A multimodal evidence-driven framework for clinical decision support in cognitive impairment.
Adding retrieval-augmented reasoning to the model improved diagnostic accuracy in external validation.
A multimodal evidence-driven framework for clinical decision support in cognitive impairment.
Deep learning approaches for cognitive impairment diagnosis have shown considerable promise, but their clinical translation remains limited by poor interpretability and weak linkage between model outputs and established medical evidence.
In external validation on a heterogeneous cohort with primary labels, integrating retrieval-augmented large language model with the mHC improved all evaluation metrics, increasing overall accuracy from 0.706 ± 0.038 to 0.753 ± 0.032.
adding retrieval-augmented reasoning raised external validation accuracy
Multimodal Evidence-Driven Reasoning Framework leverages routinely collected non-invasive data from clinical profiles and structural MRI to identify cognitive impairment stages and etiologies.
Across 15 diagnostic labels, mHC outperformed flat multimodal baselines, supporting hierarchical diagnostic modeling.
Physician review further indicated favorable quality and perceived usefulness of the generated reports.
By synthesizing hierarchical prediction with evidence-grounded reasoning, Multimodal Evidence-Driven Reasoning Framework provides a robust interpretable framework for decision support, particularly in incomplete or diagnostically ambiguous presentations.