aiqbench analysis
This research introduces the COME framework, a Transformer-based approach that explicitly models data heterogeneity across multiple medical centers to improve dementia etiology diagnosis. By integrating meta-information about acquisition semantics and modality availability alongside trust-region constrained optimization, the method achieves state-of-the-art performance while reducing reliance on spurious correlations. The study validates its robustness through superior generalization in cross-center evaluations and alignment with established clinical biomarkers like amyloid and tau levels.
Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement
arXiv:2607.22770v1 Announce Type: new Abstract: Although artificial intelligence (AI) has shown promising performance in several medical tasks, accurate dementia etiology diagnosis with AI remains challenging due to complex overlapping symptoms among diseases. Scaling up the dataset size by combining the cross-center samples may bring a gain in the pursuit of performance, while the inherent data heterogeneity across centers or populations induces the conflict. Conventional multi-task learning paradigms offer a promising framework; however, they fail to consider critical meta information (e.g., site-specific acquisition and modality availability) to combat the heterogeneity. To address this challenge, we propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis, which injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training, enabling explicit modeling of heterogeneity. Besides, a trust-region constrained optimization scheme is designed to regularize the model from spurious correlations during training through a reference model. Across seven independent cohorts, our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline, while maintaining superior out-of-domain generalization under both cross-center and cross-sequence evaluations. Extensive validation also confirms the alignment between model predictions and established biomarkers (amyloid, tau) and clinical severity, highlighting the potential of COME to enable robust and interpretable dementia diagnostics in real-world settings.
Abstract:Although artificial intelligence (AI) has shown promising performance in several medical tasks, accurate dementia etiology diagnosis with AI remains challenging due to complex overlapping symptoms among diseases. Scaling up the dataset size by combining the cross-center samples may bring a gain in the pursuit of performance, while the inherent data heterogeneity across centers or populations induces the conflict. Conventional multi-task learning paradigms offer a promising framework; however, they fail to consider critical meta information (e.g., site-specific acquisition and modality availability) to combat the heterogeneity. To address this challenge, we propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis, which injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training, enabling explicit modeling of heterogeneity. Besides, a trust-region constrained optimization scheme is designed to regularize the model from spurious correlations during training through a reference model. Across seven independent cohorts, our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline, while maintaining superior out-of-domain generalization under both cross-center and cross-sequence evaluations. Extensive validation also confirms the alignment between model predictions and established biomarkers (amyloid, tau) and clinical severity, highlighting the potential of COME to enable robust and interpretable dementia diagnostics in real-world settings.
Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2607.22770 [cs.LG]
(or arXiv:2607.22770v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.22770 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 316 words
Related coverage
GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis
arXiv · Jul 20, 2026
MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM
arXiv · Aug 25, 2026
SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence
arXiv · Sep 1, 2026
Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models
arXiv · Jun 9, 2026