemic stroke based on data mining[J]. Chinese Journal of Gerontology，2021，41（1）：177-181.
[30] PARMAR P，KRISHNAMURTHI R，IKRAM M A，et al. The Stroke RiskometerTM App：validation of a data collection tool and stroke risk predictor[J]. Int J Stroke，2015，10（2）：231-244.
[31] 陈蕾，袁丙坤，彭成，等. 区域脑卒中救治平台的构建[J]. 现代医院，2021，21（11）：1755-1757.
CHEN L，YUAN B K，PENG C，et al. Construction of a regional stroke rescue platform[J]. Modern Hospitals，2021，21（11）：1755-1757.
[32] PANDIAN J D，GALL S L，KATE M P，et al. Prevention of stroke：a global perspective[J]. Lancet，2018，392（10154）：1269-1278.
[33] GLYNN L G，HAYES P S，CASEY M，et al. Effectiveness of a smartphone application to promote physical activity in primary care：the SMART MOVE randomised controlled trial[J/OL]. Br J Gen Pract，2014，64（624）：e384-e391[2024-11-09]. https://doi.org/10.3399/bjgp14X680461.
[34] CASEY M，HAYES P S，GLYNN F，et al. Patients’ experiences of using a smartphone application to increase physical activity：the SMART MOVE qualitative study in primary care[J/OL]. Br J Gen Pract，2014，64（625）：e500-e508[2024-11-09]. https://doi.org/10.3399/bjgp14X680989.
[35] BENDER M S，COOPER B A，FLOWERS E，et al. Filipinos fit and trim—a feasible and efficacious DPP-based intervention trial[J/OL]. Contemp Clin Trials Commun，2018，12：76-84[2024-11-09]. https://doi.org/10.1016/j.conctc.2018.09.004.
[36] LOPEZ-MEYER P，TIFFANY S，PATIL Y，et al. Monitoring of cigarette smoking using wearable sensors and support vector machines[J]. IEEE Trans Biomed Eng，2013，60（7）：1867-1872.
[37] RAHEJA H，NAMANA V，CHOPRA K，et al. Electrocardiogram changes with acute alcohol intoxication：a systematic review[J/OL]. Open Cardiovasc Med J，2018，12：1-6[2024-11-09]. https://doi.org/10.2174/1874192401812010001.
[38] BUCKINGHAM S A，WILLIAMS A J，MORRISSEY K，et al. Mobile health interventions to promote physical activity and reduce sedentary behaviour in the workplace：a systematic review[J/OL]. Digit Health，2019，5：2055207619839883[2024-11-09]. https://doi.org/10.1177/2055207619839883.
[39] RAJPURKAR P，IRVIN J A，ZHU K，et al. CheXNet：radiologist-level pneumonia detection on chest X-rays with deep learning[J/OL]. ArXiv，2017：abs/1711.05225[2024-11-09]. https://doi.org/10.48550/arXiv.1711.05225.
[40] KRUSE C S，GOSWAMY R，RAVAL Y，et al. Challenges and opportunities of big data in health care：a systematic review[J/OL]. JMIR Med Inform，2016，4（4）：e38[2024-11-09]. https://doi.org/10.2196/medinform.5359.
[41] FERNANDES J N D，CARDOSO V E M，COMESAÑA-CAMPOS A，et al. Comprehensive review：machine and deep learning in brain stroke diagnosis[J/OL]. Sensors（Basel），2024，24（13）：4355[2024-11-09]. https://doi.org/10.3390/s24134355.
[42] CHEN I Y，JOHANSSON F D，SONTAG D. Why is my classifier discriminatory？[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal，Canada：Curran Associates Inc，2018：3543-3554.
[43] 孟钰婷，徐姣娜，裘可凡，等. 深度学习在缺血性脑卒中的应用[J]. 浙江临床医学，2022，24（12）：1892-1894.
MENG Y T，XU J N，QIU K F，et al. Application of deep learning in ischemic stroke[J]. Zhejiang Clinical Medical Journal，2022，24（12）：1892-1894.
[44] 鲁君，张归玲，朱文珍. 人工智能在缺血性脑卒中影像中的应用进展[J]. 中国医学影像学杂志，2022，30（4）：396-400.
LU J，ZHANG G L，ZHU W Z. Advances and applications of artificial intelligence in ischemic stroke imaging[J]. Chinese Journal of Medical Imaging，2022，30（4）：396-400.
[45] 郭雨茜，李华玲. 基于标签噪声鲁棒学习的疾病风险预测[J]. 计算机系统应用，2022，32（10）：184-191.
GUO Y Q，LI H L. Disease risk prediction based on label noise robust learning[J]. Computer Systems & Applications，2022，32（10）：184-191.
[46] GURMESSA D K，JIMMA W. A comprehensive evaluation of explainable artificial intelligence techniques in stroke diagnosis：a systematic review[J/OL]. Cogent Engineering, 2023，10：2273088[2024-11-09]. https://doi.org/10.1080/23311916.2023.2273088.
[47] ROSENFELD A. Better metrics for evaluating explainable artificial intelligence：blue sky ideas track[C/OL]//ENDRISS U，NOWÉ A，DIGNUM F，et al. AAMAS’21：proceedings of the 20th international conference on autonomous agents and multiagent systems. Richland，SC：International Foundation for Autonomous Agents and Multiagent Systems，2021：45-50[2024-11-09]. https://dl.acm.org/doi/abs/10.5555/3463952.3463962.
[48] 申曙光，吴庆艳. 健康治理视角下的数字健康：内涵、价值及应用[J]. 改革，2020（12）：132-144.
SHEN S G，WU Q Y. Connotation，value and application of digital health from health governance perspective[J]. Reform，2020（12）：132-144.
[49] 吕合凯，邓姗姗，范颜颜，等. 老年人数字健康技术应用障碍影响因素分析[J]. 医学信息学杂志，2024，45（4）：38-44.
LYU H K，DENG S S，FAN Y Y，et al. Analysis of influencing factors of digital health technology application obstacles in the elderly[J]. Journal of Medical Informatics，2024，45（4）：38-44.
[50] VAYENA E，王晶. 数字健康：面临的伦理和政策挑战[J]. 中国医学伦理学，2018，31（4）：538-539.
VAYENA E，WANG J. Digital health：ethical and policy challenges[J]. Chinese Medical Ethics，2018，31（4）：538-539.
[51] CAO L，CHONGSUVIVATWONG V，MCNEIL E B. The sociodemographic digital divide in mobile health App use among clients at outpatient departments in Inner Mongolia，China：cross-sectional survey study[J/OL]. JMIR Hum Factors，2022，9（2）：e36962[2024-11-09]. https://doi.org/10.2196/36962.
[52] RODRIGUEZ J A，SHACHAR C，BATES D W. Digital inclusion as health care—supporting health care equity with digital-infrastructure initiatives[J]. N Engl J Med，2022，386（12）：1101-1103.