Applications and Gaps of Generative AI in the Medical Device Lifecycle: A Scoping Review

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.

Authors

Institutions

Publication Details

Journal
Bioengineering
Published
2026-11-19
DOI
https://doi.org/10.3390/bioengineering13111385
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Applications and Gaps of Generative AI in the Medical Device Lifecycle: A Scoping Review

Alessio Luschi, Ali Hamza Salman, Ernesto Iadanza, Adna Softić et al.
Bioengineering
Artificial Intelligence in Healthcare and Education
article

Applications and Gaps of Generative AI in the Medical Device Lifecycle: A Scoping Review

Alessio Luschi, Ali Hamza Salman, Ernesto Iadanza, Adna Softić, Alessio Rotelli
article en

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.

BioengineeringVol. 13(11)
University of Siena (IT)
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon