sophIA: Platform to assist healthcare professionals in monitoring neonatal health

• Flávio Leandro de Morais UPE
• Stephany Paula da Silva Canejo UPE
• Maria Eduarda Ferro de Mello UPE
• Katia Maria Mendes UPE
• Waldemar Brandão Neto UPE
• Patricia Takako Endo UPE

DOI: https://doi.org/10.5753/sbcas.2026.21511

Resumo

The neonatal period is marked by high vulnerability and significant morbidity and mortality, especially in the first days of life, requiring innovative strategies to improve the quality of care. This study presents sophIA, a platform under development based on Artificial Intelligence (AI) to support clinical decision-making in the Neonatal Intensive Care Unit. Its architecture integrates real clinical data, rigorous preparation, and predictive modeling using traditional and hybrid techniques, in addition to explainability mechanisms. The interface includes an interactive dashboard for indicator visualization and a support chatbot. The sophIA estimates risks for adverse neonatal outcomes and generates interpretable clinical alerts. Preliminary results indicate technical feasibility and methodological consistency, demonstrating improved performance and reliability. It is expected to contribute to more timely interventions, reduction of preventable complications, and strengthening of neonatal health management.

Referências

Areco, K. N., Bandiera-Paiva, P., Balda, R. C., Costa-Nobre, D. T., Marinonio, A. S. S., Sanudo, A., Kawakami, M. D., Miyoshi, M. H., e Oliveira, C. N. V., Freitas, R. M., et al. (2025). Development and validation of an epidemiological risk score for neonatal death in a middle-income country. Frontiers in Public Health, 13:1675040.

BRASIL-SIM (2024). Sistema de informação sobre mortalidade. Available at: [link]. Accessed: January 05, 2026. Data updated in December 2025.

BRASIL-SINASC (2024). Sistema de informações sobre nascidos vivos. Available at: [link]. Accessed: January 05, 2026. Data updated in December 2025.

De Morais, F. L., Da Silva, R. C. L., Silva, A. B., Simão, E. P., De Mello, M. E. F., da Silva Canejo, S. P., Mendes, K. M., Neto, W. B., Da Silva, J. R. F., da Silva, M. H. L. F., et al. (2025). On usage of artificial intelligence for predicting neonatal diseases, conditions and mortality: A bibliometric review. IEEE Access.

de Pernambuco, U. (2025). Cisam - centro universitário integrado de saúde amaury de medeiros. Disponível em: [link]. Acesso em: 03 de junho de 2026.

Grillo, M. A., Mariani, G., and Ferraris, J. R. (2022). Prematurity and low birth weight in neonates as a risk factor for obesity, hypertension, and chronic kidney disease in pediatric and adult age. Frontiers in medicine, 8:769734.

Kwok, T. C., Henry, C., Saffaran, S., Meeus, M., Bates, D., Van Laere, D., Boylan, G., Boardman, J. P., and Sharkey, D. (2022). Application and potential of artificial intelligence in neonatal medicine. In Seminars in Fetal and Neonatal Medicine, volume 27, page 101346. Elsevier.

Morais, F. L. d., Canejo, S. P. d. S., Mello, M. E. F. d., Silva, R. C. L. d., Barros, M. H. L. F. d. S., Rocha, E. d. S., Mendes, K. M., Neto, W. B., and Endo, P. T. (2026). On the usage of artificial intelligence for identifying main attributes and predicting neonatal sepsis. Scientific Report. Preprint, not peer reviewed.

UNICEF (2024). Levels and trends in child mortality 2024. [link]. Accessed: November 13, 2025.

United Nations (2015). Transforming our world: the 2030 agenda for sustainable development. Resolution adopted by the General Assembly on 25 September 2015 (A/RES/70/1). Accessed: 2026-02-25.

Zinjani, S. (2023). Common medical conditions in the neonates. In Clinical Anesthesia for the Newborn and the Neonate, pages 49–70. Springer.