B-Track: A model for assisting in non-communicable diseases through human behavior analysis

• Lucas Pfeiffer Salomão Dias UNISINOS
• Jorge Luis Victória Barbosa UNISINOS

DOI: https://doi.org/10.5753/sbcas_estendido.2025.6564

Resumo

Chronic diseases are among 7 out of the 10 leading causes of death worldwide. The main chronic diseases are heart disease, cancer, chronic respiratory diseases, and diabetes. Heart disease alone causes 9 million deaths a year. Lifestyle changes can prevent many chronic diseases’ deaths and their risk factors. In addition, machine learning and wearable devices have been used for behavior analysis. Therefore, this research proposes B-Track, a computational model for assistance in chronic disease care through analyzing behaviors that attenuate or worsen the risk factors associated with chronic diseases, working with user behavior profiles and recommendations for healthier behaviors. Besides, an ontology was created to be used as a knowledge model for the B-Track model to track behaviors associated with risk factors for chronic diseases. The B-Track collects data from different data sources for current and future human behavior analysis through the usage of data fusion and machine learning models. These data comprise the patients’ context histories, which include sensor data and data from self-management surveys. Based on the ontology inferences, the B-Track acts in a personalized manner, sending recommendations for habit changes to patients and allowing user accompaniment by health professionals. The scientific contribution of B-Track model is the analysis of human behaviors directly associated with risk factors and their susceptibility to the development of chronic diseases. The model was evaluated through a prototype, which was used by 10 patients during their treatment. Patients participating in the experiment had habits associated with risk factors with susceptibility to developing coronary heart disease, diabetes, and dementia. Some of these patients already had heart disease, hypertension, or diabetes. Patients P4, P5, P6, P7, and P8 showed positive changes in their behaviors in the long term, where P4 increased their consumption of healthy foods, P5 started exercising with highest frequency, and P6, P7, and P8 also made positive changes to their exercise habits. Patient P1 showed no changes, and the others had only shorter-term improvements. Overall, the TAM evaluation showed that B-Track model was useful to 83% of patients, and 80% of the patients found the model easy to use.

Referências

Dias, L. and Barbosa, J. (2024). Cuidado ubíquo de pacientes com doenças crônicas através de um modelo de análise do comportamento humano. In Proceedings of the 30th Brazilian Symposium on Multimedia and the Web, pages 106–114, Porto Alegre, RS, Brasil. SBC.

Dias, L. P. S., Damasceno Vianna, H., Heckler, W., and Luis Victória Barbosa, J. (2024). Identifying chronic disease risk behaviors: An ontology-based approach. iSys - Brazilian Journal of Information Systems, 17(1):7:1 – 7:31.

Dias, L. P. S., Vianna, H. D., and Barbosa, J. L. V. (2022). Human behaviour data analysis and noncommunicable diseases: a systematic mapping study. Behaviour & Information Technology, 42(14):2485–2503.

dos Santos Paula, L., Barbosa, J. L. V., and Dias, L. P. S. (2022). A model for assisting in the treatment of anxiety disorder. Universal Access in the Information Society, 21(2):533–543.

El-Gayar, O. F., Ambati, L. S., and Nawa, N. (2020). Wearables, Artificial intelligence, and the Future of Healthcare, chapter Deep Learning for Medical Decision Support Systems, pages 104–129. IGI Global.

Griffiths, J. C., De Vries, J., McBurney, M. I., Wopereis, S., Serttas, S., and Marsman, D. S. (2020). Measuring health promotion: translating science into policy. European Journal of Nutrition, 59(2):11–23.

Grimaldi-Puyana, M., Fernández-Batanero, J. M., Fennell, C., and Sañudo, B. (2020). Associations of objectively-assessed smartphone use with physical activity, sedentary behavior, mood, and sleep quality in young adults: A cross-sectional study. International Journal of Environmental Research and Public Health, 17(10).

Jones, S. L., Hue, W., Kelly, R. M., Barnett, R., Henderson, V., and Sengupta, R. (2021). Determinants of longitudinal adherence in smartphone-based self-tracking for chronic health conditions: Evidence from axial spondyloarthritis. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 5(1). DOI: 10.1145/3448093.

Kyada, D. S. and Baria, D. H. (2019). Prevalence of risk factors of non-communicable diseases among the health care professionals of a tertiary care hospital of south gujarat, india. World Journal of Advance Healthcare Research, 3(4):57–61.

Milne-Ives, M., Lam, C., De Cock, C., Van Velthoven, M. H., and Meinert, E. (2020). Mobile apps for health behavior change in physical activity, diet, drug and alcohol use, and mental health: Systematic review. JMIR Mhealth Uhealth, 8(3):e17046.

Monteiro, L. Z., Varela, A. R., Alves, L. R., Santos, M. R. S., Lopes, G. R., Caetano Júnior, M. A., and Leandro, S. S. (2018). Prevalência e fatores associados ao uso de álcool e tabaco em universitários do curso de enfermagem. Revista Eletrônica de Enfermagem, 20.

Pfeiffer Salomão Dias, L., Damasceno Vianna, H., Heckler, W., and Luis Victória Barbosa, J. (2023). Ontology-based reasoning to classify behaviors associated with chronic disease risk factors. In Proceedings of the XIX Brazilian Symposium on Information Systems, SBSI ’23, page 292–299, New York, NY, USA. Association for Computing Machinery.

Rehackova, L., Araújo-Soares, V., Steven, S., Adamson, A. J., Taylor, R., and Sniehotta, F. F. (2020). Behaviour change during dietary type 2 diabetes remission: a longitudinal qualitative evaluation of an intervention using a very low energy diet. Diabetic Medicine, 37(6):953–962.

WHO (2020). Global action plan for the prevention and control of noncommunicable diseases. Available in: [link], access: Jan 19 2023.

WHO (2022). Noncommunicable diseases. Available in: [link], access: Jan 19 2023.