发表机构
School of Computer Science, Fudan University; Cooperative Medianet Innovation Center, Shanghai Jiao Tong University; Microsoft Research Asia; School of Artificial Intelligence, Shanghai Jiao Tong University（复旦大学计算机科学学院; 上海交通大学协同媒体网络创新中心; 微软亚洲研究院; 上海交通大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对痴呆病因诊断中因数据异质性导致的挑战，提出协作元知识增强（COME）框架，将多中心采集语义等作为异质性感知嵌入注入Transformer架构，并设计优化方案。该方法在多队列中性能达最优，有良好泛化能力，还能与生物标志物及临床严重程度一致。
AI 中文摘要
尽管人工智能在多项医疗任务中表现出良好性能，但由于疾病间症状复杂重叠，利用人工智能进行准确的痴呆病因诊断仍具有挑战性。通过合并跨中心样本扩大数据集规模虽可能提升性能，但中心或人群间固有的数据异质性会引发冲突。传统多任务学习范式虽提供了有前景的框架，但未能考虑关键元信息来应对异质性。为此，我们提出用于痴呆病因诊断的协作元知识增强（COME）框架，将多中心采集语义、源标识符和模态指标作为异质性感知嵌入注入统一Transformer架构进行扩大规模训练，实现对异质性的显式建模。此外，设计了信任区域约束优化方案在训练期间通过参考模型对模型进行正则化，防止虚假关联。在七个独立队列中，我们的方法实现了最先进的域内性能，平均宏平均AUC为85.62%，比最强基线提高了4.29个百分点，同时在跨中心和跨序列评估下保持了卓越的域外泛化能力。广泛验证还证实了模型预测与既定生物标志物（淀粉样蛋白、tau）及临床严重程度之间的一致性，凸显了COME在现实环境中实现强大且可解释的痴呆诊断的潜力。
英文摘要
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.
