The role of large language models in medical device´s technical file management
Salonen, Jesse (2025)
2025
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-202503013526
https://urn.fi/URN:NBN:fi:amk-202503013526
Tiivistelmä
This thesis explores how Large Language Models (LLMs) can improve the management of technical files in the medical device industry. The research was inspirated by the need to address the challenges of creating, updating, and maintaining technical documentation in a highly regulated environment.
The research followed a design methodology, combining a literature review with expert interviews to discover challenges in traditional working methods and assess the feasibility of AI-driven solutions. Key findings revealed significant opportunities to automate and optimize tasks with AI and LLM. Requirement specifications were developed for six AI-based tools, each designed to address specific pain points.
The result of the thesis shows that AI tools can reduce time spent on routine tasks while improving the accuracy and consistency of technical documentation. However, challenges such as ensuring data security and managing AI "hallucinations" must be taken to account.
The research followed a design methodology, combining a literature review with expert interviews to discover challenges in traditional working methods and assess the feasibility of AI-driven solutions. Key findings revealed significant opportunities to automate and optimize tasks with AI and LLM. Requirement specifications were developed for six AI-based tools, each designed to address specific pain points.
The result of the thesis shows that AI tools can reduce time spent on routine tasks while improving the accuracy and consistency of technical documentation. However, challenges such as ensuring data security and managing AI "hallucinations" must be taken to account.