MedJus: A Cloud-based LLM Application to Expedite Decision Making for Health Judicialization in Brazil

• Bruno Padilha USP
• Jacson Venâncio de Barros USP
• Giovanni Guido Cerri USP
• João Eduardo Ferreira USP

DOI: https://doi.org/10.5753/pesquisanuvem.2026.21913

Resumo

The increasing number of processes regarding health judicialization in Brazil has been contributing to a major overloading in the judiciary system. In spite of inherent difficulties in adapting Large Language Models (LLMs) to niche yet critical domains (e.g hallucinations, user preference alignment, response grounding), deploying these models to assist specialist users such as judges and medical doctors introduces several infrastructural challenges. In this preliminary work, we explore how the cloud native services provided by Amazon Web Services (AWS) can be employed to overcome these challenges in MedJus: a secure, scalable, and serverless cloud-native LLM application to assist and support decision making in health judicialization diligence for Brazilian cases.

Referências

Berger, A., Khanna, S., Sparrenberg, L., Deußer, T., Berghaus, D., and Sifa, R. (2025). Reasoning llms in the medical domain: A literature survey. In 2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA), pages 1–10. IEEE.

Campos, E. M., Conrado, R. C., Traina Jr, C., Traina, A. J., and Cazzolato, M. T. (2025). Assessing large language models for structuring patient records. In Simpósio Brasileiro de Banco de Dados (SBBD), pages 1–7. SBC.

Chen, T. (2024). Challenges and opportunities in integrating llms into continuous integration/continuous deployment (ci/cd) pipelines. In 2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT), pages 364–367. IEEE.

CNJ (2024). Sistema nacional de pareceres e notas técnicas (e-natjus). Acessado em: 12 mar. 2026.

Jeong, J., Kim, S., Pan, L., Hwang, D., Kim, D., Choi, J., Kwon, Y., Yi, P., Jeong, J., and Yoo, S.-J. (2025). Reducing the workload of medical diagnosis through artificial intelligence: A narrative review. Medicine, 104(6):e41470.

Joshi, S., Mehta, M., Maniar, S., Wang, M., and Singh, V. K. (2026). Performance of large language models under input variability in health care applications: Dataset development and experimental evaluation. JMIR AI, 5:e83640.

Kant, M., Nabi, S., Kant, M., Scharrer, R., Ma, M., and Nabi, M. (2025). Towards robust legal reasoning: Harnessing logical llms in law. arXiv preprint arXiv:2502.17638.

Li, S. S., Balachandran, V., Feng, S., Ilgen, J. S., Pierson, E., Koh, P. W., and Tsvetkov, Y. (2024). Mediq: Question-asking llms and a benchmark for reliable interactive clinical reasoning. Advances in Neural Information Processing Systems, 37:28858–28888.

MS (2026). Portal da comissão nacional de incorporação de tecnologias no sistema Único de saúde (conitec). Acessado em: 12 mar. 2026.

NLM (US) (2026). Pubmed. Acessado em: 12 mar. 2026.

Shool, S., Adimi, S., Saboori Amleshi, R., Bitaraf, E., Golpira, R., and Tara, M. (2025). A systematic review of large language model (llm) evaluations in clinical medicine. BMC Medical Informatics and Decision Making, 25(1):117.

Trajanoski, S. and Karadimce, A. (2025). Comparative analysis of large language models: On-premise architectures vs. cloud-based deployments. Preface to Volume 5 Issue 2 of the Journal of University of Information Science and Technology “St. Paul the Apostle”–Ohrid, 5(2):48.

Wang, P., Lu, W., Lu, C., Zhou, R., Li, M., and Qin, L. (2025). Large language model for medical images: A survey of taxonomy, systematic review, and future trends. Big Data Mining and Analytics, 8(2):496.

Zhou, S., Xie, W., Li, J., Zhan, Z., Song, M., Yang, H., Espinoza, C., Welton, L., Mai, X., Jin, Y., et al. (2025). Automating expert-level medical reasoning evaluation of large language models. npj Digital Medicine.