MétaCan
Menu
Back to cohort
Record W4409657910 · doi:10.1097/rct.0000000000001709

Beyond Human Limits: The Promise and Pitfalls of Large Language Models in Radiology Research

2025· review· en· W4409657910 on OpenAlex
Evie Nguyen, Lauren F. Alexander, Rajesh Bhayana, Zoe Deahl, Ashish Khandelwal, Maria Zulfiqar, Nelly Tan

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueJournal of Computer Assisted Tomography · 2025
Typereview
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsToronto General Hospital
Fundersnot available
KeywordsMedicineProductivityEngineering ethicsData scienceComputer science

Abstract

fetched live from OpenAlex

This review examines the applications and challenges of large language models (LLMs), like OpenAI's ChatGPT, in radiology research. ChatGPT can assist radiology researchers in generating new ideas, finding and summarizing research papers, designing studies, analyzing data, and facilitating manuscript writing. LLMs are powerful tools with numerous applications in radiology research. However, users should be mindful of potential pitfalls, such as producing incorrect or biased outputs and inconsistent responses, along with ethical and privacy concerns. We discuss approaches to optimize models and address these issues, including prompting techniques like chain-of-thought prompting, retrieval-augmented generation, and fine-tuning. For researchers, prompt engineering can be particularly effective. This review seeks to demonstrate how researchers can utilize ChatGPT for radiology research while offering strategies to mitigate associated risks. We aim to help researchers harness these potent tools to safely boost their productivity.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.981
Threshold uncertainty score0.589

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0020.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.215
GPT teacher head0.504
Teacher spread0.290 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it