Applications and Gaps of Generative AI in the Medical Device Lifecycle: A Scoping Review
Year: 2026
Type: article
Study design: Systematic Review
Abstract: Generative artificial intelligence (GenAI), including large language models, retrieval-augmented generation (RAG), and multi-agent systems, is used both as a tool around the medical device lifecycle and, less often, inside devices. These uses should not be conflated. This scoping review characterises current applications in design, regulatory management, maintenance, and risk assessment, and identifies where published evidence is thinnest. PubMed, IEEE Xplore, Scopus, and arXiv were searched for 2022–2026 studies applying GenAI to hardware devices, SaMD, or medical wearables. Sixty-one studies were charted with the population–concept–context framework and mapped to the four pillars. Most included work is experimental. Reports cluster in regulatory document analysis and in risk or cybersecurity modelling. Live maintenance and generative hardware design remain sparse in this search. RAG and agent pipelines are commonly used to ground outputs, but published metrics are task-specific and do not demonstrate automated MDR or FDA compliance. GenAI can assist retrieval and drafting across the lifecycle, yet longitudinal real-world validation and human-in-the-loop controls are still scarce. In this corpus, operationally validated maintenance and in-device safety systems are the thin end of the map, not another document-mining prototype.
Source: Bioengineering
Institution: University of Siena
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Keywords: generative AI, medical device lifecycle, large language models, retrieval-augmented generation, multi-agent systems, medical device regulation, medical equipment maintenance, medical device cybersecurity, software as a medical device, wearable medical devices, FDA compliance, hardware design
Open Access status: gold
Estimated APC paid: $3,258
OpenAlex ID: W7236849090
