MedSlice: fine-tuned large language models for secure clinical note sectioning
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.
Bibliographic record
Abstract
Objectives: Extracting sections from clinical notes is crucial for downstream analysis but is challenging due to variability in formatting and labor-intensive nature of manual sectioning. This study develops a pipeline for automated note sectioning using open-source large language models (LLMs), focusing on three sections: History of Present Illness, Interval History, and Assessment and Plan. Materials and Methods: We fine-tuned three open-source LLMs to extract sections using a curated dataset of 487 progress notes, comparing results relative to proprietary models (GPT-4o, GPT-4o mini). Internal and external validity were assessed via precision, recall, and F1 score. Results: Fine-tuned Llama 3.1 8B (F1 = 0.92) outperformed GPT-4o. On the external validity test set, performance remained high (F1 = 0.85). Discussion: While proprietary LLMs have shown promise, privacy concerns limit their utility in medicine; fine-tuned, open-source LLMs offer advantages in cost, performance, and accessibility. Conclusion: Fine-tuned, open-source LLMs can surpass proprietary models in clinical note sectioning.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it