多模态人工智能在老年认知功能障碍评估中的应用

doi:10.3969/j.issn.1003-9198.2025.11.005

摘要/Abstract

摘要： 全球人口老龄化所引发的社会问题变得日益严峻,老年人认知功能问题已成为医疗和社会保障系统急需解决的主要难题之一。人工智能技术依靠多模态数据融合,可以整合图像、语音以及生理信号等多种信息源,对老年人的认知功能状态展开动态监测,识别认知功能障碍的早期风险,为老年认知功能障碍提供有效的临床诊治支持辅助,缓解医疗资源短缺所带来的压力。本文对国内外相关最新研究进展进行综述,剖析多模态人工智能在老年认知功能障碍评估中的关键技术以及临床价值,并探讨其未来发展方向,以期为老年人认知功能的健康管理提供全新的思路和方式。

关键词: 人工智能, 认知功能障碍, 卷积神经网络, 自然语言处理

Abstract: The social issues arising from global population aging are becoming increasingly severe, and cognitive dysfunction in the elderly has emerged as one of the most pressing challenges for healthcare and social security systems. Artificial intelligence (AI) technology, leveraging multimodal data fusion, can integrate various information sources such as images, speech, and physiological signals to conduct dynamic monitoring of cognitive function status in the elderly, identify early risks of cognitive dysfunction, and provide effective clinical diagnostic and therapeutic support for patients with cognitive dysfunction, thereby alleviating the pressure caused by shortages in medical resources. This paper reviews the latest research progress, which analyzes the key technologies and clinical value of multimodal AI in the assessment of cognitive dysfunction in the elderly, and explores its future development directions, thereby providing new insights and approaches for the health management of cognitive function in the elderly.

Key words: artificial intelligence, cognitive impairment, convolutional neural networks, natural language processing

中图分类号:

杨嘉慧, 陶新宇, 曲晨,. 多模态人工智能在老年认知功能障碍评估中的应用[J]. 实用老年医学, 2025, 39(11): 1098-1101.

YANG Jiahui, TAO Xinyu, QU Chen. Application of multimodal artificial intelligence in the assessment of cognitive impairment in the elderly[J]. Practical Geriatrics, 2025, 39(11): 1098-1101.

参考文献

[1] 2020 Alzheimer’s disease facts and figures[J]. Alzheimers Dement, 2020. doi: 10.1002/alz.12068. Online ahead of print.
[2] JIA L, DU Y, CHU L, et al. Prevalence, risk factors, and management of dementia and mild cognitive impairment in adults aged 60 years or older in China: a cross-sectional study[J]. Lancet Public Health, 2020, 5(12): e661-e671.
[3] LIVINGSTON G, HUNTLEY J, LIU K Y, et al. Dementia prevention, intervention, and care: 2024 report of the Lancet Standing Commission[J]. Lancet, 2024, 404(10452): 572-628.
[4] 乔梦媛. 老年人认知衰弱风险预测模型的构建及中医体质的关联分析研究[D]. 成都: 成都中医药大学, 2023.
[5] 徐文惠, 阴梦玲. 探索人工智能在抑郁症患者诊断、治疗、护理中的研究进展[J]. 心理月刊, 2025, 20(1): 236-240.
[6] JAMIL Y, KRISHNASWAMI A, ORKABY A R, et al. The impact of cognitive impairment on cardiovascular disease[J]. J Am Coll Cardiol, 2025, 85(25): 2472-2491.
[7] SELKOE D J, HARDY J. The amyloid hypothesis of Alzheimer’s disease at 25 years[J]. EMBO Mol Med, 2016, 8(6):595-608.
[8] VOET S, SRINIVASAN S, LAMKANFI M, et al. Inflammasomes in neuroinflammatory and neurodegenerative diseases[J]. EMBO Mol Med, 2019, 11(6): e10248.
[9] LIANG J, WANG Y, LIU B, et al. Gut microbiota mediates neuroinflammation in Alzheimer’s disease: unraveling key factors and mechanistic insights[J]. Mol Neurobiol, 2025, 62(3): 3746-3763.
[10] RAHMAN M M, USMAN O L, MUNIYANDI R C, et al. A review of machine learning methods of feature selection and classification for autism spectrum disorder[J]. Brain Sci, 2020, 10(12): 949.
[11] AUDUREAU E, SOUBEYRAN P, MARTINEZ-TAPIA C, et al. Machine learning to predict mortality in older patients with cancer: development and external validation of the geriatric cancer scoring system using two large French cohorts[J]. J Clin Oncol, 2025, 43(12):1429-1440.
[12] KIM J, GWAK D, KIM S, et al. Identifying the suicidal ideation risk group among older adults in rural areas: developing a predictive model using machine learning methods[J]. J Adv Nurs, 2023, 79(2): 641-651.
[13] NA K S, GEEM Z W, CHO S E. The development of a suicidal ideation predictive model for community-dwelling elderly aged >55 years[J]. Neuropsychiatr Dis Treat, 2022, 18: 163-172.
[14] ALAHMADI H H, SHEN Y, FOUAD S, et al. Classifying cognitive profiles using machine learning with privileged information in mild cognitive impairment[J]. Front Comput Neurosci, 2016, 10: 117.
[15] AFOURAS T, CHUNG J S, SENIOR A, et al. Deep audio-visual speech recognition[J]. IEEE Trans Pattern Anal Mach Intell, 2022, 44(12):8717-8727.
[16] FU Y, XU L, ZHANG Y, et al. Classification and diagnosis model for Alzheimer’s disease based on multimodal data fusion[J]. Medicine: Baltimore, 2024, 103(52): e41016.
[17] SEAMLESS Communication Team. Joint speech and text machine translation for up to 100 languages[J]. Nature, 2025, 637(8046): 587-593.
[18] LIU T, ZHANG Y, LI Y, et al. Effective gene expression prediction and optimization from protein sequences[J]. Adv Sci: Weinh, 2025, 12(8):e2407664.
[19] TRUHN D, ECKARDT J N, FERBER D, et al. Large language models and multimodal foundation models for precision oncology[J]. NPJ Precis Oncol, 2024, 8(1): 72.
[20] LAHAT A, SHARIF K, ZOABI N, et al. Assessing generative pretrained transformers (GPT) in clinical decision-making: comparative analysis of GPT-3.5 and GPT-4[J]. J Med Internet Res, 2024, 26: e54571.
[21] HOPKINS E G, LEMAN P J, CERVIN M, et al. Network of mental activities, cognitive function and depression in older men and women[J]. J Psychiatr Res, 2023, 162: 113-122.
[22] XU X, ZHOU Y, SUN S, et al. Risk prediction for elderly cognitive impairment by radiomic and morphological quantification analysis based on a cerebral MRA imaging cohort[J]. Eur Radiol, 2025, 35(7): 4300-4314.
[23] KERZ E, ZANWAR S, QIAO Y, et al. Toward explainable AI (XAI) for mental health detection based on language behavior[J]. Front Psychiatry, 2023, 14: 1219479.
[24] QIU S, MILLER M I, JOSHI P S, et al. Multimodal deep learning for Alzheimer’s disease dementia assessment[J]. Nat Commun, 2022, 13(1): 3404.
[25] GARCÍA-COLOMO A, LÓPEZ-SANZ D, STAM C J, et al. Minimum spanning tree analysis of unimpaired individuals at risk of Alzheimer’s disease[J]. Brain Commun, 2024, 6(5): fcae283.