Bridging the Gap with Retrieval-Augmented Generation: Making Prosthetic Device User Manuals Available in Marginalised Languages

2025-06-30

AI Summary

Millions of people across Africa face barriers to accessing critical health information due to linguistic diversity and low literacy rates—particularly evident in the absence of localized user manuals for donated prosthetic devices. To address this, we propose a lightweight, open-source medical document localization framework tailored for low-resource languages. It integrates retrieval-augmented generation (RAG) with multilingual NLP techniques to enable cross-lingual semantic understanding, generative question answering, and real-time translation. The framework is designed for rapid adaptation to marginalized languages and deployable on resource-constrained edge devices. Experimental evaluation demonstrates its efficacy in transforming English prosthetic manuals into linguistically appropriate, comprehensible local-language versions. End users can query the system in their native language and receive accurate, context-aware safety alerts and operational guidance. Results indicate significant improvements in patient self-management and frontline healthcare decision-making, offering a scalable technical pathway toward global health information equity.

Technology Category

Humans and AI: AI for AccessibilityNatural Language Processing: Safety and RobustnessComputer Vision: Language and Vision

Application Category

Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web searchSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applicationsUser Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Millions of people in African countries face barriers to accessing healthcare due to language and literacy gaps. This research tackles this challenge by transforming complex medical documents -- in this case, prosthetic device user manuals -- into accessible formats for underserved populations. This case study in cross-cultural translation is particularly pertinent/relevant for communities that receive donated prosthetic devices but may not receive the accompanying user documentation. Or, if available online, may only be available in formats (e.g., language and readability) that are inaccessible to local populations (e.g., English-language, high resource settings/cultural context). The approach is demonstrated using the widely spoken Pidgin dialect, but our open-source framework has been designed to enable rapid and easy extension to other languages/dialects. This work presents an AI-powered framework designed to process and translate complex medical documents, e.g., user manuals for prosthetic devices, into marginalised languages. The system enables users -- such as healthcare workers or patients -- to upload English-language medical equipment manuals, pose questions in their native language, and receive accurate, localised answers in real time. Technically, the system integrates a Retrieval-Augmented Generation (RAG) pipeline for processing and semantic understanding of the uploaded manuals. It then employs advanced Natural Language Processing (NLP) models for generative question-answering and multilingual translation. Beyond simple translation, it ensures accessibility to device instructions, treatment protocols, and safety information, empowering patients and clinicians to make informed healthcare decisions.

Problem

• Translating prosthetic manuals into marginalized languages
• Overcoming language barriers in healthcare access
• Enabling real-time multilingual medical Q&A

Innovation

• Uses Retrieval-Augmented Generation for document processing
• Integrates NLP for multilingual question-answering
• Open-source framework for marginalized language translation