P.132 The role of large language models in neuroradiology: a scoping review and thematic analysis
Bibliographic record
Abstract
Background: Large language models (LLMs) have gained popularity in medicine, however, their roles in neuroradiology remain underexplored. This study aimed to evaluate the current landscape, identify evidence gaps, and propose future directions for LLMs in neuroradiology. Methods: A systematic literature search of PubMed, Embase, Web of Science, and Scopus was conducted to identify relevant studies published between January 1, 2010, and October 1, 2024. Two reviewers screened eligible studies and selected original research applying LLMs in neuroradiology for inclusion. Included studies were evaluated using thematic and geographical analyses to identify trends. Results: Of 287 identified studies, 57 met the inclusion criteria. Findings revealed a significant upward trend in publications since 2018, with an annual growth rate of 78.2%. Three main themes emerged: Operational Workflow Optimization (n=26, 45.6%), Diagnostic Decision Support (n=20, 35.1%), and Education and Training (n=11, 19.3%). Geographically, most studies originated from North America (n=23, 40.4%), Europe (n=19, 33.3%), and Asia (n=12, 21.1%), with limited contribution from other regions (n=3, 5.3%). Key knowledge gaps included strategies to mitigate hallucinations, enhance transparency, and safeguard patient privacy. Conclusions: LLMs are being applied in neuroradiology to support diagnostics, streamline workflows, and enhance education. Future research should prioritize clinical validation, promote ethical practices, and expand global involvement.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.071 | 0.184 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.006 |
| Bibliometrics | 0.030 | 0.035 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.006 | 0.011 |
| Open science | 0.003 | 0.007 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.008 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".