发表机构
Université Paris-Est Créteil (UPEC); Université Sorbonne Paris Nord (USPN)（巴黎东部克雷泰伊大学; 巴黎北部索邦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对阿尔茨海默病预测的问题，提出含SFCN MRI编码器等的多模态多任务框架，在多数据集上取得良好预测性能，可处理缺失模态并支持亚组评估。
AI 中文摘要
阿尔茨海默病预测存在随访不规律、测量指标异质及模态不完整的问题。本研究提出一种多模态多任务框架，结合适配的SFCN MRI编码器、四个因果临床Transformer、共享融合模块及任务特定的ODE-GRU动态模块；通过微调与LoRA适配最终两个MRI模块，Task-DRO平衡任务损失，Group-CVaR针对队列与共病分层。分支特定输入控制、按受试者分组的划分及经验因果性检查支持纵向评估。在ADNI、OASIS-2和MIRIAD的2649名受试者及17317次随访中，内部验证的诊断、1期进展、1期首次随访进展AUROC分别为0.935±0.002、0.884±0.003、0.870±0.005（3个随机种子的均值±标准差），对应混合AUROC为0.951、0.909、0.896；下一次随访MMSE平均绝对误差（MAE）为1.61分，最差分层诊断AUROC为0.827±0.008。对ADNI的采样解释识别出任务特定的输入依赖，OASIS-3外部验证的网络与混合诊断AUROC为0.763、0.767，混合下一次随访进展AUROC为0.764，诊断校准误差从0.197降至0.052，下一次随访MMSE MAE为0.86。对6个组件的种子42配对消融实验显示，合并诊断与进展AUROC差异在-0.004至+0.004之间，移除临床编码器输入使诊断AUROC降低0.272。该框架在统一流程中整合了纵向预测、缺失模态处理、辅助共病建模及亚组评估。
英文摘要
Alzheimer's disease prediction involves irregular visits, heterogeneous measurements and incomplete modalities. This study presents a multimodal multitask framework combining an adapted SFCN MRI encoder, four causal clinical Transformers, shared fusion and task-specific ODE-GRU dynamics. Fine-tuning and LoRA adapt the final two MRI blocks. Task-DRO balances task losses, while Group-CVaR targets cohort and comorbidity strata. Branch-specific input controls, subject-grouped partitions and empirical causality checks support longitudinal evaluation. Across 2,649 subjects and 17,317 visits from ADNI, OASIS-2 and MIRIAD, internal validation yields diagnosis, stage-1 progression and first-stage-1-visit progression AUROCs of 0.935 +/- 0.002, 0.884 +/- 0.003 and 0.870 +/- 0.005, respectively (mean +/- SD across three seeds). Corresponding hybrid AUROCs are 0.951, 0.909 and 0.896. Next-visit MMSE mean absolute error (MAE) is 1.61 points; worst-stratum diagnosis AUROC is 0.827 +/- 0.008. Sampled ADNI explanations identify task-specific input dependence. OASIS-3 external validation yields network and hybrid diagnosis AUROCs of 0.763 and 0.767, hybrid next-visit progression AUROC of 0.764, diagnosis calibration error decreasing from 0.197 to 0.052, and next-visit MMSE MAE of 0.86. Seed-42 paired ablations of six components yield pooled diagnosis and progression AUROC differences between -0.004 and +0.004; removing clinical encoder inputs lowers diagnosis AUROC by 0.272. The framework integrates longitudinal prediction, missing-modality handling, auxiliary comorbidity modelling and subgroup evaluation within a common pipeline.
