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

Oct 22, 2026

Uploaded by Patrick

Millions of people in African countries face barriers to accessing healthcare due to language and literacy gaps. This research converts complex medical documents—prosthetic device user manuals—into accessible, localised formats for underserved populations. It demonstrates a case study using Pidgin and an open-source framework to extend to other languages and dialects. The proposed AI system enables uploads of English manuals, multilingual question answering, and real-time, safety-focused guidance for users and clinicians.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages5

Reading Time13 min

AccessFree to download

Abstract

Introduction

Bridging the Gap with Retrieval-Augmented Generation: Making Prosthetic Device User Manuals Available in Marginalised Languages Ikechukwu Ogbonna 1,*, Lesley Davidson2, Soumya Banerjee3, Abhishek Dasgupta4, Laurence Kenney2, and Vikranth Harthikote Nagaraja2,\# 1Department of Biomechanical Engineering, Faculty of Science and Technology, University of Twente, Enschede, Netherlands; 2Centre for Human Movement and Rehabilitation, School of Health and Society, University of Salford, Salford, M6 6PU, UK; 3Department of Computer Science & Technology, University of Cambridge, 15 J.J. Thomson Ave., Cambridge, CB3 0FD, UK; 4Doctoral Training Centre, University of Oxford, 1–4 Keble Road, Oxford, OX1 3NP, UK. *[i.i.ogbonna@student.utwente.nl](i.i.ogbonna@student.utwente.nl |#v.harthikotenagaraja@salford.ac.uk)[ |](i.i.ogbonna@student.utwente.nl |#v.harthikotenagaraja@salford.ac.uk)[\#](i.i.ogbonna@student.utwente.nl |#v.harthikotenagaraja@salford.ac.uk)[v.harthikotenagaraja@salford.ac.uk](i.i.ogbonna@student.utwente.nl |#v.harthikotenagaraja@salford.ac.uk) 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 AIpowered 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 questionanswering 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. This framework supports integrating additional languages, making it adaptable to a wide range of global health challenges, including public health campaigns and disaster relief, where accurate communication in native languages can save lives. With far-reaching implications, this research serves as an interim solution for health organisations/providers in such communities and a call to action for policymakers and governments of the Global South to reduce inequities in accessing critical medical information. Overall, it offers a vision of healthcare that empowers marginalised communities, fosters trust, and ensures no one is left behind due to language or literacy barriers. 1 Introduction Prosthetic manufacturers provide support for their products, and the relevant details are typically outlined within the product documentation. User manuals are crucial since they provide end users with critical information regarding safety, device limitations, and appropriate use. Such guidelines are intended to influence user behaviour(s) with their prosthetic limb. However, in African countries, it is common practice to accept secondhand assistive technologies like p

FAQs

What problem does the research address?

It addresses language and literacy barriers that prevent underserved populations in African countries from understanding healthcare materials, specifically prosthetic device user manuals.

How does the proposed system work at a high level?

Users upload English-language manuals, ask questions in their native language, and receive accurate, localised answers in real time. The system uses a retrieval-augmented generation pipeline plus NLP models for multilingual generative question answering and translation.

Why is translation of prosthetic manuals especially important?

User manuals provide critical safety, limitations, and proper-use guidance. Lack of access to appropriate manuals can increase frustration and improper use, potentially leading to harm and underutilisation of devices.

Oct 22, 2026

Uploaded by Patrick