MétaCan
Menu
Back to cohort
Record W4410782593 · doi:10.3390/ai6060109

What We Know About the Role of Large Language Models for Medical Synthetic Dataset Generation

2025· article· en· W4410782593 on OpenAlex

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.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueAI · 2025
Typearticle
Languageen
FieldComputer Science
TopicMachine Learning in Healthcare
Canadian institutionsnot available
FundersFundação para a Ciência e a Tecnologia
KeywordsComputer scienceNatural language processingData science

Abstract

fetched live from OpenAlex

Synthetic medical text generation has emerged as a solution to data scarcity and privacy constraints in clinical NLP. This review systematically evaluates the use of Large Language Models (LLMs) for structured medical text generation, examining techniques such as retrieval-augmented generation (RAG), structured fine-tuning, and domain-specific adaptation. Four search queries were applied following the PRISMA methodology to identify and extract data from 153 studies. Key benchmarking metrics, such as performance measures, and qualitative insights, including methodological trends and challenges, were documented. The results show that while LLM-generated text improves fluency, hallucinations and factual inconsistencies persist. Structured consultation models, such as SOAP and Calgary–Cambridge, enhance coherence but do not fully prevent errors. Hybrid techniques that combine retrieval-based grounding with domain-specific fine-tuning improve factual accuracy and task performance. Conventional evaluation metrics (e.g., ROUGE, BLEU) are insufficient for medical validation, highlighting the need for domain-specific benchmarks. Privacy-preserving strategies, including differential privacy and PHI de-identification, support regulatory compliance but may reduce linguistic quality. These findings are relevant for clinical NLP applications, such as AI-powered scribe systems, where structured synthetic datasets can improve transcription accuracy and documentation reliability. The conclusions highlight the need for balanced approaches that integrate medical structure, factual control, and privacy to enhance the usability of synthetic medical text.

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)0.001
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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.983
Threshold uncertainty score0.167

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
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 head0.014
GPT teacher head0.341
Teacher spread0.327 · 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