Predição de Níveis de Ansiedade Utilizando Dados de Smartwatches em Ambiente Não Controlado
Resumo
A ansiedade é um transtorno relacionado a alterações de inquietação e sono. Este estudo investiga dispositivos vestíveis para monitoramento contínuo em ambientes não controlados, utilizando aprendizado profundo. Foi avaliada uma rede LSTM para regressão dos níveis de ansiedade com dados de acelerômetro de 41 voluntários coletados por 24 horas. As pontuações foram obtidas pelo IDATE, com aumento de dados (20, 50 e 100 vezes). O melhor desempenho ocorreu com 50 (MAE: 6,04 treino; 5,30 validação). As correlações de Pearson foram 0,71 e 0,50, respectivamente. Os resultados indicam potencial para monitoramento contínuo e não invasivo da saúde mental.Referências
Alvaro, P. K., Roberts, R. M., and Harris, J. K. (2016). The bidirectional relationship between sleep and anxiety: Implications for treatment. Sleep Medicine Reviews, 28:1–12.
Bursa, S. Ö., Durmaz İncel, Ö., and Işıklar Alptekin, G. (2023). Building lightweight deep learning models with tensorflow lite for human activity recognition on mobile devices. Annals of Telecommunications, 78(11):687–702.
Duval, E. R., Javanbakht, A., and Liberzon, I. (2015). Neural circuits in anxiety and stress disorders: a focused review. Therapeutics and clinical risk management, pages 115–126.
Elkjær, E., Mikkelsen, M. B., Michalak, J., Mennin, D. S., and O’Toole, M. S. (2022a). Motor alterations in depression and anxiety disorders: A systematic review and meta-analysis. Journal of affective disorders, 317:373–387.
Elkjær, E., Mikkelsen, M. B., Michalak, J., Mennin, D. S., and O’Toole, M. S. (2022b). Motor alterations in depression and anxiety disorders: A systematic review and meta-analysis. Journal of affective disorders, 317:373–387.
Fang, L., Zeng, W., Zheng, S., Du, S., Yang, H., Luo, X., Zeng, S., Huang, Z., Chen, W., and Zhang, B. (2025). a. Depression and anxiety, 2025(1):3082856.
Franklin, A. R., Mathersul, D. C., Raine, A., and Ruscio, A. M. (2021a). Restlessness in generalized anxiety disorder: using actigraphy to measure physiological reactions to threat. Behavior therapy, 52(3):734–744.
Franklin, A. R., Mathersul, D. C., Raine, A., and Ruscio, A. M. (2021b). Restlessness in generalized anxiety disorder: using actigraphy to measure physiological reactions to threat. Behavior therapy, 52(3):734–744.
Graves, A. (2012). Long short-term memory. Supervised sequence labelling with recurrent neural networks, pages 37–45.
Hamitouche, D., Zamorano, T., Barkat, Y., Parekh, D., Palaniyappan, L., Jalali, S., and Benrimoh, D. (2025). Sleep and activity patterns as transdiagnostic behavioral biomarkers in psychiatry: Longitudinal observational study from the deep-dd study. JMIR Form Res, 9.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436–444.
Liang, Q., Xu, Z., Chen, S., and Qiu, Y. (2026). Differential neural dynamics in psychomotor retardation and agitation of depression. Human Brain Mapping, 47(2):e70453.
Luca, M., Luca, A., Barlati, S., Buson, L., Menesello, V., Magistrali, A., Silva, R., Perusi, G., Nibbio, G., Bignotti, S., Tura, G., Ferri, R., Gennarelli, M., Vita, A., Souery, D., Kasper, S., Zohar, J., Montgomery, S., Ferentinos, P., and Spina, E. (2026). Agitation and anxiety features define a more severe phenotype in unipolar depression. Psychiatry Research, 357:116928.
Pastre, M. and Lopez-Castroman, J. (2022). Actigraphy monitoring in anxiety disorders: A mini-review of the literature. Frontiers in psychiatry, 13:984878.
Pompili, M., Ducci, G., Galluzzo, A., Rosso, G., Palumbo, C., and De Berardis, D. (2021). The management of psychomotor agitation associated with schizophrenia or bipolar disorder: a brief review. International journal of environmental research and public health, 18(8):4368.
Spielberger, C. and Gorsuch, R. (1983). Manual for the State-trait Anxiety Inventory (form Y) (”self-evaluation Questionnaire”). Consulting Psychologists Press.
Straus, L. D., An, X., Ji, Y., McLean, S. A., Neylan, T. C., Group, A. S., Cakmak, A. S., Richards, A., Clifford, G. D., Liu, M., et al. (2023). Utility of wrist-wearable data for assessing pain, sleep, and anxiety outcomes after traumatic stress exposure. JAMA psychiatry, 80(3):220–229.
Vincent, C. J., Aguilar-Alvarez, R., Vanderhoof, S. O., Mott, D. D., and Jasnow, A. M. (2025). An amygdala-cortical circuit for encoding generalized fear memories. Molecular Psychiatry, pages 1–14.
Wang, J., Chen, Y., Hao, S., Peng, X., and Hu, L. (2019). Deep learning for sensor-based human activity recognition: A survey. Sensors, 17:416.
Bursa, S. Ö., Durmaz İncel, Ö., and Işıklar Alptekin, G. (2023). Building lightweight deep learning models with tensorflow lite for human activity recognition on mobile devices. Annals of Telecommunications, 78(11):687–702.
Duval, E. R., Javanbakht, A., and Liberzon, I. (2015). Neural circuits in anxiety and stress disorders: a focused review. Therapeutics and clinical risk management, pages 115–126.
Elkjær, E., Mikkelsen, M. B., Michalak, J., Mennin, D. S., and O’Toole, M. S. (2022a). Motor alterations in depression and anxiety disorders: A systematic review and meta-analysis. Journal of affective disorders, 317:373–387.
Elkjær, E., Mikkelsen, M. B., Michalak, J., Mennin, D. S., and O’Toole, M. S. (2022b). Motor alterations in depression and anxiety disorders: A systematic review and meta-analysis. Journal of affective disorders, 317:373–387.
Fang, L., Zeng, W., Zheng, S., Du, S., Yang, H., Luo, X., Zeng, S., Huang, Z., Chen, W., and Zhang, B. (2025). a. Depression and anxiety, 2025(1):3082856.
Franklin, A. R., Mathersul, D. C., Raine, A., and Ruscio, A. M. (2021a). Restlessness in generalized anxiety disorder: using actigraphy to measure physiological reactions to threat. Behavior therapy, 52(3):734–744.
Franklin, A. R., Mathersul, D. C., Raine, A., and Ruscio, A. M. (2021b). Restlessness in generalized anxiety disorder: using actigraphy to measure physiological reactions to threat. Behavior therapy, 52(3):734–744.
Graves, A. (2012). Long short-term memory. Supervised sequence labelling with recurrent neural networks, pages 37–45.
Hamitouche, D., Zamorano, T., Barkat, Y., Parekh, D., Palaniyappan, L., Jalali, S., and Benrimoh, D. (2025). Sleep and activity patterns as transdiagnostic behavioral biomarkers in psychiatry: Longitudinal observational study from the deep-dd study. JMIR Form Res, 9.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436–444.
Liang, Q., Xu, Z., Chen, S., and Qiu, Y. (2026). Differential neural dynamics in psychomotor retardation and agitation of depression. Human Brain Mapping, 47(2):e70453.
Luca, M., Luca, A., Barlati, S., Buson, L., Menesello, V., Magistrali, A., Silva, R., Perusi, G., Nibbio, G., Bignotti, S., Tura, G., Ferri, R., Gennarelli, M., Vita, A., Souery, D., Kasper, S., Zohar, J., Montgomery, S., Ferentinos, P., and Spina, E. (2026). Agitation and anxiety features define a more severe phenotype in unipolar depression. Psychiatry Research, 357:116928.
Pastre, M. and Lopez-Castroman, J. (2022). Actigraphy monitoring in anxiety disorders: A mini-review of the literature. Frontiers in psychiatry, 13:984878.
Pompili, M., Ducci, G., Galluzzo, A., Rosso, G., Palumbo, C., and De Berardis, D. (2021). The management of psychomotor agitation associated with schizophrenia or bipolar disorder: a brief review. International journal of environmental research and public health, 18(8):4368.
Spielberger, C. and Gorsuch, R. (1983). Manual for the State-trait Anxiety Inventory (form Y) (”self-evaluation Questionnaire”). Consulting Psychologists Press.
Straus, L. D., An, X., Ji, Y., McLean, S. A., Neylan, T. C., Group, A. S., Cakmak, A. S., Richards, A., Clifford, G. D., Liu, M., et al. (2023). Utility of wrist-wearable data for assessing pain, sleep, and anxiety outcomes after traumatic stress exposure. JAMA psychiatry, 80(3):220–229.
Vincent, C. J., Aguilar-Alvarez, R., Vanderhoof, S. O., Mott, D. D., and Jasnow, A. M. (2025). An amygdala-cortical circuit for encoding generalized fear memories. Molecular Psychiatry, pages 1–14.
Wang, J., Chen, Y., Hao, S., Peng, X., and Hu, L. (2019). Deep learning for sensor-based human activity recognition: A survey. Sensors, 17:416.
Publicado
01/06/2026
Como Citar
FERNANDES, Raphael M. M.; REBELLO, Bernardo M.; RODRIGUES, João Vitor P.; ALVES, Ana Luiza P.; CONCEIÇÃO, Gabriel V. S.; FERNANDES, Arthur M.; MUCHALUAT-SAADE, Débora C.; RAMOS, Taiane C..
Predição de Níveis de Ansiedade Utilizando Dados de Smartwatches em Ambiente Não Controlado. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 26. , 2026, Ouro Preto/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 1014-1025.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2026.21603.
