Retrieval-Augmented Generation in Healthcare Systems: A Systematic Review with Emphasis on Public Data

• Rafael Santos Novo Pereira UNIFACCAMP
• Andre Gomes Regino CTI Renato Archer / UniFAJ / UniMAX
• Fernando Rezende Zagatti CTI Renato Archer / UniFAJ / UniMAX / UFSCar
• Matheus Bernardelli de Moraes CTI Renato Archer
• Guilherme Ruppert CTI Renato Archer
• Ana Carolina Monteiro CTI Renato Archer
• Rodrigo Bonacin UNIFACCAMP / CTI Renato Archer

DOI: https://doi.org/10.5753/sbcas.2026.21577

Resumo

Retrieval-Augmented Generation (RAG) enhances Large Language Models by integrating external knowledge retrieval. In public healthcare, this is relevant for handling heterogeneous data and specialized terminology. This paper presents a systematic review of RAG applications in healthcare, focusing on challenges and opportunities for Brazilian public data systems such as DataSUS. Following PRISMA, 145 studies were analyzed, with 14 meeting the inclusion criteria. Results indicate advances in hybrid retrieval and prompt engineering, but reveal gaps in regulatory compliance, multilingual support, and integration with Brazilian datasets. The study highlights research opportunities for developing RAG solutions tailored to public healthcare systems in Brazil.

Referências

Alkhalaf, M., Yu, P., Yin, M., and Deng, C. (2024). Applying generative ai with retrieval augmented generation to summarize and extract key clinical information from electronic health records. Journal of Biomedical Informatics, 156:104662.

Chen, Z., Cano, A. H., Romanou, A., Bonnet, A., Matoba, K., Llorca, F., Shi, K., Sivakumar, S., Dorn, J., Jaggi, M., et al. (2023). Meditron-70b: Multilingual medical language model with regional adaptations.

de Almeida Cardoso, M. M., Machado-Rugolo, J., Thabane, L., da Rocha, N. C., Barbosa, A. M. P., Komoda, D. S., de Almeida, J. T. C., Curado, D. d. S. P., Weber, S. A. T., and de Andrade, L. G. M. (2024). Application of natural language processing to predict final recommendation of brazilian health technology assessment reports. International journal of technology assessment in health care, 40(1):e19.

Huston, P., Edge, V. L., and Bernier, E. (2019). Reaping the benefits of open data in public health. Can Commun Dis Rep, 45(11):252–256.

Karamanlıoğlu, A., Demirel, B., Tural, O., and Doğan, O. T. (2024). Privacy-preserving clinical decision support for emergency triage using llms: System architecture and real-world evaluation. Applied Sciences, 15(15):8412.

Kresevic, S., Giuffrè, M., Ajcevic, M., Accardo, A., and Crocè, L. S. (2024). Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework. NPJ digital medicine, 7(1):102.

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–9474.

Miao, J., Thongprayoon, C., Suppadungsuk, S., Khoury, N. M., Choudhury, A., Garcia Valencia, O. A., and Cheungpasitporn, W. (2024). Integrating retrieval-augmented generation with large language models in nephrology: Advancing practical applications. Medicina, 60(3):445.

Ministério da Saúde (2025). Sobre o DATASUS - Histórico. Departamento de Informação e Informática do SUS - DATASUS. Acesso em: 07 ago. 2025.

Page, M. J., Moher, D., Bossuyt, P. M., Boutron, I., Hoffmann, T. C., Mulrow, C. D., Shamseer, L., Tetzlaff, J. M., Akl, E. A., Brennan, S. E., Chou, R., Glanville, J., Grimshaw, J. M., Hróbjartsson, A., Lalu, M. M., Li, T., Loder, E. W., Mayo-Wilson, E., McDonald, S., McGuinness, L. A., Stewart, L. A., Thomas, J., Tricco, A. C., Welch, V. A., Whiting, P., and McKenzie, J. E. (2021). Prisma 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews. BMJ, 372.

Souza, R. C. d., Freire, S. M., and Almeida, R. T. d. (2010). Sistema de informação para integrar os dados da assistência oncológica ambulatorial do sistema único de saúde. Cadernos de Saúde Pública, 26(6):1131–1140.

Topsakal, O. and Akinci, T. C. (2023). Creating large language model applications utilizing langchain: A primer on developing llm apps fast. In International conference on applied engineering and natural sciences, volume 1, pages 1050–1056.

Unlu, O., Padrez, K. A., Murray, D. L., Kolla, B. P., Bois, M. C., Edwards, B. S., Dispenzieri, A., Grogan, M., and Maleszewski, J. J. (2024). Retrieval augmented generation enabled generative pre-trained transformer 4 (gpt-4) performance for clinical trial screening. NEJM AI.

Viana, S. W., Faleiro, M. D., Mendes, A. L. F., Torquato, A. C., Tavares, C. P. O., Feres, B., Fernandez, M. G., SOBREIRA, I. R., AQUINO, C., MARQUES, D., et al. (2023). Limitations of using the datasus database as a primary source of data in surgical research: a scoping review. Revista do Colégio Brasileiro de Cirurgiões, 50:e20233545.

Wu, J., Zhu, J., Qi, Y., Chen, J., Xu, M., Menolascina, F., and Grau, V. (2024). Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation.

Yang, R., Ning, Y., Keppo, E., Liu, M., Hong, C., Bitterman, D. S., Ong, J. C. L., Ting, D. S. W., and Liu, N. (2025). Retrieval-augmented generation for generative artificial intelligence in health care. npj Health Systems, 2(1):2.

Yang, R., Tan, T. F., Lu, W., Thirunavukarasu, A. J., Ting, D. S. W., and Liu, N. (2023). Large language models in health care: Development, applications, and challenges. Health Care Science, 2(4):255–263.

Zakka, C., Shad, R., Chaurasia, A., Dalal, A. R., Kim, J. L., Moor, M., Fong, R., Phillips, C., Alexander, K., Ashley, E., et al. (2024). Almanac—retrieval-augmented language models for clinical medicine. Nejm ai, 1(2):AIoa2300068.

Zhou, Q., Liu, C., Duan, Y., Wu, J., Liu, H., Wu, Z., Zhang, X., Sun, J., Wei, X., and Qiu, X. (2024). Gastrobot: a chinese gastrointestinal disease chatbot based on retrieval-augmented generation. Frontiers in Medicine, 11:1392555.

Ziletti, A. and D’Ambrosi, L. (2024). Retrieval augmented text-to-sql generation for epidemiological question answering using electronic health records. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 47–53. Association for Computational Linguistics.