Predicting Asthma Exacerbations in Digital Health Ecosystems Using Machine Learning Frameworks
Resumo
A triagem do risco de exacerbações asmáticas é crítica para a saúde digital e dados gerados por pacientes (PGHD). Este trabalho avalia um modelo de triagem inteligente para o aplicativo Afilaxy, classificando perfis de risco com base nos critérios da GINA. Testou-se Regressão Logística, Random Forest, Gradient Boosting e XGBoost em dados sintéticos. O XGBoost obteve AUC de 91,3% e Sensibilidade de 89,2% no limiar otimizado. Apesar do forte desempenho, a taxa de 10,8% de falsos negativos exige cautela clínica. O estudo estabelece uma prova de conceito para futura implementação em dispositivos móveis.Referências
Afilaxy (2025). Afilaxy: A rede social de quem tem asma. [link]. Acesso em: 23 ago. 2026.
Alotaibi, S. et al. (2020). Machine learning applications in asthma monitoring and management: A systematic review. IEEE Access, 8:109508–109521.
Altman, D. G. and Bland, J. M. (2000). Diagnostic tests 2: Predictive values. BMJ, 321(7258):430.
Bousquet, J. et al. (2017). Next-generation care pathways for asthma with mobile technology: Mask-asthma (mobile airways sentinel network). Journal of Allergy and Clinical Immunology, 140(5):1245–1249.
Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.
Carvalho-Pinto, R. P. et al. (2022). Recomendações para o manejo da asma grave da sociedade brasileira de pneumologia e tisiologia - 2021. Jornal Brasileiro de Pneumologia, 48(1):e20210273.
Demiris, G. et al. (2019). Patient-generated health data as a resource for research and clinical care. Methods of Information in Medicine, 58(S 01):e1–e2.
Global Initiative for Asthma (2024). Global Strategy for Asthma Management and Prevention. Global Initiative for Asthma (GINA). Disponível em: [link]. Acesso em: 17 jun. 2026.
Guarnieri, M. and Balmes, J. R. (2014). Outdoor air pollution and asthma. The Lancet, 383(9918):724–734.
Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Science & Business Media, New York, 2nd edition.
James, G., Witten, D. C., Hastie, T., and Tibshirani, R. (2021). An Introduction to Statistical Learning: with Applications in R. Springer, New York, 2nd edition.
Merchant, R. K. et al. (2016). Integrating digital health tools into the management of chronic respiratory diseases. JMIR mHealth and uHealth, 4(2):e40.
Patel, S. et al. (2021). Bridging the gap: patient-generated health data and digital health ecosystems. npj Digital Medicine, 4(1):112.
Alotaibi, S. et al. (2020). Machine learning applications in asthma monitoring and management: A systematic review. IEEE Access, 8:109508–109521.
Altman, D. G. and Bland, J. M. (2000). Diagnostic tests 2: Predictive values. BMJ, 321(7258):430.
Bousquet, J. et al. (2017). Next-generation care pathways for asthma with mobile technology: Mask-asthma (mobile airways sentinel network). Journal of Allergy and Clinical Immunology, 140(5):1245–1249.
Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.
Carvalho-Pinto, R. P. et al. (2022). Recomendações para o manejo da asma grave da sociedade brasileira de pneumologia e tisiologia - 2021. Jornal Brasileiro de Pneumologia, 48(1):e20210273.
Demiris, G. et al. (2019). Patient-generated health data as a resource for research and clinical care. Methods of Information in Medicine, 58(S 01):e1–e2.
Global Initiative for Asthma (2024). Global Strategy for Asthma Management and Prevention. Global Initiative for Asthma (GINA). Disponível em: [link]. Acesso em: 17 jun. 2026.
Guarnieri, M. and Balmes, J. R. (2014). Outdoor air pollution and asthma. The Lancet, 383(9918):724–734.
Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Science & Business Media, New York, 2nd edition.
James, G., Witten, D. C., Hastie, T., and Tibshirani, R. (2021). An Introduction to Statistical Learning: with Applications in R. Springer, New York, 2nd edition.
Merchant, R. K. et al. (2016). Integrating digital health tools into the management of chronic respiratory diseases. JMIR mHealth and uHealth, 4(2):e40.
Patel, S. et al. (2021). Bridging the gap: patient-generated health data and digital health ecosystems. npj Digital Medicine, 4(1):112.
Publicado
19/10/2026
Como Citar
SIN, Herbert Jung; SILVA, Martony Demes da.
Predicting Asthma Exacerbations in Digital Health Ecosystems Using Machine Learning Frameworks. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 861-872.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.30598.
