Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices

Source

arXiv

arxiv.org/abs/2608.12025v1

Read the source

Source

  • Source name: arXiv
  • Source kind: paper
  • Authors / organization: Tuhinangshu Gangopadhyay, Rasmus Adler, Peter Liggesmeyer, Jan Reich
  • Venue: arXiv: cs.SE
  • Published: 2026-08-12
  • Collected: 2026-08-13
  • URL: http://arxiv.org/abs/2608.12025v1
  • PDF: https://arxiv.org/pdf/2608.12025v1
  • DOI: UNKNOWN
  • Registry group: academic_apis_and_preprints
  • Evidence role: canonical_academic_index
  • Language: en
  • Country / region: UNKNOWN

Plain-Language Brief

The paper proposes a framework for medical device safety using Large Language Models (LLMs). The goal is to streamline the process of managing risk-management evidence in medical devices that are becoming increasingly software-intensive and AI-enabled.

What the Document Says

  • Medical devices are becoming more software-intensive, connected, and AI-enabled.
  • The development of these devices requires risk-management evidence aligned with ISO 14971 and IEC 62304.
  • This evidence needs to be kept consistent across various stages such as requirements, design decisions, software changes, verification results, complaints, and post-market data.
  • The process is costly and depends on scarce safety and domain experts.
  • Large Language Models (LLMs) could potentially reduce parts of this effort due to the document-based nature of medical-device safety work.
  • Current LLM-based safety engineering studies have limitations such as addressing isolated methods, relying on generic prompting or public examples, and providing limited support for traceability, uncertainty handling, lifecycle updates, and recorded expert review.
  • The paper argues that the central research problem is not safety-text generation, but source-linked safety-knowledge support.
  • The proposed framework connects device artifacts, controlled knowledge storage and retrieval, method-specific generation of candidate safety items, critique and uncertainty checks, and recorded expert review.
  • The framework prepares, links, checks, and updates candidate safety artifacts for expert decision-making.
  • It does not decide whether a device is safe and does not provide regulatory approval.
  • An evaluation strategy is outlined using non-public or newly built medical-device case studies and expert reference analyses to assess the framework's performance.

Key Concepts Mentioned

  • Medical devices
  • Safety evidence
  • ISO 14971
  • IEC 62304
  • Large Language Models (LLMs)
  • Risk management
  • Safety-knowledge support
  • Document-based work
  • Expert review

Claims Made by the Document

  • LLMs could potentially reduce parts of the costly and expert-dependent safety evidence process in medical device development.

Evidence Used

  • The text mentions that current LLM-based studies have limitations, implying a need for improvement. The proposed framework aims to address these limitations.

Methods / Approach

  • Proposing an evidence-grounded framework
  • Outlining an evaluation strategy

Limitations Stated by the Authors

  • The proposed framework is still a proposal and has not been implemented or tested.
  • The evaluation strategy involves non-public or newly built medical-device case studies, which may limit its generalizability.

Limitations Noted by the Agent

Agent interpretation — not from the source.

  • The agent might struggle to implement the proposed framework without access to necessary resources, such as medical devices and safety experts.
  • The agent might not be able to conduct a comprehensive evaluation due to limitations in available data.

Open Questions

  • What specific methods will be used for controlled knowledge storage and retrieval?
  • How will the framework handle uncertainties beyond critique checks?

Notes for Future Q&A

May include interpretation. Labeled where it does.

  • The text does not provide details about the specific methods for controlled knowledge storage and retrieval.
  • The text mentions uncertainty handling but does not specify how it will be addressed beyond critique checks.

Raw Abstract / Excerpt

Medical devices are becoming more software-intensive, connected, and AI-enabled. Their development requires risk-management evidence aligned with ISO 14971 and, for software, IEC 62304. This evidence must be kept consistent across requirements, design decisions, software changes, verification results, complaints, and post-market data. These tasks are costly and depend on scarce safety and domain experts. Large language models (LLMs) may reduce parts of this effort because medical-device safety work is highly document-based. However, current LLM-based safety-engineering studies often address isolated methods, rely on generic prompting or public examples, and provide limited support for source links, traceability, uncertainty handling, lifecycle updates, and recorded expert review. This limits their use in regulated medical-device development. This paper argues that the central research problem is not safety-text generation, but source-linked safety-knowledge support. We propose an evidence-grounded framework that connects device artifacts, controlled knowledge storage and retrieval, method-specific generation of candidate safety items, critique and uncertainty checks, and recorded expert review. The framework prepares, links, checks, and updates candidate safety artifacts for expert decision-making. It does not decide whether a device is safe and does not provide regulatory approval. We also outline an evaluation strategy using non-public or newly built medical-device case studies and expert reference analyses to assess coverage, correctness, relevance, traceability, duplicate rate, unsupported claims, and review effort.