Clinically aligned rationale generation for glaucoma subtype classification via a knowledge-distilled language model
Discuss this preprint
Start a discussion What are Sciety discussions?Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Automated glaucoma subtype classification from clinical notes remains clinically unactionable without subspecialty-aligned explanations supporting clinician-facing deployment. We extended our Ci-SSGAN with a GPT-5.2-to-Qwen3-8B teacher-distilled reasoning module, fine-tuning Qwen3-8B on 2,660 de-identified ophthalmology notes using expert-reviewed rationales. On 294 notes, the fine-tuned model achieved ROUGE-L 0.792 ± 0.013 and BERTScore F1 0.955 ± 0.004, surpassing eight zero-shot comparators including GPT-4o and GPT-4.1, establishing privacy-preserving distillation as a path to interpretable AI.
