Back to feed
AR
arXiv CS.AI
7/14/2026
From ML Predictions to Informed Diagnostic Assistance Using the Toulmin Model of Argumentation

From ML Predictions to Informed Diagnostic Assistance Using the Toulmin Model of Argumentation

Short summary

This paper applies the Toulmin model of argumentation to decompose ML-based retinal diagnoses into structured components: claim, grounds, warrant, qualifier, and rebuttal. A MedGemma agent provides medical-knowledge warrants, while MedSigLip computes image-similarity-based rebuttals. The framework presents all components to human experts for more informed and critical assessment of AI-generated diagnoses.

  • •Decomposes ML diagnosis into Toulmin argumentation components (claim, grounds, warrant, qualifier, rebuttal)
  • •MedGemma agent supplies medical-knowledge warrants; MedSigLip generates rebuttals via image similarity
  • •Targets interpretable, human-reviewable AI diagnostic assistance for retinal imaging

Generated with AI, which can make mistakes.

#research-breakthrough#ai-tools
Read full article at arXiv CS.AI

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

The original title is a survey title, not a news headline. I need to rewrite it as a news headline for a mobile feed.
arXiv CS.AI
Discourse-Aware Policy Analysis with Argumentation: A Hybrid LLM-Symbolic Framework for Disaster Governance
arXiv cs.CL
GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis
arXiv CS.AI
RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotation
arXiv CS.AI