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

Researchers propose a framework that decomposes ML-based retinal diagnosis using the Toulmin model of argumentation, where a MedGemma agent analyzes the warrant linking biomarker evidence to the diagnosis, and a rebuttal is generated via MedSigLip image similarity. The approach aims to provide structured, interpretable assessments to help clinicians critically evaluate ML predictions.

arXiv:2607.09664v1 Announce Type: new Abstract: To provide a structured and interpretable assessment, we decompose the image-based diagnosis into components following the Toulmin model of argumentation. This model consists of a claim, grounds, warrant, qualifier, rebuttal, and backing. Consider a claim generated by a machine learning ML model for retinal diagnosis. Rather than accepting this claim at face value, one could either apply explainable AI XAI methods or adopt an argumentation-based approach. In our framework, a model specialized in biomarker extraction from images provides the grounds. The warrant-linking the grounds to the claim - is analyzed by an agent equipped with medical knowledge; in our architecture, this role is fulfilled by a MedGemma agent. The qualifier is determined based on the overall quantitative evaluation of both the warrant and grounds models. Finally, a rebuttal is constructed using image similarity measures computed with MedSigLip. All these components are presented to the human expert, enabling a more informed and critical assessment of the ML-generated diagnosis.