Machine Learning-Based Clinical Triage for Leptospirosis Using SINAN/SUS Data
Resumo
This study proposes a predictive model to support the clinical triage of suspected leptospirosis cases using data from the Notifiable Diseases Information System (SINAN), based on clinical, demographic, and epidemiological variables. The LightGBM model achieved the best performance in classifying confirmed versus discarded cases (AUC ≈ 0.93) and moderate performance in predicting clinical severity (AUC ≈ 0.70). Threshold analysis indicated that values below 0.5 are more appropriate for prioritizing sensitivity and reducing false negatives in triage settings.Referências
Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A nextgeneration hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2623–2631.
Berrar, D. (2019). Cross-validation.
Bohm, B. C. (2024). Avaliação de dados do sistema de saúde e elaboração de ferramentas de triagem. pages 91–105.
Brasil. Ministério da Saúde (2014). Leptospirose: diagnóstico e manejo clínico. Technical report, Ministério da Saúde.
Brasil. Ministério da Saúde (2016). Sistema de informação de agravos de notificação (sinan): normas e rotinas. Technical report, Ministério da Saúde.
Brasil. Ministério da Saúde (2023). Sistema Único de saúde (sus): estrutura, princípios e funcionamento. Technical report, Ministério da Saúde.
Brasil. Ministério da Saúde (2024). Guia de vigilância em saúde: volume 3. Technical report, Ministério da Saúde.
Brasil. Ministério da Saúde (2025). Datasus-tabnet. Acesso em: 2025.
Breiman, L. (2001). Random forests. Machine learning, 45:5–32.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357.
Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.
Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine learning, 20:273–297.
Costa, F., Hagan, J. E., Calcagno, J., Kane, M., Torgerson, P., Martinez-Silveira, M. S., Stein, C., Abela-Ridder, B., and Ko, A. I. (2015). Global morbidity and mortality of leptospirosis: a systematic review. PLoS neglected tropical diseases, 9:e0003898.
da Silva, A. F., Figueiredo, K., Falcão, I. W. S., Costa, F. A. R., da Rocha Seruffo, M. C., and de Moraes, C. C. G. (2024). Study of machine learning techniques for outcome assessment of leptospirosis patients. Scientific Reports, 14:13929.
da Silva, L. P., Moreira, C. M. M., Amorim, M. H. C., de Castro, D. S., and Zandonade, E. (2014). Avaliação da qualidade dos dados do sistema de informações sobre nascidos vivos e do sistema de informações sobre mortalidade no período neonatal, espírito santo, brasil, de 2007 a 2009. Ciência & Saúde Coletiva, 19:2011–2020.
de Araujo Lima, C. R., de Andrade Schramm, J. M., Coeli, C. M., and da Silva, M. E. M. (2009). Revisão das dimensões de qualidade dos dados e métodos aplicados na avaliação dos sistemas de informação em saúde. Cadernos de saúde pública, 25:2095–2109.
Fawcett, T. (2006). An introduction to roc analysis. Pattern recognition letters, 27:861–874.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189–1232.
Galdino, G. S., de Sandes-Freitas, T. V., de Andrade, L. G. M., Adamian, C. M. C., Meneses, G. C., da Silva Junior, G. B., and de Francesco Daher, E. (2023). Development and validation of a simple machine learning tool to predict mortality in leptospirosis. Scientific Reports, 13:4506.
Guyon, I. and Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of machine learning research, 3:1157–1182.
He, H. and Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, 21:1263–1284.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
Kraskov, A., Stögbauer, H., and Grassberger, P. (2004). Estimating mutual information. Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 69:66138.
Kutner, M. H., Nachtsheim, C. J., Neter, J., and Li, W. (2005). Applied Linear Statistical Models. McGraw-Hill/Irwin, english edition.
Li, D., Liang, H., Yi, R., Xiao, Q., Zhu, Y., Chang, Q., Zhou, L., Liu, B., He, J., Liu, T., et al. (2022). Clinical characteristics and prognosis of patient with leptospirosis: A multicenter retrospective analysis in south of china. Frontiers in Cellular and Infection Microbiology, 12:1014530.
Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., and Talwalkar, A. (2018). Hyperband: A novel bandit-based approach to hyperparameter optimization. Journal of machine learning research, 18:1–52.
Mooney, S. J. and Pejaver, V. (2018). Big data in public health: Terminology, machine learning, and privacy. Annual Review of Public Health, 39:95–112.
Niculescu-Mizil, A. and Caruana, R. (2007). Obtaining calibrated probabilities from boosting. volume 5, pages 413–420.
Pappas, G., Papadimitriou, P., Siozopoulou, V., Christou, L., and Akritidis, N. (2008). The globalization of leptospirosis: worldwide incidence trends. International journal of infectious diseases, 12:351–357.
Pongpan, S., Thanatrakolsri, P., Vittaporn, S., Khamnuan, P., and Daraswang, P. (2023). Prognostic factors for leptospirosis infection severity. Tropical Medicine and Infectious Disease, 8:112.
Reagan, K. L., Deng, S., Sheng, J., Sebastian, J., Wang, Z., Huebner, S. N., Wenke, L. A., Michalak, S. R., Strohmer, T., and Sykes, J. E. (2022). Use of machine-learning algorithms to aid in the early detection of leptospirosis in dogs. Journal of Veterinary Diagnostic Investigation, 34:612–621. PMID: 35603565.
Reinheimer, I. C., Corrêa-Dos-Santos, A., Carlan, B. D., Telöken, I. B., da Silva Lessa-De-Oliveira, V., Braga-Da-Silveira, J., Escouto, D. C., Barra, A. B. L., Strogoff-De-Matos, J. P., and Poli-De-Figueiredo, C. E. (2025). Impacto do balanceamento de dados na performance de modelos de machine learning para predição de óbito de pacientes em hemodiálise no sus. Braz. J. Nephrol., 47:S501.
Sawesi, S., Jadhav, A., and Rashrash, B. (2025). Machine learning and deep learning techniques for prediction and diagnosis of leptospirosis: Systematic literature review. JMIR Med Inform, 13:e67859.
Berrar, D. (2019). Cross-validation.
Bohm, B. C. (2024). Avaliação de dados do sistema de saúde e elaboração de ferramentas de triagem. pages 91–105.
Brasil. Ministério da Saúde (2014). Leptospirose: diagnóstico e manejo clínico. Technical report, Ministério da Saúde.
Brasil. Ministério da Saúde (2016). Sistema de informação de agravos de notificação (sinan): normas e rotinas. Technical report, Ministério da Saúde.
Brasil. Ministério da Saúde (2023). Sistema Único de saúde (sus): estrutura, princípios e funcionamento. Technical report, Ministério da Saúde.
Brasil. Ministério da Saúde (2024). Guia de vigilância em saúde: volume 3. Technical report, Ministério da Saúde.
Brasil. Ministério da Saúde (2025). Datasus-tabnet. Acesso em: 2025.
Breiman, L. (2001). Random forests. Machine learning, 45:5–32.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357.
Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.
Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine learning, 20:273–297.
Costa, F., Hagan, J. E., Calcagno, J., Kane, M., Torgerson, P., Martinez-Silveira, M. S., Stein, C., Abela-Ridder, B., and Ko, A. I. (2015). Global morbidity and mortality of leptospirosis: a systematic review. PLoS neglected tropical diseases, 9:e0003898.
da Silva, A. F., Figueiredo, K., Falcão, I. W. S., Costa, F. A. R., da Rocha Seruffo, M. C., and de Moraes, C. C. G. (2024). Study of machine learning techniques for outcome assessment of leptospirosis patients. Scientific Reports, 14:13929.
da Silva, L. P., Moreira, C. M. M., Amorim, M. H. C., de Castro, D. S., and Zandonade, E. (2014). Avaliação da qualidade dos dados do sistema de informações sobre nascidos vivos e do sistema de informações sobre mortalidade no período neonatal, espírito santo, brasil, de 2007 a 2009. Ciência & Saúde Coletiva, 19:2011–2020.
de Araujo Lima, C. R., de Andrade Schramm, J. M., Coeli, C. M., and da Silva, M. E. M. (2009). Revisão das dimensões de qualidade dos dados e métodos aplicados na avaliação dos sistemas de informação em saúde. Cadernos de saúde pública, 25:2095–2109.
Fawcett, T. (2006). An introduction to roc analysis. Pattern recognition letters, 27:861–874.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189–1232.
Galdino, G. S., de Sandes-Freitas, T. V., de Andrade, L. G. M., Adamian, C. M. C., Meneses, G. C., da Silva Junior, G. B., and de Francesco Daher, E. (2023). Development and validation of a simple machine learning tool to predict mortality in leptospirosis. Scientific Reports, 13:4506.
Guyon, I. and Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of machine learning research, 3:1157–1182.
He, H. and Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, 21:1263–1284.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
Kraskov, A., Stögbauer, H., and Grassberger, P. (2004). Estimating mutual information. Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 69:66138.
Kutner, M. H., Nachtsheim, C. J., Neter, J., and Li, W. (2005). Applied Linear Statistical Models. McGraw-Hill/Irwin, english edition.
Li, D., Liang, H., Yi, R., Xiao, Q., Zhu, Y., Chang, Q., Zhou, L., Liu, B., He, J., Liu, T., et al. (2022). Clinical characteristics and prognosis of patient with leptospirosis: A multicenter retrospective analysis in south of china. Frontiers in Cellular and Infection Microbiology, 12:1014530.
Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., and Talwalkar, A. (2018). Hyperband: A novel bandit-based approach to hyperparameter optimization. Journal of machine learning research, 18:1–52.
Mooney, S. J. and Pejaver, V. (2018). Big data in public health: Terminology, machine learning, and privacy. Annual Review of Public Health, 39:95–112.
Niculescu-Mizil, A. and Caruana, R. (2007). Obtaining calibrated probabilities from boosting. volume 5, pages 413–420.
Pappas, G., Papadimitriou, P., Siozopoulou, V., Christou, L., and Akritidis, N. (2008). The globalization of leptospirosis: worldwide incidence trends. International journal of infectious diseases, 12:351–357.
Pongpan, S., Thanatrakolsri, P., Vittaporn, S., Khamnuan, P., and Daraswang, P. (2023). Prognostic factors for leptospirosis infection severity. Tropical Medicine and Infectious Disease, 8:112.
Reagan, K. L., Deng, S., Sheng, J., Sebastian, J., Wang, Z., Huebner, S. N., Wenke, L. A., Michalak, S. R., Strohmer, T., and Sykes, J. E. (2022). Use of machine-learning algorithms to aid in the early detection of leptospirosis in dogs. Journal of Veterinary Diagnostic Investigation, 34:612–621. PMID: 35603565.
Reinheimer, I. C., Corrêa-Dos-Santos, A., Carlan, B. D., Telöken, I. B., da Silva Lessa-De-Oliveira, V., Braga-Da-Silveira, J., Escouto, D. C., Barra, A. B. L., Strogoff-De-Matos, J. P., and Poli-De-Figueiredo, C. E. (2025). Impacto do balanceamento de dados na performance de modelos de machine learning para predição de óbito de pacientes em hemodiálise no sus. Braz. J. Nephrol., 47:S501.
Sawesi, S., Jadhav, A., and Rashrash, B. (2025). Machine learning and deep learning techniques for prediction and diagnosis of leptospirosis: Systematic literature review. JMIR Med Inform, 13:e67859.
Publicado
19/10/2026
Como Citar
PEREIRA, Ana Carolyne; LIMA, Diego Pereira; BERTON, Lilian.
Machine Learning-Based Clinical Triage for Leptospirosis Using SINAN/SUS Data. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 325-336.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.29943.
