数字表型在双相情感障碍患者复发预警中应用的范围综述

doi:10.3761/j.issn.0254-1769.2026.12.017

摘要/Abstract

摘要：

目的对数字表型在双相情感障碍患者复发预警中的应用研究进行范围综述，为未来研究和临床应用提供参考。方法以澳大利亚乔安娜布里格斯循证卫生保健中心范围综述方法学框架为指导，系统检索PubMed、Embase、CINAHL、Scopus、Web of Science、Cochrane Library、中国知网、万方数据库、维普数据库、中国生物医学文献数据库，检索时限为建库至2025年10月16日，并对数字表型在双相情感障碍患者复发预警中应用的相关文献进行整合分析。结果共纳入17篇文献。数字表型主要依托智能手机与可穿戴活动追踪设备，采用主动报告与被动传感相结合的混合数据采集模式，收集患者的行为活动、睡眠与昼夜节律、生理信号、语音声学特征、通信与社交模式、情绪自评、环境光照等多维数据；预警触发方式包括持续性行为偏离警报、高风险概率警报和综合健康指数警报。部分研究报告了较高的预测性能指标与临床预警提前期。结论数字表型在双相情感障碍患者复发预警中具有应用潜力，可实现早期、客观的复发风险识别，未来需推动数字表型与护理工作的实用化整合，开展以患者结局为导向的研究。

关键词: 数字表型, 双相情感障碍, 复发预警, 范围综述, 护理

Abstract:

Objective To conduct a scoping review of the application of digital phenotyping in the early warning of relapse in patients with bipolar disorder，and to provide a reference for future research and clinical application. Methods Guided by the Joanna Briggs Institute methodological framework for scoping reviews，a systematic search was performed in PubMed，Embase，CINAHL，Scopus，Web of Science，Cochrane Library，CNKI，Wanfang Database，VIP Database，and CBM from their inception to October 16，2025. The included literature was integrated and analyzed. Results A total of 17 articles were included. Digital phenotyping primarily relies on smartphones and wearable activity tracking devices，employing a hybrid data collection model that collects patients’ behavioral activities，sleep and circadian rhythms，physiological signals，speech acoustic features，communication and social patterns，self-rated emotions，and ambient lighting. Warning triggers include alerts for persistent behavioral deviations，high-risk probability alerts，and composite health index alerts. Some studies reported higher prediction performance indicators and clinical warning periods. Conclusion Digital phenotyping shows potential for application in the early warning of recurrence in patients with bipolar disorder，enabling early and objective identification of recurrence risk. In the future，it is necessary to promote the practical integration of digital phenotyping with nursing work and conduct patient outcome-oriented research.

Key words: Digital Phenotype, Bipolar Disorder, Recurrence Warning, Scoping Review, Nursing Care

刘志萍, 张梦婷, 王菊子, 贺敏, 吴义凡, 侯永超. 数字表型在双相情感障碍患者复发预警中应用的范围综述[J]. 中华护理杂志, 2026, 61(12): 1710-1716.

LIU Zhiping, ZHANG Mengting, WANG Juzi, HE Min, WU Yifan, HOU Yongchao. The application of digital phenotyping in the warning of recurrence for patients with bipolar disorder：a scoping review[J]. Chinese Journal of Nursing, 2026, 61(12): 1710-1716.

图/表 1

参考文献 32

[1]	世界卫生组织. ICD-11精神、行为和神经发育障碍临床描述与诊断指南[M]. 北京: 人民卫生出版社, 2024.
	World Health Organization. ICD-11 clinical descriptions and diagnostic guidelines for mental,behavioral and neurodevelo-pmental disorders[M]. Beijing: People’s Medical Publishing House, 2024.
[2]	Park DY, Do D, Chang L, et al. Episode accumulation associated with hastened recurrence and delayed recovery in bipolar disorder[J]. J Affect Disord, 2018, 227:657-664. DOI URL
[3]	Davidson BI. The crossroads of digital phenotyping[J]. Gen Hosp Psychiatry, 2022, 74:126-132. DOI URL
[4]	Bufano P, Laurino M, Said S, et al. Digital phenotyping for mo-nitoring mental disorders:systematic review[J]. J Med Internet Res, 2023, 25:e46778. DOI URL
[5]	Zhong RR, Wu XH, Chen J, et al. Using digital phenotyping to discriminate unipolar depression and bipolar disorder:systematic review[J]. J Med Internet Res, 2025, 27:e72229. DOI URL
[6]	Peters MDJ, Marnie C, Tricco AC, et al. Updated methodological guidance for the conduct of scoping reviews[J]. JBI Evid Synth, 2020, 18(10):2119-2126. DOI PMID
[7]	仇如霞, 顾艳荭. 范围综述报告规范(PRISMA-ScR)的解读[J]. 中国循证医学杂志, 2022, 22(6):722-730.
	Qiu RX, Gu YH. Interpretation of the PRISMA extension for scoping review(PRISMA-ScR)[J]. Chin J Evid Based Med, 2022, 22(6):722-730.
[8]	Ludwig VM, Bittendorf CA, Reinhard I, et al. Early warning signals of bipolar relapse:investigating critical slowing down in smartphone data[J]. J Affect Disord, 2025, 391:119972. DOI URL
[9]	Lipschitz JM, Lin SD, Saghafian S, et al. Digital phenotyping in bipolar disorder:using longitudinal Fitbit data and personalized machine learning to predict mood symptomatology[J]. Acta Psy-chiatr Scand, 2025, 151(3):434-447.
[10]	Kaczmarek-Majer K, Dominiak M, Antosik AZ, et al. Acoustic features from speech as markers of depressive and manic symptoms in bipolar disorder:a prospective study[J]. Acta Psy-chiatr Scand, 2025, 151(3):358-374.
[11]	Wu CT, Hsieh MH, Chen IM, et al. Using wearable device and machine learning to predict mood symptoms in bipolar disorder:development and usability study[J]. JMIR Med Inform, 2025, 13:e66277. DOI URL
[12]	Ludwig VM, Bittendorf CA, Reinhard I, et al. Predicting depressive and manic episodes in patients with bipolar disorder using statistical process control methods on passive sensing data[J]. J Psychopathol Clin Sci, 2025, 134(8):971-981. DOI URL
[13]	Ortiz A, Halabi R, Alda M, et al. Day-to-day variability in activity levels detects transitions to depressive symptoms in bipolar disorder earlier than changes in sleep and mood[J]. Int J Bipolar Disord, 2025, 13(1):13. DOI PMID
[14]	Lim D, Jeong J, Song YM, et al. Accurately predicting mood episodes in mood disorder patients using wearable sleep and circadian rhythm features[J]. NPJ Digit Med, 2024, 7(1):324. DOI PMID
[15]	Jakobsen P, Côté-Allard U, Riegler MA, et al. Early warning signals observed in motor activity preceding mood state change in bipolar disorder[J]. Bipolar Disord, 2024, 26(5):468-478. DOI PMID
[16]	Hsu JH, Wu CH, Lin EC, et al. MoodSensing:a smartphone APP for digital phenotyping and assessment of bipolar disorder[J]. Psychiatry Res, 2024, 334:115790. DOI URL
[17]	Sokół-Szawłowska M, Kamińska O, Sochacka M. MoodMon:novel optimization of bipolar disorder monitoring through patient-driven voice parameter submission and AI technology[J]. Pos-tep Psychiatr Neurol, 2024, 33(4):230-240.
[18]	Liu QM, Ning E, Ross MK, et al. Digital phenotypes of mobile keyboard backspace rates and their associations with symptoms of mood disorder:algorithm development and validation[J]. J Med Internet Res, 2024, 26:e51269. DOI URL
[19]	Lee HJ, Cho CH, Lee T, et al. Prediction of impending mood episode recurrence using real-time digital phenotypes in major depression and bipolar disorders in South Korea:a pros-pective nationwide cohort study[J]. Psychol Med, 2023, 53(12):5636-5644. DOI URL
[20]	Hsu JH, Tseng HW, Wu CH, et al. Temporal and type corre-lation in digital phenotyping for bipolar disorder state prediction using multitask self-supervised learning[C]// 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference(APSIPA ASC). October 31- November 3,2023,Taipei,China. IEEE, 2023:2189-2195.
[21]	Dominiak M, Kaczmarek-Majer K, Antosik-Wójcińska AZ, et al. Behavioral and self-reported data collected from smart-phones for the assessment of depressive and manic symptoms in patients with bipolar disorder:prospective observational study[J]. J Med Internet Res, 2022, 24(1):e28647. DOI URL
[22]	Bennett CC, Ross MK, Baek E, et al. Predicting clinically rele-vant changes in bipolar disorder outside the clinic walls based on pervasive technology interactions via smartphone typing dynamics[J]. Pervasive Mob Comput, 2022, 83:101598. DOI URL
[23]	Kunkels YK, Riese H, Knapen SE, et al. Efficacy of early warning signals and spectral periodicity for predicting transi-tions in bipolar patients:an actigraphy study[J]. Transl Psychia-try, 2021, 11(1):350.
[24]	Cho CH, Lee T, Lee JB, et al. Effectiveness of a smartphone APP with a wearable activity tracker in preventing the recur-rence of mood disorders:prospective case-control study[J]. JMIR Ment Health, 2020, 7(8):e21283. DOI URL
[25]	刘国庆, 王月, 韩婧怡, 等. 移动健康技术在精神障碍患者管理中的应用进展[J]. 中华护理杂志, 2022, 57(11):1324-1329. DOI
	Liu GQ, Wang Y, Han JY, et al. Application progress of mo-bile health technology in the management of patients with mental disorders[J]. Chin J Nurs, 2022, 57(11):1324-1329.
[26]	Zhang YB, Wang J, Zong H, et al. The comprehensive clinical benefits of digital phenotyping:from broad adoption to full impact[J]. NPJ Digit Med, 2025, 8(1):196. DOI
[27]	Dlima SD, Shevade S, Menezes SR, et al. Digital phenotyping in health using machine learning approaches:scoping review[J]. JMIR Bioinform Biotechnol, 2022, 3(1):e39618. DOI URL
[28]	吴韬, 方媛媛, 钱瑞莲. 共享决策在严重精神障碍患者中的应用进展[J]. 中华护理杂志, 2022, 57(18):2205-2211.
	Wu T, Fang YY, Qian RL. Application progress of shared de-cision-making for patients with severe mental disorders[J]. Chin J Nurs, 2022, 57(18):2205-2211.
[29]	Geoffroy PA, Maruani J. Chronobiology of mood disorders:the role of the biological clock in depression and bipolar disor-der[J]. Biol Psychiatry, 2025, 98(11):830-841. DOI URL
[30]	Ehlers CL, Frank E, Kupfer DJ. Social zeitgebers and biological rhythms. A unified approach to understanding the etiology of depression[J]. Arch Gen Psychiatry, 1988, 45(10):948-952. DOI PMID
[31]	Oudin A, Maatoug R, Bourla A, et al. Digital phenotyping:data-driven psychiatry to redefine mental health[J]. J Med Internet Res, 2023, 25:e44502. DOI URL
[32]	柏新蕊, 张红燕, 安宁, 等. 价值共创视角下数字赋能护理质量管理的研究进展[J]. 中华护理杂志, 2025, 60(3):379-384.
	Bai XR, Zhang HY, An N, et al. Research progress on nursing quality management empowered by digital technology from the perspective of value co-creation[J]. Chin J Nurs, 2025, 60(3):379-384.