Clinically aligned rationale generation for glaucoma subtype classification via a knowledge-distilled language model
Moradi, M.; Fujita, A.; Bineshfar, N.; Vu, D. M.; Aziz, K.; Liebman, D.; Wang, M.; Elze, T.; Eslami, M.; Zebardast, N.
Show 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 and BERTScore F1 0.955, surpassing eight zero-shot comparators including GPT-4o and GPT-4.1, establishing privacy-preserving distillation as a path to interpretable AI.
Matching journals
The top 1 journal accounts for 50% of the predicted probability mass.
Similar papers in this journal
- Understanding the robustness of vision-language models to medical image artefacts 93%
- Equity-Enhanced Glaucoma Progression Prediction from OCT with Knowledge Distillation 92%
- Clinical Knowledge Extraction via Sparse Embedding Regression (KESER) with Multi-Center Large Scale Electronic Health Record Data 92%
Similar papers in this journal
- Artificial intelligence to facilitate clinical trial recruitment in age-related macular degeneration 93%
- Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3500 Inherited Retinal Disease Patients from the United Kingdom 92%
- Evaluating the Performance of ChatGPT in Ophthalmology: An Analysis of its Successes and Shortcomings 90%
Similar papers in this journal
- Whole-exome sequencing study identifies novel rare variants and genes associated with intraocular pressure and glaucoma 92%
- Deep representation learning for clustering longitudinal survival data from electronic health records 92%
- Integrating genetic regulation and single-cell expression with GWAS prioritizes causal genes and cell types for glaucoma 91%
Similar papers in this journal
- Advancing Question-Answering in Ophthalmology with Retrieval Augmented Generations (RAG): Benchmarking Open-source and Proprietary Large Language Models 91%
- AutoMorph: Automated Retinal Vascular Morphology Quantification via a Deep Learning Pipeline 91%
- Identification of Risk Factors for Glaucoma Progression in Free-Text Clinical Notes using a Local Small Language Model 90%
Similar papers in this journal
- Large Language Models Improve the Identification of Emergency Department Visits for Symptomatic Kidney Stones 92%
- Construction and optimization of multi-platform precision pathways for precision medicine 91%
- Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.