背景：心臟衰竭為全球重要的慢性疾病之一，病人常伴隨焦慮、憂鬱等負向情緒，尤其在加護病房等高壓環境中更為明顯，可能對病人造成身心壓力與心理困擾，導致高死亡率與再住院率。臨床上常以 NT-pro BNP、MAGGIC 風險評估與住院天數等作為病情與預後的指標。然而，現行多仰賴主觀量表，較少應用即時、客觀的情緒與生理監測，亦缺乏整合臉部情緒、生理與身心健康之相關探討。
研究目的：探討心臟衰竭病人的臉部表情類型（FD）與生理功能、身心健康指標之關聯性，在控制人口學與疾病變項下檢視FD對各項身心健康指標之解釋力。
研究方法：本研究採橫斷式設計，以30位心臟內科加護病房心衰病人為樣本，收集4小時臉部影像及生理參數變化，每秒截取一幀畫面，共計432000幀，運用 OpenFace系統辨識每幀出現的各類臉部動作單元(AUs），個別AU的出現頻率和表現強度，再以階層式聚類分析法（Hierarchical Cluster Analysis，HCA），找出協同出現程度在中、強度以上的臉部表情類型，共有三項(FD1-FD3)，以多元迴歸模型分別檢視此三項臉部表情對其身心健康指標的影響程度。
研究結果：以GEE分析，在控制共變項後發現: 臉部表情類型FD1（害怕厭煩）分別與血氧值、NT-pro BNP、MAGGIC 與住院天數之間呈現正關聯；FD2（傷心訝異）與 MAGGIC 呈正相關；FD3（喜惡參半）則分別與心率、收縮壓、 NT-pro BNP 與 MAGGIC 呈負相關。在逐步回歸分析中，以 NT-pro BNP 為依變項的模型中，FD1（害怕厭煩）、呼吸速率與FD3（喜惡參半）為重要影響因子，具有32.7%的解釋變異量，其中FD1為第一影響因子，可解釋模型中約14%變異量；在以 MAGGIC 為依變項的模型中，控制年齡後，FD1 可單獨解釋約10%的變異。
結論：本前驅研究發現特定臉部表情類型與心臟衰竭病人在加護病房中的心臟功能指標有高度相關。其中，FD1（害怕厭煩）是 NT-pro BNP、MAGGIC 的重要預測因子，具有10-14% 的影響解釋力。綜合而言，本研究整合臉部表情辨識技術、生理參數與臨床指標，建構一套即時且非侵入性的情緒—生理—病情評估模式，提供智慧照護與個別化臨床監測之實證參考。未來可據此結果，開發臉部FD1（害怕厭煩）辨識模型，以作為CHF疾病嚴重度變化的生物特徵指標。

Heart failure (HF) patients in the ICU often face severe psychological distress, negatively impacting their prognosis (NT-pro BNP, MAGGIC score, length of stay). Current subjective assessments lack real-time objectivity. This cross-sectional study analyzed the relationship between objective facial display types (FDs), physiological parameters, and these biopsychosocial health indicators. We collected four hours of continuous facial video (432,000 frames) and physiological data from 30 cardiac ICU patients. OpenFace was used to analyze Action Units (AUs) and Hierarchical Cluster Analysis (HCA) identified three FD types (FD1–FD3). Multivariate regression examined the FDs' explanatory power on health indicators. GEE and regression analyses showed that FD1 (Fearfully Disgusted) was significantly and positively associated with SpO2, NT-pro BNP, MAGGIC score, and hospital stay. FD1 was the strongest predictor for NT-pro BNP and MAGGIC score, explaining 10–14% of the variance. FD3 (Happily Disgusted) showed negative associations with HR, SBP, NT-pro BNP, and MAGGIC. This research validates a real-time, non-invasive emotion-physiology assessment model, positioning FD1 as a valuable biometric indicator for monitoring HF severity.

Canal, F. Z., Müller, T. R., Matias, J. C., Scotton, G. G., de Sa Junior, A. R., Pozzebon, E., & Sobieranski, A. C. (2022). A survey on facial emotion recognition techniques: A state-of-the-art literature review. Information Sciences, 582, 593-617.
Chang, H. Y., Lin, M. Y., & Kuo, C. L. (2024). The RAM index: A novel prognostic tool to predict mortality in acute heart failure patients in the emergency department. Journal of Emergency and Critical Care Medicine, 8(1), 15–23.
Chavanon, M. L., Meyer, T., Belnap, B. H., Huang, Y., Abebe, K. Z., Rollman, B. L., & Herrmann-Lingen, C. (2019). Emotion regulation in patients with heart failure: Its relationship with depressive symptoms and rehospitalization. Journal of psychosomatic research, 125, 109811. https://doi.org/10.1016/j.jpsychores.2019.109811
Chung, M. L., Moser, D. K., Lennie, T. A., & Rayens, M. K. (2021). The effect of depressive symptoms on quality of life in patients with heart failure. European Journal of Cardiovascular Nursing, 20(3), 251–259. https://doi.org/10.1177/1474515120924398
Cîrneanu, A.-L., Popescu, D., & Iordache, D. (2023). New trends in emotion recognition using image analysis by neural networks: A systematic review. Sensors, 23(16), 7092. https://doi.org/10.3390/s23167092
Cramer, J. P., Hettiarachchi, N., Brecknell, B., Liu, X., Knight, S. R., & Lu, H. (2025). Quantifying facial clues of acute illness: A scoping review. Frontiers in Medicine, 12, 1153275. https://doi.org/10.3389/fmed.2023.1153275
Demaree, H. A., Schmeichel, B. J., Robinson, J. L., Pu, J., Everhart, D. E., & Berntson, G. G. (2006). Up-and down-regulating facial disgust: Affective, vagal, sympathetic, and respiratory consequences. Biological psychology, 71(1), 90-99.
Dokoupil, P., Kramarz, E., & Małyszko, J. (2022). New perspectives in heart failure management: A review. Cardiology Journal, 29(1), 1–11. https://doi.org/10.5603/CJ.a2022.0001
Dong, Z., Wang, G., Lu, S., Li, J., Yan, W., & Wang, S.-J. (2022). Spontaneous facial expressions and micro-expressions coding: From brain to face. Frontiers in Psychology, 12, 784834. https://doi.org/10.3389/fpsyg.2021.784834
Dubey, M., & Singh, L. (2016). Automatic emotion recognition using facial expression: a review. International Research Journal of Engineering and Technology (IRJET), 3(2), 488-492.
Ekman, P., & Friesen, W. V. (1978). Facial Action Coding System: A technique for the measurement of facial movement. Consulting Psychologists Press.
Ekman, P., Friesen, W. V., & Hager, J. C. (2002). Facial Action Coding System (FACS): Manual. Salt Lake City: A Human Face.
Fugate, J. M. B., & Franco, C. L. (2021). Implications for emotion: Using anatomically based facial coding to compare emoji faces across platforms. Frontiers in Psychology, 12, 605928. https://doi.org/10.3389/fpsyg.2021.605928
Gaffey, A. E., Gathright, E. C., Fletcher, L. M., & Goldstein, C. M. (2023). Screening for psychological distress and risk of cardiovascular disease and related mortality: A systematized review, meta-analysis, and case for prevention. Journal of Cardiopulmonary Rehabilitation and Prevention, 42(6), 404–415. https://doi.org/10.1097/HCR.0000000000000751
Gathright, E. C., et al. (2016). Depression and health outcomes in patients with heart failure: A meta-analytic review. Journal of Psychosomatic Research, 81, 68–73. https://doi.org/10.1016/j.jpsychores.2015.12.006
Gathright, E. C., et al. (2016). Depression in heart failure: Can we accurately diagnose and treat it? Current Heart Failure Reports, 13(1), 10–18. https://doi.org/10.1007/s11897-016-0276-1
Gezginci, E., Arikan Donmez, A., & Konukbay, D. (2022). The effects of intensive care unit environment stress on anxiety and depression. Intensive and Critical Care Nursing, 68, 103133. https://doi.org/10.1016/j.iccn.2021.103133
Guzzetti, S., Dassi, S., Pecis, M., Casati, R., Cerutti, S., & Malliani, A. (2001). Heart rate variability in chronic heart failure. Autonomic Neuroscience: Basic and Clinical, 90(1–2), 102–105. https://doi.org/10.1016/S1566-0702(01)00268-4
Immanuel, S., Teferra, M. N., Baumert, M., & Bidargaddi, N. (2023). Heart rate variability for evaluating psychological stress changes in healthy adults: A scoping review. Neuropsychobiology, 82(4), 187–202. https://doi.org/10.1159/000530376
Jauniaux, C., et al. (2020). Emotional modulation of heart rate variability: Exploring autonomic flexibility. Psychophysiology, 57(7), e13526. https://doi.org/10.1111/psyp.13526
Jauniaux, J., Waterschoot, J., Heeren, A., Timary, P. D., & Billieux, J. (2020). Emotion regulation of others’ positive and negative emotions is related to distinct patterns of heart rate variability and empathic traits. PLOS ONE, 15(12), e0244427. https://doi.org/10.1371/journal.pone.0244427
Johansson, P., Andersson, G., Jaarsma, T., Lundgren, J., Westas, M., & Mourad, G.(2021). Psychological distress in patients with cardiovascular disease: Time to do something about it? European Journal of Cardiovascular Nursing, 20(4), 293–294. https://doi.org/10.1093/eurjcn/zvab007
Kim, S. E., Cho, D. H., Son, J. W., Kim, J. Y., Kang, S. M., Cho, M. C., … Yoo, B. S. (2022). Impact of NT-proBNP on prognosis of acute decompensated chronic heart failure versus de novo heart failure. International Journal of Cardiology, 363, 163–170. https://doi.org/10.1016/j.ijcard.2022.10.030
Kok, B. E., & Fredrickson, B. L. (2013). Positive emotions and vagal tone: Evidence for the upward spiral theory of positive emotions and health. Psychological Science, 24(7), 1123–1132. https://doi.org/10.1177/0956797612470827
López-Vilella, R., Marqués-Sulé, E., Sánchez-Lázaro, I., Laymito Quispe, R., Martinez Dolz, L., & Almenar Bonet, L. (2021). Creatinine and NT-proBNP levels could predict the length of hospital stay of patients with decompensated heart failure. Acta Cardiologica, 76(10), 1100–1107. https://doi.org/10.1080/00015385.2021.1880597
Miki, K., et al. (2016). Heart rate variability in chronic heart failure: Nonlinear and spectral analysis approaches. Biological Psychology, 117, 41–49. https://doi.org/10.1016/j.biopsycho.2016.02.001
Ministry of Health and Welfare, Taiwan. (2024). Statistics of causes of death. Retrieved from https://www.mohw.gov.tw
Feng, L. S., Wang, Y. M., Liu, H., Ning, B., Yu, H. B., Li, S. L., ... & Ma, J. (2024). Hyperactivity in the Hypothalamic-Pituitary-Adrenal Axis: An Invisible Killer for Anxiety and/or Depression in Coronary Artherosclerotic Heart Disease. Journal of Integrative Neuroscience, 23(12), 222.
Sobolewska-Nowak, J., Wachowska, K., Nowak, A., Orzechowska, A., Szulc, A., Płaza, O., & Gałecki, P. (2023). Exploring the heart–mind connection: unraveling the shared pathways between depression and cardiovascular diseases. Biomedicines, 11(7), 1903.Moses, J. C., Adibi, S., Angelova, M., & Islam, S. M. S. (2024). Time‐domain heart rate variability features for automatic congestive heart failure prediction. ESC Heart Failure, 11(1), 378-389
Nerella, S., Bihorac, A., Tighe, P., & Rashidi, P. (2024). Facial action unit detection on ICU data for pain assessment. Proceedings of the IEEE International Conference on Biomedical and Health Informatics (BHI). https://arxiv.org/abs/2403.00075
Nerella, S., Cupka, J., Ruppert, M., Tighe, P., Bihorac, A., & Rashidi, P. (2021, July). Pain action unit detection in critically ill patients. In *Proceedings of the 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC)* (pp. 645–651). IEEE. https://doi.org/10.1109/COMPSAC51774.2021.00102
Nogueira, M. (2017). Serum sodium levels and blood pressure monitoring in heart failure: Enhanced diagnostic and prognostic value. European Journal of Internal Medicine, 45, 38–42. https://doi.org/10.1016/j.ejim.2017.09.004
Osser, G., Osser, B., Toth, C., Miuța, C. C., Marconi, G. R., & Bondar, L. I. (2024). Exploring the relationship between ejection fraction, arterial stiffness, NT-proBNP, and hospitalization risk in heart failure patients. Diagnostics, 14(24), 2885. https://doi.org/10.3390/diagnostics14242885
Pocock, S. J., Ariti, C. A., McMurray, J. J. V., Maggioni, A., Køber, L., Squire, I. B., ... & Meta‐Analysis Global Group in Chronic Heart Failure (MAGGIC). (2013). Predicting survival in heart failure: a risk score based on 39,372 patients from 30 studies. European Heart Journal, 34(19), 1404–1413. https://doi.org/10.1093/eurheartj/ehs337
Radaelli, A., Bernardi, L., & Porta, A. (2023). Respiratory patterns and baroreflex function in heart failure. Journal of Applied Physiology, 134(5), 1156–1165. https://doi.org/10.1152/japplphysiol.00781.2022
Rashid, M., et al. (2023). Psychological distress and its relationship with outcomes in heart failure: A meta-analysis. European Heart Journal, 44(2), 129–137. https://doi.org/10.1093/eurheartj/ehac720
Rich, J. D., Burns, J., Freed, B. H., et al. (2018). Meta‐Analysis Global Group in Chronic Heart Failure risk score: Validation of a simple tool for the prediction of morbidity and mortality in heart failure with preserved ejection fraction. Journal of the American Heart Association, 7(18), e009529. https://doi.org/10.1161/JAHA.118.009529
Saltnes-Lillegård, H. J., Haugen, A. S., Flaatten, H., Lydersen, S., & Reitan, J. A. (2023). Patient self-reported symptoms in the ICU: A prospective observational multicenter study. Intensive and Critical Care Nursing, 73, 103352. https://doi.org/10.1016/j.iccn.2023.103352
Sawano, M., Kohsaka, S., Yoshikawa, T., et al. (2018). Performance of the MAGGIC risk score and its modification by adding brain natriuretic peptide in acute heart failure patients in Japan. ESC Heart Failure, 5(3), 407–415. https://doi.org/10.1002/ehf2.12261
Schiweck, C., Piette, D., Berckmans, D., Claes, S., & Vrieze, E. (2018). Heart rate and high-frequency heart rate variability during stress as biomarkers for clinical depression: A systematic review. Psychological Medicine, 49(2), 200–211. https://doi.org/10.1017/S0033291718001988
Shaffer, F., & Ginsberg, J. P. (2017). An overview of heart rate variability metrics and norms. Frontiers in Public Health, 5, 258. https://doi.org/10.3389/fpubh.2017.00258
Shdaifat, S. A., & Al Qadire, M. (2022). Anxiety and depression among patients admitted to intensive care. Nursing in Critical Care, 27(1), 106–112. https://doi.org/10.1111/nicc.12536​:contentReference[oaicite:0]{index=0}
Shukla, M., Lau, J. Y. F., Lissek, S., Pandey, R., & Kumari, V. (2020). Reduced emotional responsiveness in individuals with marginal elevation in blood pressure within the normal range: Evidence from altered affect-modulated startle response. International Journal of Psychophysiology, 153, 18–26. https://doi.org/10.1016/j.ijpsycho.2020.04.013
Siniorakis, E., Arvanitakis, S., & Kalaitzidis, R. (2018). Acute heart failure in the emergency department: Respiratory rate as a risk predictor. Hellenic Journal of Cardiology, 59(6), 365–372. https://doi.org/10.1016/j.hjc.2018.01.001
Sokoreli, I., de Vries, J. J. G. P., Pauws, S. C., & Steyerberg, E. W. (2016). Depression and anxiety as predictors of mortality among heart failure patients: Systematic review and meta-analysis. Heart Failure Reviews, 21(1), 49–63. https://doi.org/10.1007/s10741-015-9517-4
Taiwan Society of Cardiology. (2022). Heart Failure Clinical Practice Guidelines. Taipei: TSOC.
Tanenbaum, S. J., et al. (2016). Understanding care for depression in patients with chronic illness. Medical Care Research and Review, 73(2), 127–157. https://doi.org/10.1177/1077558715619246
Thayer, J. F., Åhs, F., Fredrikson, M., Sollers, J. J., & Wager, T. D. (2012). A meta-analysis of heart rate variability and neuroimaging studies: Implications for heart rate variability as a marker of stress and health. Neuroscience & Biobehavioral Reviews, 36(2), 747–756. https://doi.org/10.1016/j.neubiorev.2011.11.009
Tiwari, R., Kumar, R., Malik, S., Raj, T., & Kumar, P. (2021). Analysis of heart rate variability and implication of different factors on heart rate variability. Current Cardiology Reviews, 17(5), e160721189770. https://doi.org/10.2174/1573403X16999201231203854
Virani, S. S., et al. (2021). Heart disease and stroke statistics—2021 update: A report from the American Heart Association. Circulation, 143(8), e254–e743. https://doi.org/10.1161/CIR.0000000000000950
Wang, S., Zhu, R., Cai, H., Mao, J., Zhou, W., Zhang, C., Lv, M., Meng, H., & Guo, L. (2025). Prevalence and risk factors of depression and anxiety symptoms in intensive care unit patients with cardiovascular disease: A cross-sectional study. Journal of Clinical Nursing, 34(1), 139–150. https://doi.org/10.1111/jocn.17203
World Health Organization. (2023). Cardiovascular diseases (CVDs). Retrieved from https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)
Wu, C. L., Liu, S. F., Yu, T. L., Shih, S. J., Chang, C. H., Yang Mao, S. F., ... & Chao, W. C. (2022). Deep learning-based pain classifier based on the facial expression in critically ill patients. Frontiers in Medicine, 9, 851690.
Yu, J., & Lu, X. (2025). Compound Expression Recognition via Large Vision-Language Models. arXiv preprint arXiv:2503.11241.
Zigmond, A. S., & Snaith, R. P. (1983). The hospital anxiety and depression scale. Acta psychiatrica Scandinavica, 67(6), 361–370. https://doi.org/10.1111/j.1600-0447.1983.tb09716.x
林麗英、張玉珍、李美華、吳春枝（2017）。心臟加護病房病人壓力感受與生理指標變化之相關性探討。護理雜誌, 64(2), 57–66。