Fine-tuning medical large language models for differential diagnosis: from synthetic data to real-world evaluation

Date

2026-1

Author

Çavaş, Ezgi

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

66
views

38
downloads

Cite This

Access to large-scale, annotated Electronic Health Records (EHR) is limited by privacy rules. This creates a major setback for training strong clinical natural language processing (NLP) models. Synthetic data provides a way to protect privacy, but how well synthetic text works for fine-tuning large language models (LLMs) in real-world tasks is still an important issue to explore. Our thesis presents a framework that uses synthetic patient summaries to fine-tune a medical LLM model for multi-label disease diagnosis. This approach offers a cost-effective and privacy-focused method for creating clinical diagnostic tools with minimal use of sensitive real-world data. The results show that synthetic data can successfully reshape the medical models. This also helps the hospitals that are struggling with triage and the overcrowding of patients.

Subject Keywords

Clinical transformers, Synthetic data augmentation, Electronic health records, Computational phenotyping

URI

https://hdl.handle.net/11511/118704

Collections

Graduate School of Natural and Applied Sciences, Thesis