AFP assistant: a retrieval-augmented generation and large language model-powered multilingual polio chatbot for low-resource language communities
5 affiliations
- 1School of Biomedical Engineering, Jimma Institute of Technology, Jimma University
- 2Faculty of Computing and Informatics, Jimma Institute of Technology, Jimma University
- 3Department of Educational Technology and Information Management, Mattu University
- 4Department of Biomedical Engineering, Gannon University
- 5Global South Artificial Intelligence for Pandemic and Epidemic Preparedness and Response Network (AI4PEP)
Abstract
Acute flaccid paralysis (AFP) surveillance in Ethiopia remains limited due to hard-to-reach populations, restricted healthcare access, low public awareness, and persistent underreporting within community-based surveillance (CBS) systems. Contributing to this are inadequate training of community reporters, communication barriers, and cultural beliefs and misinformation that further hinder timely case detection. Here, AFP Assistant, a multilingual large language model powered chatbot, is developed to strengthen CBS through improved health communication and real-time reporting. The system supports Amharic, Afaan Oromo, and English to enhance accessibility and inclusivity. A curated dataset derived from literature, guidelines, and community interviews was translated and validated by experts to ensure clinical and cultural accuracy. The system integrates supervised fine-tuning with retrieval-augmented generation (RAG) to deliver accurate, context-aware responses. Trained on 468 question–answer pairs using pretrained Gemini 2.5-flash, the model achieved an accuracy of 0.90 and a loss of 0.31. The RAG framework improved retrieval relevance, grounding, and response efficiency. Evaluation through in-house testing and human annotation using a structured rubric demonstrated robust performance across tasks and languages, while user feedback confirmed usability and relevance. These findings highlight the potential of AI-driven chatbots to enhance AFP surveillance and equitable health communication in low-resource settings.
Related
- Real-world evaluation of a multilingual agentic retrieval-augmented clinical AI framework for evidence-grounded medical decision support
- Retrieval-augmented generation in biomedicine: a survey of technologies, datasets, and clinical applications
- Retrieval-augmented generation in medicine: A scoping review of technical implementations, clinical applications, and ethical considerations
- IPF-RAG: temporal-aware retrieval-augmented generation for idiopathic pulmonary fibrosis care.
- Limits of Single-Pass Retrieval-Augmented Generation for AI-Powered Cancer Care Navigation: A Comparison of Retrieval Strategies
BibTeX
@article{biru2026assistant,
title = {{AFP assistant: a retrieval-augmented generation and large language model-powered multilingual polio chatbot for low-resource language communities}},
author = {Gelane Biru and Honey Gemechu and Firanol Teshome and Eyerusalem Gebremeskel and Hundessa Daba Nemomssa and Kokeb Dese and Melaku Tilahun and Karrasaaqii Bulti Wakgari and Nardos Bisrat and Gelan Ayana and Jude Kong},
journal = {npj Digital Medicine},
year = {2026},
month = jun,
doi = {10.1038/s41746-026-02944-4},
url = {https://doi.org/10.1038/s41746-026-02944-4},
note = {CC BY},
}
RIS
TY - JOUR
TI - AFP assistant: a retrieval-augmented generation and large language model-powered multilingual polio chatbot for low-resource language communities
AU - Gelane Biru
AU - Honey Gemechu
AU - Firanol Teshome
AU - Eyerusalem Gebremeskel
AU - Hundessa Daba Nemomssa
AU - Kokeb Dese
AU - Melaku Tilahun
AU - Karrasaaqii Bulti Wakgari
AU - Nardos Bisrat
AU - Gelan Ayana
AU - Jude Kong
PY - 2026
DA - 2026/06/01
JO - npj Digital Medicine
DO - 10.1038/s41746-026-02944-4
UR - https://doi.org/10.1038/s41746-026-02944-4
AB - Acute flaccid paralysis (AFP) surveillance in Ethiopia remains limited due to hard-to-reach populations, restricted healthcare access, low public awareness, and persistent underreporting within community-based surveillance (CBS) systems. Contributing to this are inadequate training of community reporters, communication barriers, and cultural beliefs and misinformation that further hinder timely case detection. Here, AFP Assistant, a multilingual large language model powered chatbot, is developed to strengthen CBS through improved health communication and real-time reporting. The system supports Amharic, Afaan Oromo, and English to enhance accessibility and inclusivity. A curated dataset derived from literature, guidelines, and community interviews was translated and validated by experts to ensure clinical and cultural accuracy. The system integrates supervised fine-tuning with retrieval-augmented generation (RAG) to deliver accurate, context-aware responses. Trained on 468 question–answer pairs using pretrained Gemini 2.5-flash, the model achieved an accuracy of 0.90 and a loss of 0.31. The RAG framework improved retrieval relevance, grounding, and response efficiency. Evaluation through in-house testing and human annotation using a structured rubric demonstrated robust performance across tasks and languages, while user feedback confirmed usability and relevance. These findings highlight the potential of AI-driven chatbots to enhance AFP surveillance and equitable health communication in low-resource settings.
SN - 2398-6352
ER -