Implementasi Konsultasi Stunting Balita Menggunakan Large Language Models (LLMs)

Tanwir Tanwir; Khasnur  Hidjah; Dyah  Susilowati

doi:10.31294/reputasi.v6i1.8961

Authors

Tanwir Tanwir Universitas Bumigora
Khasnur Hidjah Universitas Bumigora
Dyah Susilowati Universitas Bumigora

DOI:

https://doi.org/10.31294/reputasi.v6i1.8961

Keywords:

Stunting balita, Large Language Models (LLMs), LLaMA 3, Matrik ROUGE, Chatbot konsultasi kesehatan

Abstract

Stunting pada balita merupakan masalah kesehatan kritis di Indonesia yang memerlukan intervensi berbasis teknologi untuk meningkatkan akses informasi nutrisi. Penelitian ini bertujuan mengembangkan chatbot konsultasi stunting berbasis Large Language Models (LLMs) guna menyediakan rekomendasi kesehatan yang akurat dan mudah diakses. Metode yang digunakan berupa Model LLaMA 3 di-fine-tuning menggunakan dataset Q&A spesifik stunting berisi 7.642 entri, kemudian dievaluasi dengan matrik ROUGE untuk mengukur kesesuaian semantik respons. Hasil menunjukkan model Stunting mencapai skor ROUGE-1 (72,24%), ROUGE-2 (64,54%), ROUGE-L (70,42%), dan ROUGE-Lsum (70,96%), secara signifikan melampaui model baseline seperti LLaMA3, Deepseek-R1, dan Mistral. Chatbot diimplementasikan dalam aplikasi web berbasis cloud dengan arsitektur terdistribusi, dilengkapi enkripsi SSL dan HTTPS untuk menjamin keamanan data. Sistem ini memungkinkan interaksi real-time antara pengguna dan model LLMs melalui antarmuka berbasis Gradio. Temuan penelitian mengonfirmasi potensi LLMs dalam menyederhanakan layanan kesehatan preventif, khususnya di daerah dengan sumber daya terbatas

References

[1] V. Y. Lameky, “Stunting in Indonesia: Current progress and future directions,” Journal of Healthcare Administration, vol. 3, no. 1, pp. 82–90, Jun. 2024, doi: 10.33546/joha.3388.

[2] UNICEF, “Levels and Trends in Child Malnutrition,” UNICEF/WHO/World Bank Group Joint Child Malnutrition Estimates, 2023.

[3] Q. Rachmah et al., “Peningkatan Pengetahuan Gizi Terkait Makanan Pendamping Asi (Mp-Asi) Melalui Edukasi Dan Hands-On-Activity Pada Kader Dan Non-Kader,” Media Gizi Indonesia, vol. 17, no. 1SP, pp. 47–52, Dec. 2022, doi: 10.20473/mgi.v17i1sp.47-52.

[4] Dinas Kesehatan, “Jumlah Balita berdasarkan Status Gizi Kurang, Pendek dan Kurus di Nusa Tenggara Barat.” Accessed: Apr. 10, 2025. [Online]. Available: https://data.ntbprov.go.id/index.php/dataset/9d274132-1480-48ea-aacf-14426b63c7d6/show

[5] L. K. Wardani, V. Aulia, M. Hadhikul, and M. Kardila, “Risks of Stunting and Interventions to prevent Stunting,” Journal of Community Engagement in Health, vol. 6, no. 2, pp. 79–83, Sep. 2023, doi: 10.30994/jceh.v6i2.528.

[6] E. S. Yanti, R. Imami, and A. Arica, “Raising Awareness of the Impact of Stunting on Toddler Development Through Parental Education,” Amalee: Indonesian Journal of Community Research and Engagement, vol. 5, no. 2, pp. 751–764, Oct. 2024, doi: 10.37680/amalee.v5i2.5850.

[7] endang naryono, “STUNTING, THE MAIN THREAT TO HUMAN QUALITY,” Aug. 07, 2023. doi: 10.31219/osf.io/2w9yn.

[8] M. E. Dominguez Tabera et al., “The Application of Artificial Intelligence for the Design of a Virtual Assistant (Chatbot) as an innovative approach in user service: Social Security Center No.102,” International Journal of Combinatorial Optimization Problems and Informatics, vol. 15, no. 4, pp. 149–162, Nov. 2024, doi: 10.61467/2007.1558.2024.v15i4.484.

[9] H. G. Cavalcante et al., “DEVELOPING CHATBOTS IN THE FIELD OF HEALTHCARE: A SYSTEMATIC REVIEW,” Revista de Sistemas e Computação, vol. 12, no. 1, pp. 30–39, 2022, doi: 10.36558/rsc.v12i1.7589.

[10] W. Hadikurniawati, S. Wijono, D. Manongga, I. Sembiring, and K. D. Hartomo, “Toddler Stunting Consulting Chatbot using Rasa Framework,” Jurnal Rekayasa Elektrika, vol. 19, no. 4, Dec. 2023, doi: 10.17529/jre.v19i4.33014.

[11] M. Arevalillo-Herraez, P. Arnau-Gonzalez, and N. Ramzan, “On Adapting the DIET Architecture and the Rasa Conversational Toolkit for the Sentiment Analysis Task,” IEEE Access, vol. 10, pp. 107477–107487, 2022, doi: 10.1109/ACCESS.2022.3213061.

[12] D. Escobar-Grisales, J. C. Vásquez-Correa, and J. R. Orozco-Arroyave, “Evaluation of effectiveness in conversations between humans and chatbots using parallel convolutional neural networks with multiple temporal resolutions,” Multimed Tools Appl, vol. 83, no. 2, pp. 5473–5492, Jan. 2024, doi: 10.1007/s11042-023-14896-y.

[13] S. Zhou, J. Silvasstar, C. Clark, A. J. Salyers, C. Chavez, and S. S. Bull, “An artificially intelligent, natural language processing chatbot designed to promote COVID-19 vaccination: A proof-of-concept pilot study,” Digit Health, vol. 9, Jan. 2023, doi: 10.1177/20552076231155679.

[14] A. Gangavarapu, “LLMs: A Promising New Tool for Improving Healthcare in Low-Resource Nations,” in 2023 IEEE Global Humanitarian Technology Conference (GHTC), IEEE, Oct. 2023, pp. 252–255. doi: 10.1109/GHTC56179.2023.10354650.

[15] A. Goel et al., “LLMs Accelerate Annotation for Medical Information Extraction,” Dec. 2023, [Online]. Available: http://arxiv.org/abs/2312.02296

[16] A. Telenti, M. Auli, B. L. Hie, C. Maher, S. Saria, and J. P. A. Ioannidis, “Large language models for science and medicine,” Eur J Clin Invest, vol. 54, no. 6, Jun. 2024, doi: 10.1111/eci.14183.

[17] C. Munley, A. Jarmusch, and S. Chandrasekaran, “LLM4VV: Developing LLM-driven testsuite for compiler validation,” Future Generation Computer Systems, vol. 160, pp. 1–13, Nov. 2024, doi: 10.1016/j.future.2024.05.034.

[18] C. Curto, D. Giordano, D. G. Indelicato, and V. Patatu, “Can a Llama Be a Watchdog? Exploring Llama 3 and Code Llama for Static Application Security Testing,” in 2024 IEEE International Conference on Cyber Security and Resilience (CSR), IEEE, Sep. 2024, pp. 395–400. doi: 10.1109/CSR61664.2024.10679444.

[19] S. Kumar, A. Solanki, and N. Jhanjhi, “ROUGE-SS: A New ROUGE Variant for the Evaluation of Text Summarization,” Recent Advances in Computer Science and Communications, vol. 17, Jun. 2024, doi: 10.2174/0126662558304595240528111535.