视觉技术在慢性病患者负性情绪评估中的应用进展

doi:10.3761/j.issn.0254-1769.2025.05.019

摘要/Abstract

摘要：

慢性病患者常伴有焦虑、抑郁等负性情绪，精准评估患者的负性情绪对制订有效的护理计划和干预措施尤为重要。传统的负性情绪评估存在主观、可及性限制等问题，难以做到精准的识别和评估。近年来，视觉技术因其准确、快速、实时、客观等特点，在情绪识别方面具有独特优势。该研究从视觉技术的发展进程及相关方法、在慢性病患者负性情绪评估中的应用及效果、存在的问题等方面进行综述，并提出相关对策，以期为慢性病患者负性情绪的评估提供参考。

关键词: 视觉技术, 负性情绪, 慢性病, 综述, 护理

Abstract:

Chronic disease patients often experience negative emotions such as anxiety and depression，and the accurate assessment of these emotions is crucial for developing effective care plans and interventions. Traditional assessments of negative emotions are limited by subjectivity，error and accessibility issues，making precise identification and evaluation difficult. In recent years，vision technology has demonstrated unique advantages in emotion recognition due to its accuracy，speed，consistency，objectivity nature. This paper reviews the development process of computer vision technology，the content and effects of its application in negative emotion assessment for chronic disease patients，and the current challenges，in order to provide references for the evaluation of chronic disease patients’ negative emotions.

Key words: Vision Technology, Negative Emotion, Chronic Disease, Review, Nursing Care

伍慧霞, 成彗芳, 黄珊珊, 黄远思, 刘翔宇. 视觉技术在慢性病患者负性情绪评估中的应用进展[J]. 中华护理杂志, 2025, 60(5): 635-641.

WU Huixia, CHENG Huifang, HUANG Shanshan, HUANG Yuansi, LIU Xiangyu. Research progress on application of vision technology in negative emotion assessment for chronic disease patients[J]. Chinese Journal of Nursing, 2025, 60(5): 635-641.

参考文献 47

[1]	杨宁, 王欣然. 信息化技术在重症患者负性情绪调节中的研究进展[J]. 中国护理管理, 2024, 24(6):934-937.
	Yang N, Wang XR. Research progress on information techno-logy in the regulation of negative emotion in critical patients[J]. Chin Nurs Manag, 2024, 24(6):934-937.
[2]	张华果, 司文腾, 何宇迪, 等. 老年髋部骨折术后患者跌倒恐惧心理体验的质性研究[J]. 中华护理杂志, 2021, 56(4):527-533. DOI URL
	Zhang HG, Si WT, He YD, et al. Experiences of fear of falling in elderly patients following hip fracture surgery:a qualitative descriptive study[J]. Chin J Nurs, 2021, 56(4):527-533.
[3]	周小莉, 杨孟叶, 钱嘉璐, 等. 胎儿异常引产产妇产褥期心理体验的质性研究[J]. 中华护理杂志, 2019, 54(9):1359-1363. DOI URL
	Zhou XL, Yang MY, Qian JL, et al. Women’s experiences of termination of pregnancy for a fetal anomaly during the postpartum period:a qualitative study[J]. Chin J Nurs, 2019, 54(9):1359-1363.
[4]	刘松柏, 马临庆, 秦芳英, 等. 老年慢性病患者焦虑抑郁情况及影响因素的调查分析[J]. 国际精神病学杂志, 2024,51(1):143-146.
	Liu SB, Ma LQ, Qin FY, et al. Investigation and analysis of anxiety and depression in elderly chronic disease patients and its influencing factors[J]. J Int Psychiatry,2024,51(1):143-146.
[5]	Gu ZH, Qiu T, Yang SH, et al. A study on the psychological factors affecting the quality of life among ovarian cancer patients in China[J]. Cancer Manag Res, 2020,12:905-912.
[6]	Yang J, Xie QY, Chen B, et al. Screening for negative emotions and analysis of related factors among general surgery inpatients:a retrospective cross-sectional study[J]. Front Psychol, 2024, 15:1343164.
[7]	马宁, 陈润滋, 张五芳, 等. 2020年中国精神卫生资源状况分析[J]. 中华精神科杂志, 2022, 55(6):459-468.
	Ma N, Chen RZ, Zhang WF, et al. The mental health resources in Chinese mainland by 2020[J]. Chin J Psychiatry, 2022, 55(6):459-468.
[8]	Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare[J]. Nat Med, 2019, 25(1):24-29. DOI PMID
[9]	科技部, 教育部, 工业和信息化部, 等. 《关于加快场景创新以人工智能高水平应用促进经济高质量发展的指导意见》[J]. 机器人技术与应用, 2022(5):2.
	Ministry of Science and Technology,Ministry of Education, Ministry of Industry and Information Technology, et al. Guiding opinions on accelerating scenario innovation and promoting high-quality economic development through high-level appli-cation of artificial intelligence[J]. Rob Tech App, 2022(5):2.
[10]	Yang JY, Wang C, Xiang J, et al. Oral CT image processing based on oral CT image filtering algorithm[J]. Comput Intell Neurosci, 2022,2022:6041872.
[11]	Chen Z, Zhang CH, Li Z, et al. Automatic segmentation of ova-rian follicles using deep neural network combined with edge information[J]. Front Reprod Health, 2022,4:877216.
[12]	Pampouchidou A, Simos PG, Marias K, et al. Automatic assess-ment of depression based on visual cues:a systematic review[J]. IEEE Trans Affect Comput, 2019, 10(4):445-470.
[13]	Mehrabian A, Ferris SR. Inference of attitudes from nonverbal communication in two channels[J]. J Consult Psychol, 1967, 31(3):248-252. PMID
[14]	袁钦湄, 杨峘, 张骏, 等. 基于深度学习算法的抑郁症表情与动作及其心理整合变化的过程分析[J]. 中国临床心理学杂志, 2023, 31(1):241-245,217.
	Yuan QM, Yang H, Zhang J, et al. Analysis of facial expres-sions and movements based on deep learning and inner emotional experiences on a patient with depression[J]. Chin J Clin Psychol, 2023, 31(1):241-245,217.
[15]	Chen LY, Ma XT, Zhu N, et al. Facial expression recognition with machine learning and assessment of distress in patients with cancer[J]. Oncol Nurs Forum, 2021, 48(1):81-93. DOI PMID
[16]	Zhou Y, Han W, Yao XY, et al. Developing a machine learn-ing model for detecting depression,anxiety,and apathy in older adults with mild cognitive impairment using speech and facial expressions:a cross-sectional observational study[J]. Int J Nurs Stud, 2023,146:104562.
[17]	Gavrilescu M, Vizireanu N. Predicting depression,anxiety,and stress levels from videos using the facial action coding system[J]. Sensors, 2019, 19(17):3693.
[18]	周滢. 老年轻度认知障碍患者情绪问题多模态特征融合分类模型的构建与评价研究[D]. 北京: 北京协和医学院, 2022.
	Zhou Y. Construction and evaluation of multi-modal feature fusion classification model for emotional problems of elderly patients with mild cognitive impairment[D]. Beijing: Peking Union Medical College, 2022.
[19]	成思哲, 冯博, 王胤丞, 等. 焦虑障碍高危人群自陈式问卷作答的眼动特征分析[J]. 空军军医大学学报, 2022, 43(2):136-140.
	Cheng SZ, Feng B, Wang YC, et al. Analysis on eye move-ment characteristics of high-risk group of anxiety disorders when answering self-reported questionnaire[J]. J Air Forc Med Unive, 2022, 43(2):136-140.
[20]	Zhang D, Liu X, Xu LH, et al. Effective differentiation bet-ween depressed patients and controls using discriminative eye movement features[J]. J Affect Disord, 2022,307:237-243.
[21]	Li M, Cao L, Zhai Q, et al. Method of depression classification based on behavioral and physiological signals of eye move-ment[J]. Complexity, 2020,2020:4174857.
[22]	付心仪, 薛程, 李希, 等. 基于姿态的情感计算综述[J]. 计算机辅助设计与图形学学报, 2020, 32(7):1052-1061.
	Fu XY, Xue C, Li X, et al. A review of body gesture based affective computing[J]. J Comput-Aid Des Comput Grap, 2020, 32(7):1052-1061.
[23]	Aviezer H, Trope Y, Todorov A. Body cues,not facial expres-sions,discriminate between intense positive and negative emotions[J]. Science, 2012, 338(6111):1225-1229. DOI PMID
[24]	Dehcheshmeh TF, Majelan AS, Maleki B. Correlation between depression and posture(a systematic review)[J]. Curr Psychol, 2024, 43(33):27251-27261.
[25]	Richer R, Koch V, Abel L, et al. Machine learning-based detec- tion of acute psychosocial stress from body posture and move-ments[J]. Sci Rep, 2024, 14(1):8251.
[26]	侯峰, 张明, 蔺向彬, 等. 基于行为与事件相关电位的机器学习重度抑郁识别研究[J]. 中国生物医学工程学报, 2023, 42(5):542-553.
	Hou F, Zhang M, Lin XB, et al. Recognition of major de-pression using machine learning methods based on behavioral and event-related potentials[J]. Chin J Biomed Eng, 2023, 42(5):542-553.
[27]	Horigome T, Sumali B, Kitazawa M, et al. Evaluating the seve-rity of depressive symptoms using upper body motion captu-red by RGB-depth sensors and machine learning in a clinical interview setting:a preliminary study[J]. Compr Psy-chiatry, 2020,98:152169.
[28]	Smrke U, Mlakar I, Lin S, et al. Language,speech,and facial expression features for artificial intelligence-based detection of cancer survivors’ depression:scoping meta-review[J]. JMIR Ment Health, 2021, 8(12):e30439.
[29]	Argolo F, Magnavita G, Mota NB, et al. Lowering costs for large-scale screening in psychosis:a systematic review and meta-analysis of performance and value of information for speech-based psychiatric evaluation[J]. Braz J Psychiatry, 2020, 42(6):673-686.
[30]	李志营, 纪俊, 周书喆, 等. 基于深度学习语音分析的双相障碍患者情绪时相检测[J]. 中华精神科杂志, 2024, 57(4):207-212.
	Li ZY, Ji J, Zhou SZ, et al. Emotional time-based detection of patients with bipolar disorder based on deep learning speech analysis[J]. Chin J Psychiatry, 2024, 57(4):207-212.
[31]	黄祥胜, 廖义龙, 张文劲, 等. 基于语音预训练模型的抑郁症识别研究[J]. 生物医学工程学杂志, 2024, 41(1):9-16.
	Huang XS, Liao YL, Zhang WJ, et al. A research on depres-sion recognition based on voice pre-training model[J]. J Bio-med Eng, 2024, 41(1):9-16.
[32]	Faurholt-Jepsen M, Rohani DA, Busk J, et al. Voice analyses using smartphone-based data in patients with bipolar disor-der,unaffected relatives and healthy control individuals,and during different affective states[J]. Int J Bipolar Disord, 2021, 9(1):38. DOI PMID
[33]	Le Glaz A, Haralambous Y, Kim-Dufor DH, et al. Machine learn-ing and natural language processing in mental health:systematic review[J]. J Med Internet Res, 2021,23(5):e15708.
[34]	Masukawa K, Aoyama M, Yokota S, et al. Machine learning models to detect social distress,spiritual pain,and severe physical psychological symptoms in terminally ill patients with cancer from unstructured text data in electronic medical records[J]. Palliat Med,2022, 36(8):1207-1216.
[35]	Koleck TA, Topaz M, Tatonetti NP, et al. Characterizing shared and distinct symptom clusters in common chronic conditions through natural language processing of nursing notes[J]. Res Nurs Health, 2021, 44(6):906-919. DOI PMID
[36]	Dobbs MF, McGowan A, Selloni A, et al. Linguistic correlates of suicidal ideation in youth at clinical high-risk for psychosis[J]. Schizophr Res, 2023,259:20-27.
[37]	Glauser T, Santel D, DelBello M, et al. Identifying epilepsy psy-chiatric comorbidities with machine learning[J]. Acta Neurol Scand, 2020, 141(5):388-396. DOI PMID
[38]	Li I, Pan J, Goldwasser J, et al. Neural natural language pro-cessing for unstructured data in electronic health records:a review[J]. Comput Sci Rev, 2022,46:100511.
[39]	Anders C, Arnrich B. Wearable electroencephalography and multi-modal mental state classification:a systematic literature review[J]. Comput Biol Med, 2022,150:106088.
[40]	Zhang JH, Yin Z, Chen P, et al. Emotion recognition using multi-modal data and machine learning techniques:a tutorial and review[J]. Inf Fusion, 2020,59:103-126.
[41]	Stolicyn A, Steele JD, Seriès P. Prediction of depression sym-ptoms in individual subjects with face and eye movement tracking[J]. Psychol Med, 2022, 52(9):1784-1792.
[42]	de Hond A, van Buchem M, Fanconi C, et al. Predicting depres-sion risk in patients with cancer using multimodal data[J]. Stud Health Technol Inform, 2023,302:817-818.
[43]	Mutawa AM, Hassouneh A. Multimodal real-time patient emotion recognition system using facial expressions and brain EEG signals based on machine learning and log-sync methods[J]. Biomed Signal Process Contr, 2024,91:105942.
[44]	王东煜. 基于语音和面部图像融合的抑郁识别研究[D]. 兰州: 兰州大学, 2021.
	Wang DY. Research on depression recognition based on speech and facial image fusion[D]. Lanzhou: Lanzhou University,2021.
[45]	Xie WQ, Wang C, Lin ZX, et al. Multimodal fusion diagnosis of depression and anxiety based on CNN-LSTM model[J]. Comput Med Imaging Graph,2022,102:102128.
[46]	栾琳琳, 丁敏, 卢振玲, 等. 虚拟现实技术在ICU危重症患者中的应用进展[J]. 中华护理杂志, 2021, 56(8):1255-1260. DOI URL
	Luan LL, Ding M, Lu ZL, et al. Application progress of virtual reality technology in ICU critically ill patients[J]. Chin J Nurs, 2021, 56(8):1255-1260. DOI URL
[47]	陈利, 杨又. 区块链技术在临床护理中的应用进展[J]. 中华护理杂志, 2024, 59(2):250-256. DOI URL
	Chen L, Yang Y. Research progress of blockchain technology in clinical nursing[J]. Chin J Nurs, 2024, 59(2):250-256. DOI URL