Clinical Note Generation From Doctor-Patient Conversations Using Parameter-Efficient Fine-Tuning Large Language Models: Comparative Study
Saib Ahmed, Farig Yousuf Sadeque · 2026
Read Clinical Note Generation From Doctor-Patient Conversations Using Parameter-Efficient Fine-Tuning Large Language Models: Comparative Study by Saib Ahmed, Farig Yousuf Sadeque (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13232911.txt.
Description
Saib Ahmed and Farig Yousuf Sadeque published a 2026 comparative study on software that drafts clinical notes from recorded doctor-patient conversations. Writing notes takes clinicians much time, and open conversation datasets are scarce. The pair tested whether large language models could be adapted cheaply, using parameter-efficient fine-tuning, a method that adjusts only a small part of a model.
They trained Mistral, Meditron, and Llama models on 1,700 conversation and note pairs. Meditron-7B and Llama3-8B earned the strongest scores on standard overlap and meaning measures, with Mistral-7B close behind. A physician also rated the drafts for accuracy, completeness, and readability. The results suggest small, efficiently tuned models can produce usable notes without heavy computing resources.
Catalog record
| CREATOR | Saib Ahmed, Farig Yousuf Sadeque |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |