Article

Clinically aligned rationale generation for glaucoma subtype classification via a knowledge-distilled language model

2026-06-26

Abstract excerpt

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 0.7...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: a1e58b4a-a30b-5db0-a334-b402ed6b867c
DOI: 10.64898/2026.06.15.26355522

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Clinically aligned rationale generation for glaucoma subtype classification via a knowledge-distilled language modelDOI 10.64898/2026.06.15.26355522Read

Learning Ophthalmologist Clinical Reasoning for Glaucoma Diagnosis from Fundus ImagesSemantic proximity Read

GlaucoRAG: A Retrieval-Augmented Large Language Model for Expert-Level Glaucoma AssessmentSemantic proximity Read

Open-source DeepSeek-R1 Outperforms Proprietary Non-Reasoning Large Language Models With and Without Retrieval-Augmented GenerationSemantic proximity Read

OphthaBERT: Automated Glaucoma Diagnosis from Clinical NotesSemantic proximity Read

Ophtimus-V2-Tx: A Compact Domain-Specific LLM for Ophthalmic Diagnosis and Treatment PlanningSemantic proximity Read

Clinically Informed Semi-Supervised Learning Improves Disease Annotation and Equity from Electronic Health Records: A Glaucoma Case StudySemantic proximity Read

Glaucoma Detection Using Deep Learning and Prompt-Based Explainable Report GenerationSemantic proximity Read

MAP-RAG: A Multi-View Adaptive Pattern-Aware Medical Retrieval-Augmented Generation Diagnostic FrameworkSemantic proximity Read

Compact Vision–Language Models Enable Efficient and Interpretable Automated OCT Analysis Through Layer Specific Multimodal LearningSemantic proximity Read

Evaluating a Large Reasoning Model’s Performance on Open-Ended Medical ScenariosSemantic proximity Read

Fostering transparent medical image AI via an image-text foundation model grounded in medical literatureSemantic proximity Read