人工智能与可穿戴设备在老年人静脉血栓栓塞防治中的研究进展

doi:10.3969/j.issn.1003-9198.2025.09.021

摘要/Abstract

摘要： 随着全球人口老龄化的加剧,静脉血栓栓塞(VTE)在老年人群中的发病率显著上升,其防治面临诸多挑战,包括老年特异性风险因素的复杂性、传统评估工具的局限性等。本文系统综述了人工智能(AI)与可穿戴设备在老年VTE防治中的研究进展,在预测与预防方面,AI模型通过整合多源数据显著提升风险识别精度,AUC值达到0.88。智能鞋垫、毫米波雷达及柔性电子皮肤贴片等可穿戴设备,通过监测步态变异、下肢微动频率及温度梯度等生理指标,实现了对VTE的早期预警,并支持个性化干预措施的制定。在诊断与评估方面,手持床旁超声(POCUS)与可穿戴超声系统结合AI,提升了诊断的效率和准确性。基于电子健康记录(EHR)的决策支持工具和智能设备实时监测生理参数,优化了风险评估与健康管理策略。在治疗方面,AI技术可指导个体化抗凝策略的制定及下腔静脉滤器的循证决策,以及可穿戴设备的动态监测结合行为干预措施,均有效降低了VTE的发生率。尽管AI与可穿戴设备在老年VTE防治中潜力巨大,但数据隐私保护、老年群体技术接受度不同及医疗资源不均仍是主要的推广障碍,未来需构建整合多源数据的智能健康管理平台,强化隐私保护机制,优化设备的适老化设计,并通过多中心临床验证推动技术的转化和应用,以实现更高效、安全的老年VTE智能防治体系。

关键词: 人工智能, 可穿戴设备, 静脉血栓栓塞, 老年人, 个性化医疗

Abstract: With the aging of the global population, the incidence of venous thromboembolism (VTE) has increased significantly in the elderly population, and its prevention and treatment face many challenges, including the complexity of age-specific risk factors and the limitations of traditional assessment tools. This paper systematically reviews the research progress of artificial intelligence (AI) and wearable devices in the prevention and treatment of VTE in the elderly. In terms of prediction and prevention, the AI model significantly improves the accuracy of risk identification by integrating multi-source data, with an AUC value of 0.88. Wearable devices such as smart insoles, millimetre-wave radar, and flexible e-skin patch achieve the early detection of VTE through monitoring the physiological indexes such as gait variations, lower limb micromovement frequency, and temperature gradient, achieving early warning of VTE and supporting the development of personalised interventions. In terms of diagnosis and assessment, handheld bedside ultrasound (POCUS) and wearable ultrasound systems combined with AI have improved the efficiency and accuracy of diagnosis. Decision support tools based on electronic health records (EHR) and real-time physiological parameter monitoring by smart devices optimise risk assessment and health management strategies. On the therapeutic side, AI technology guides the development of individualised anticoagulation strategies and evidence-based decision-making for inferior vena cava filters, and dynamic monitoring of wearable devices combined with behavioural interventions effectively reduces the incidence of VTE. Although AI and wearable devices have great potential in the prevention and treatment of VTE in the elderly, data privacy protection, differences in the acceptance of technology in the elderly population, and uneven medical resources are still the main barriers to the promotion of the technology. In the future, it is necessary to build a smart health management platform integrating data from multiple sources, strengthen the privacy protection mechanism, optimize the aging-adapted design of the devices, and promote the translation and application of the technology through multicenter clinical validation, in order to achieve a more efficient and safe system of intelligent prevention and treatment for VTE in the elderly.

Key words: artificial intelligence, wearable devices, venous thromboembolism, aged, personalized medicine

中图分类号:

周丹, 魏可欣, 邓姝, 何锐. 人工智能与可穿戴设备在老年人静脉血栓栓塞防治中的研究进展[J]. 实用老年医学, 2025, 39(9): 963-967.

ZHOU Dan, WEI Kexin, DENG Shu, HE Rui. Research progress on the prevention and treatment of venous thromboembolism in elderly using artificial intelligence and wearable devices[J]. Practical Geriatrics, 2025, 39(9): 963-967.

参考文献

[1] TRAGAKI A.From ‘demographic bomb’ to ‘silver tsunami’: navigating global population shifts[J]. Eur View, 2024, 23(1): 22-30.
[2] MISMETTI P, BERTOLETTI L, GOUIN I, et al. Elderly patients with venous thromboembolism: insights from the RIETE registry[J]. Presse Med, 2024, 53(4): 104246.
[3] OLEKSIUK-BÓJKO M, LISOWSKA A. Venous thromboembolism: why is it still a significant health problem?[J]. Adv Med Sci, 2023, 68(1): 10-20.
[4] 崔宇浩, 黄立新. 全膝置换术后下肢深静脉血栓形成因素的研究进展[J]. 中华养生保健, 2024, 42(23): 66-69.
[5] CHIASAKUL T, LAM B D, MCNICHOL M, et al. Artificial intelligence in the prediction of venous thromboembolism: a systematic review and pooled analysis[J]. Eur J Haematol, 2023, 111(6): 951-962.
[6] GUAN C, MA F, CHANG S, et al. Interpretable machine learning models for predicting venous thromboembolism in the intensive care unit: an analysis based on data from 207 centers[J]. Crit Care, 2023, 27(1): 406.
[7] JAFLEH E A, ALNAQBI F A, ALMAEENI H A, et al. The role of wearable devices in chronic disease monitoring and patient care: a comprehensive review[J]. Cureus, 2024, 16(9): e68921.
[8] ENGBERS M J, BLOM J W, CUSHMAN M, et al. Functional impairment and risk of venous thrombosis in older adults[J]. J Am Geriatr Soc, 2017, 65(9): 2003-2008.
[9] KEKADE S, HSEIEH C H, ISLAM M M, et al. The usefulness and actual use of wearable devices among the elderly population[J]. Comput Methods Programs Biomed, 2018, 153: 137-159.
[10] GARCIA REYES E P, KELLY R, BUCHANAN G, et al. Understanding older adults’ experiences with technologies for health self-management: interview study[J]. JMIR Aging, 2023, 6: e43197.
[11] AN R, SHEN J, WANG J, et al. A scoping review of methodologies for applying artificial intelligence to physical activity interventions[J]. J Sport Health Sci, 2024, 13(3): 428-441.
[12] 柏霞, 潘力生, 查振平, 等. 静脉血栓栓塞症物理预防研究进展[J]. 当代护士:中旬刊, 2024, 31(2): 5-8.
[13] DELGADO-GONZALO R, HUBBARD J, RENEVEY P, et al. Real-time gait analysis with accelerometer-based smart shoes[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2017, 2017: 148-148c.
[14] TURPPA E, KORTELAINEN J M, ANTROPOV O, et al. Vital sign monitoring using FMCW radar in various sleeping scenarios[J]. Sensors, 2020, 20(22): 6505.
[15] 刘欢欢, 孟虎, 王朝晖. 适老化智能可穿戴设计研究进展及发展趋势[J]. 纺织学报, 2024, 45(3): 236-243.
[16] ZAKI H A, ALBAROUDI B, SHABAN E E, et al. Deep venous thrombosis (DVT) diagnostics: gleaning insights from point-of-care ultrasound (PoCUS) techniques in emergencies: a systematic review and meta-analysis[J]. Ultrasound J, 2024, 16(1): 37.
[17] ZHANG Z, ZHANG R, CHANG C W, et al. iWRAP: a theranostic wearable device with real-time vital monitoring and auto-adjustable compression level for venous thromboembolism[J]. IEEE Trans Biomed Eng, 2021, 68(9): 2776-2786.
[18] YORKGITIS B K, BERNDTSON A E, CROSS A, et al. American Association for the Surgery of Trauma/American College of Surgeons-Committee on Trauma Clinical Protocol for inpatient venous thromboembolism prophylaxis after trauma[J]. J Trauma Acute Care Surg, 2022, 92(3): 597-604.
[19] 宋珅,衡佳鸣,王宁浩,等.可穿戴超声系统的研究进展[J].应用声学,2024,43(3):678-688.
[20] 张敏, 修坤皓, 孙敬尧, 等. 柔性可穿戴压电超声传感器研究进展[J]. 计测技术, 2024, 44(3): 72-83.
[21] 王光明,柏正尧, 宋帅, 等. 阿尔茨海默病辅助诊断的多模态数据融合轻量级网络[J]. 浙江大学学报(工学版), 2025, 59(1): 39-48.
[22] SHENG W, WANG X, XU W, et al. Development and validation of machine learning models for venous thromboembolism risk assessment at admission: a retrospective study[J]. Front Cardiovasc Med, 2023, 10: 1198526.
[23] MOSHAWRAB M, ADDA M, BOUZOUANE A, et al. Smart wearables for the detection of cardiovascular diseases: a systematic literature review[J]. Sensors, 2023, 23(2): 828.
[24] 徐佳诗,吴巧英.柔性织物传感器在智能袜中的应用研究进展[J].现代纺织技术,2024,32(11): 1-14.
[25] 徐建光, 王彤, 单春雷, 等. 虚拟现实技术应用于感觉-运动功能康复的专家共识[J]. 中国康复医学杂志, 2024, 39(4): 461-470.
[26] 刘亚国. 基于智能可穿戴设备的实时健康监测系统[J]. 软件工程与应用, 2022(5): 959-967.
[27] 钱文君, 沈晴霓, 吴鹏飞, 等. 大数据计算环境下的隐私保护技术研究进展[J]. 计算机学报, 2022, 45(4): 669-701.
[28] LAM B D, CHRYSAFI P, CHIASAKUL T, et al. Machine learning natural language processing for identifying venous thromboembolism: systematic review and meta-analysis[J]. Blood Adv, 2024, 8(12): 2991-3000.
[29] PATEL S, PARK H, BONATO P, et al. A review of wearable sensors and systems with application in rehabilitation[J]. J Neuroeng Rehabil, 2012, 9: 21.
[30] WANG G, HAN B, DAI G, et al. Role of physical activity and sedentary behavior in venous thromboembolism: a systematic review and dose-response meta-analysis[J]. Sci Rep, 2024, 14(1): 22088.
[31] 杨鑫鑫, 郭清, 王晓迪, 等. 近十年我国可穿戴设备在健康管理领域的研究现状及发展趋势[J]. 中国全科医学, 2023, 26(12): 1513-1519.
[32] GUPTA A, LAM B D, ZERBEY S, et al. Artificial intelligence meets venous thromboembolism: informaticians’ insights on diagnosis, prevention, and management[J]. Blood Vessel Thromb Hemost, 2024, 1(4): 100031.
[33] SPYROPOULOS A C, GOLDIN M, KOULAS I, et al. Universal EHRs clinical decision support for thromboprophylaxis in medical inpatients: a cluster randomized trial[J]. JACC Adv, 2023, 2(8): 100597.
[34] 麻琛彬, 徐浩然, 李德玉, 等. 穿戴式生理参数监测及其临床应用研究进展[J]. 生物医学工程学杂志, 2021, 38(3): 583-593.
[35] 彭仲康, 崔兴然, 张政波, 等. 可穿戴设备: 评估与监测人体生理状态的展望[J]. 生物医学工程学杂志, 2023, 40(6): 1045-1052.
[36] ROBERTS L M, JAEGER B C, BAPTISTA L C, et al. Wearable technology to reduce sedentary behavior and CVD risk in older adults: a pilot randomized clinical trial[J]. Clin Interv Aging, 2019, 14: 1817-1828.
[37] SHIWANI T, RELTON S, EVANS R, et al. New horizons in artificial intelligence in the healthcare of older people[J]. Age Ageing, 2023, 52(12): afad219.