An Lijun, Pichet-Binette Alexa, Hristovska Ines, Vilkaite Gabriele, Yu Xiao, Smets Bart, Saloner Rowan, Tasaki Shinya, Xu Ying, Krish Varsha, Imam Farhad, Janelidze Shorena, van Westen Danielle, Stomrud Erik, Whelan Christopher D, Palmqvist Sebastian, Ossenkoppele Rik, Mattsson-Carlgren Niklas, Hansson Oskar, Vogel Jacob W
Department of Clinical Sciences Malmö, SciLifeLab, Lund University, Lund, Sweden.
Clinical Memory Research Unit, Department of Clinical Sciences Malmö, Lund University, Lund, Sweden.
medRxiv. 2025 Jul 1:2025.06.27.25330344. doi: 10.1101/2025.06.27.25330344.
Co-pathology is a common feature of neurodegenerative diseases that complicates diagnosis, treatment and clinical management. However, sensitive, specific and scalable biomarkers for in vivo pathological diagnosis are not available for most neurodegenerative neuropathologies. Here, we present ProtAIDe-Dx, a deep joint-learning model trained on 17,170 patients and controls that uses plasma proteomics to provide simultaneous probabilistic diagnosis across six conditions associated with dementia in aging. ProtAIDe-Dx achieves cross-validated balanced classification accuracy of 69%-96% and AUCs > 79% across all conditions. The model's diagnostic probabilities highlighted subgroups of patients with co-pathologies, and were associated with pathology-specific biomarkers in an external sample, even among cognitively unimpaired people. Model interpretation revealed a suite of protein networks marking shared and specific biological processes across diseases, and identified novel and previously described proteins discriminating each diagnosis. ProtAIDe-Dx significantly improved biomarker-based differential diagnosis in a memory clinic sample, pinpointing proteins leading to diagnostic decisions at an individual level. Together, this work highlights the promise of plasma proteomics to improve patient-level diagnostic work-up with a single blood draw.
共病理学是神经退行性疾病的一个常见特征，它使诊断、治疗和临床管理变得复杂。然而，对于大多数神经退行性神经病理学而言，尚无用于体内病理诊断的灵敏、特异且可扩展的生物标志物。在此，我们展示了ProtAIDe-Dx，这是一种基于17170名患者和对照进行训练的深度联合学习模型，它利用血浆蛋白质组学对与衰老相关的六种痴呆症相关病症进行同步概率诊断。ProtAIDe-Dx在所有病症中均实现了69%-96%的交叉验证平衡分类准确率以及大于79%的曲线下面积（AUC）。该模型的诊断概率突出了存在共病理学的患者亚组，并且在外部样本中与病理特异性生物标志物相关，即使在认知未受损的人群中也是如此。模型解释揭示了一组标记跨疾病共享和特定生物学过程的蛋白质网络，并鉴定出区分每种诊断的新蛋白质和先前已描述的蛋白质。ProtAIDe-Dx在记忆门诊样本中显著改善了基于生物标志物的鉴别诊断，在个体水平上确定了导致诊断决策的蛋白质。总之，这项工作突出了血浆蛋白质组学通过一次抽血改善患者水平诊断检查的前景。
