Automated Radiology Report Labeling in Chest X-Ray Pathologies: Development and Evaluation of a Large Language Model Framework
Bibliographic record
Abstract
Background: Labeling unstructured radiology reports is crucial for creating structured datasets that facilitate downstream tasks, such as training large-scale medical imaging models. Current approaches typically rely on Bidirectional Encoder Representations from Transformers (BERT)-based methods or manual expert annotations, which have limitations in terms of scalability and performance. Objective: This study aimed to evaluate the effectiveness of a generative pretrained transformer (GPT)-based large language model (LLM) in labeling radiology reports, comparing it with 2 existing methods, CheXbert and CheXpert, on a large chest X-ray dataset (MIMIC Chest X-ray [MIMIC-CXR]). Methods: In this study, we introduce an LLM-based approach fine-tuned on expert-labeled radiology reports. Our model's performance was evaluated on 687 radiologist-labeled chest X-ray reports, comparing F1 scores across 14 thoracic pathologies. The performance of our LLM model was compared with the CheXbert and CheXpert models across positive, negative, and uncertainty extraction tasks. Paired t tests and Wilcoxon signed-rank tests were performed to evaluate the statistical significance of differences between model performances. Results: The GPT-based LLM model achieved an average F1 score of 0.9014 across all certainty levels, outperforming CheXpert (0.8864) and approaching CheXbert's performance (0.9047). For positive and negative certainty levels, our model scored 0.8708, surpassing CheXpert (0.8525) and closely matching CheXbert (0.8733). Statistically, paired t tests indicated no significant difference between our model and CheXbert (P=.35) but a significant improvement over CheXpert (P=.01). Wilcoxon signed-rank tests corroborated these findings, showing no significant difference between our model and CheXbert (P=.14) but confirming a significant difference with CheXpert (P=.005). The LLM also demonstrated superior performance for pathologies with longer and more complex descriptions, leveraging its extended context length. Conclusions: The GPT-based LLM model demonstrates competitive performance compared with CheXbert and outperforms CheXpert in radiology report labeling. These findings suggest that LLMs are a promising alternative to traditional BERT-based architectures for this task, offering enhanced context understanding and eliminating the need for extensive feature engineering. Furthermore, with large context length LLM-based models are better suited for this task as compared with the small context length of BERT based models.
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 | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".