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

arXiv: https://arxiv.org/abs/2607.09664 · HTML: https://mlsanity.com/paper/2607.09664/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 2 of 2)

- [OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods](https://mlsanity.com/paper/2312.08255/) (2023)
- [From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning](https://mlsanity.com/paper/2604.11137/) (2026)

## Built on by (most cited first, 1 of 1)

- [Review Before Trust: Source-Grounded Integrity Gates for AI-Assisted Personal Health Records](https://mlsanity.com/paper/2608.29965/) (2026)

## Abstract (arXiv)

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.