IaraMed: A Women’s Healthcare Chatbot for Portuguese Speakers

• Fernanda B. Färber AKCIT / UFG
• Julia S. Dollis AKCIT / UFG
• Pedro S. F. B. Ribeiro AKCIT / UFG
• Iago A. Brito AKCIT / UFG
• Rafael T. Sousa AKCIT / UFMT
• Arlindo R. Galvão Filho AKCIT / UFG

DOI: https://doi.org/10.5753/sbcas.2025.7897

Resumo

The advent of large language models has significantly advanced natural language processing, revolutionizing numerous applications within the healthcare domain. Despite these advances, most existing research remains predominantly centered around English, resulting in notable disparities in medical AI accessibility for non-English speaking communities. To bridge this gap, we introduce a specialized Portuguese-language chatbot tailored explicitly to women’s healthcare needs, addressing critical shortages in linguistic resources and culturally relevant data. Leveraging retrieval-augmented generation, our chatbot integrates accurate, evidence-based information directly into generated responses. Evaluations demonstrate that our approach markedly enhances reliability, highlighting the potential for tailored AI applications to significantly improve healthcare accessibility and outcomes for Portuguese-speaking women.

Referências

Chi, Z., Huang, H., Liu, L., Bai, Y., Gao, X., and Mao, X.-L. (2023). Can pretrained english language models benefit non-english nlp systems in low-resource scenarios? IEEE/ACM Transactions on Audio, Speech, and Language Processing, 32:1061–1074.

Chiu, T. K., Moorhouse, B. L., Chai, C. S., and Ismailov, M. (2024). Teacher support and student motivation to learn with artificial intelligence (ai) based chatbot. Interactive Learning Environments, 32(7):3240–3256.

Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L., and Stoyanov, V. (2020). Unsupervised cross-lingual representation learning at scale. In Jurafsky, D., Chai, J., Schluter, N., and Tetreault, J., editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8440–8451, Online. Association for Computational Linguistics.

Consoli, B., dos Santos, H. D. P., Ulbrich, A. H. D. P. S., Vieira, R., and Bordini, R. H. (2022). BRATECA (Brazilian tertiary care dataset): a clinical information dataset for the Portuguese language. In Calzolari, N., Béchet, F., Blache, P., Choukri, K., Cieri, C., Declerck, T., Goggi, S., Isahara, H., Maegaard, B., Mariani, J., Mazo, H., Odijk, J., and Piperidis, S., editors, Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5609–5616, Marseille, France. European Language Resources Association.

Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Burstein, J., Doran, C., and Solorio, T., editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.

dos Santos Junior, J. B., Gomes, J., da Silva Dias, J., de Souza, L. N. O., Zanotti, A. C. N., Dias, R. P., and de Carvalho, Â. B. (2021). Uma proposta de chatbot para apoio a gestantes no contexto do sistema de saúde brasileiro. Revista Ibérica de Sistemas e Tecnologias de Informação, (E42):344–352.

Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazaré, P.-E., Lomeli, M., Hosseini, L., and Jégou, H. (2024). The faiss library. arXiv preprint arXiv:2401.08281.

Elshin, D., Karpachev, N., Gruzdev, B., Golovanov, I., Ivanov, G., Antonov, A., Skachkov, N., Latypova, E., Layner, V., Enikeeva, E., Popov, D., Chekashev, A., Negodin, V., Frantsuzova, V., Chernyshev, A., and Denisov, K. (2024). From general LLM to translation: How we dramatically improve translation quality using human evaluation data for LLM finetuning. In Haddow, B., Kocmi, T., Koehn, P., and Monz, C., editors, Proceedings of the Ninth Conference on Machine Translation, pages 247–252, Miami, Florida, USA. Association for Computational Linguistics.

García-Méndez, S., De Arriba-Perez, F., González-Castaño, F. J., Regueiro-Janeiro, J. A., and Gil-Castiñeira, F. (2021). Entertainment chatbot for the digital inclusion of elderly people without abstraction capabilities. IEEE Access, 9:75878–75891.

Gemini Team, R. A., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K., et al. (2023). Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805.

Gong, Y., Liu, G., Xue, Y., Li, R., and Meng, L. (2023). A survey on dataset quality in machine learning. Information and Software Technology, 162:107268.

Jin, D., Pan, E., Oufattole, N., Weng, W.-H., Fang, H., and Szolovits, P. (2021). What disease does this patient have? a large-scale open domain question answering dataset from medical exams. Applied Sciences, 11(14).

Kirubakaran, S., Kathrine, J. W., E, G. M. K., J, M. R., Singh A, R. G., and E, Y. (2024). A rag-based medical assistant especially for infectious diseases. In 2024 International Conference on Inventive Computation Technologies (ICICT), pages 1128–1133.

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., Riedel, S., and Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H., editors, Advances in Neural Information Processing Systems, volume 33, pages 9459–9474. Curran Associates, Inc.

Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., and Liang, P. (2024). Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12:157–173.

Miao, J., Thongprayoon, C., Suppadungsuk, S., 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.

Montenegro, J. L. Z., da Costa, C. A., and Janssen, L. P. (2022). Evaluating the use of chatbot during pregnancy: A usability study. Healthcare Analytics, 2:100072.

Oliveira, L. E. S. e., Peters, A. C., Da Silva, A. M. P., Gebeluca, C. P., Gumiel, Y. B., Cintho, L. M. M., Carvalho, D. R., Al Hasan, S., and Moro, C. M. C. (2022). Semclinbr-a multi-institutional and multi-specialty semantically annotated corpus for portuguese clinical nlp tasks. Journal of Biomedical Semantics, 13(1):13.

Passinato, E., Rios, W., and Filho, A. G. (2024). Integração de modelos de linguagem e rag na criação de chatbots oftalmológicos. In Anais do XXIV Simpósio Brasileiro de Computação Aplicada à Saúde, pages 354–365, Porto Alegre, RS, Brasil. SBC.

Puspitasari, I. W., Rinawan, F. R., Purnama, W. G., Susiarno, H., and Susanti, A. I. (2022). Development of a chatbot for pregnant women on a posyandu application in indonesia: From qualitative approach to decision tree method. In Informatics, volume 9, page 88. MDPI.

Robinson, J., Rytting, C. M., and Wingate, D. (2022). Leveraging large language models for multiple choice question answering. arXiv preprint arXiv:2210.12353.

Souza, F., Nogueira, R., and Lotufo, R. (2020). Bertimbau: Pretrained bert models for brazilian portuguese. In Intelligent Systems: 9th Brazilian Conference, BRACIS 2020, Rio Grande, Brazil, October 20–23, 2020, Proceedings, Part I, page 403–417, Berlin, Heidelberg. Springer-Verlag.

Tawfik, E., Ghallab, E., and Moustafa, A. (2023). A nurse versus a chatbot–the effect of an empowerment program on chemotherapy-related side effects and the self-care behaviors of women living with breast cancer: a randomized controlled trial. BMC nursing, 22(1):102.

Tu, T., Palepu, A., Schaekermann, M., Saab, K., Freyberg, J., Tanno, R., Wang, A., Li, B., Amin, M., Tomasev, N., et al. (2024). Towards conversational diagnostic ai. arXiv preprint arXiv:2401.05654.

Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., and Wei, F. (2022). Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533.

Xiong, G., Jin, Q., Lu, Z., and Zhang, A. (2024). Benchmarking retrieval-augmented generation for medicine. In Ku, L.-W., Martins, A., and Srikumar, V., editors, Findings of the Association for Computational Linguistics: ACL 2024, pages 6233–6251, Bangkok, Thailand. Association for Computational Linguistics.

Xu, L., Sanders, L., Li, K., Chow, J. C., et al. (2021). Chatbot for health care and oncology applications using artificial intelligence and machine learning: systematic review. JMIR cancer, 7(4):e27850.

Ye, Y., Huang, Z., Xiao, Y., Chern, E., Xia, S., and Liu, P. (2025). Limo: Less is more for reasoning. arXiv preprint arXiv:2502.03387.

Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., Chen, Y., et al. (2023). Siren’s song in the ai ocean: A survey on hallucination in large language models. arXiv preprint arXiv:2309.01219, 2(5).