Establish genuine clinical agreement between CMTN and radiologist judgment
Establish whether the Cross-Modal Triage Network (CMTN) can achieve clinically valid severity-triage agreement with independent radiologist judgment rather than merely reproducing severity labels generated by the CheXpert natural-language-processing pipeline.
References
The Phase I audit is the only evaluation in this study that measures agreement with authentic clinical judgment directly, and it indicates that CMTN has not yet demonstrated this capability.
— Cross-modal triage network: a multimodal deep learning framework for severity-based triage and visual explainability in chest radiographs
(2609.04357 - Ghulam et al., 3 Sep 2026) in Section 4, Discussion
It also fits two other explanations, noise in the gold labels and a mismatch between our rubric and the annotators' own; with one annotator and no access to the original guidelines, we cannot tell these apart.
— Structure vs. Chain-of-Thought: Evaluating LLM Criteria Extraction for Depression Severity
(2609.39049 - Chen, 30 Sep 2026) in Section 5.5, “Can a human reader recover the labels?”