Deep Learning for AD Risk Screening and Progression Prediction
Advanced Science · 05.11.2026
DOI: 10.1002/advs.78537 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 05.11.2026. Verfasst von Bin Lu und 12 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Cognitive Science and Mental Health, Institute of Psychology, Chinese Academy of Sciences, Beijing, People's Republic of Chin…. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Brain Science and Brain-like Intelligence Technology-National Science and Technology Major Project, National Natural Science Foundation of China, Construction Fund of Key Medical Disciplines of Hangzhou.
Abstract (Originalsprache)
The rise of Alzheimer's disease (AD) immunotherapies underscores the need for accessible, time‐efficient biomarkers for early diagnosis. MRI‐based deep learning shows promise in this regard, yet few models have undergone comprehensive clinical validation. Using the SILCODE cohort (722 Chinese participants, 1,105 scans), we test the transportability of our classifier (pretrained on Western samples) to an independent Chinese cohort without retraining. The associations between risk scores and disease progression, cognitive performance, and plasma biomarkers are examined. In addition, an interpretable framework is developed to generate individualized brain risk maps and identify subtypes. The model classifies AD with an AUC of 0.913 and 95.2% sensitivity, identifying 90.5% of high‐risk individuals 2–3 years before clinical diagnosis. Risk scores correlate significantly with cognitive and plasma indices, particularly p‐tau 217. Brain risk maps reveal AD subtypes, including a subgroup with rapid cognitive decline. These findings establish a population‐robust, clinically relevant MRI‐based model for early AD detection and risk stratification.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- State Key Laboratory of Cognitive Science and Mental Health, Institute of Psychology, Chinese Academy of Sciences, Beijing, People's Republic of China.
- Department of Psychology, University of the Chinese Academy of Sciences, Beijing, People's Republic of China.
- Donders Centre for Cognitive Neuroimaging, Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, the Netherlands.
- Department of Psychology and Neuroscience, University of North Carolina At Chapel Hill, Chapel Hill, North Carolina, USA.
- Department of Neurology, National Clinical Research Center for Geriatric Diseases, XuanWu Hospital of Capital Medical University, Beijing, People's Republic of China.
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing, People's Republic of China.
ORCID-Profile: Yan-Rong Chen, Rui-Xian Li, Guan-Qun Chen, Francisco Xavier Castellanos, Paul M Thompson, Jie Lu, Ying Han, Chao-Gan Yan
Förderung
- Brain Science and Brain-like Intelligence Technology-National Science and Technology Major Project
- National Natural Science Foundation of China
- Construction Fund of Key Medical Disciplines of Hangzhou
- Scientific Foundation of Institute of Psychology, Chinese Academy of Sciences
- Beijing Nova Program of Science and Technology
- Beijing Natural Science Foundation
- the Qiantang Scholars Program
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Lu, B., Chen, Y. R., Li, R. X., Zhang, M. K., Yan, S. Z., Chen, G. Q., Wang, J. H., Chai, W. H., Castellanos, F. X., Thompson, P. M., Lu, J., Han, Y., & Yan, C. G. (2026). Deep Learning for AD Risk Screening and Progression Prediction. Advanced Science. https://doi.org/10.1002/advs.78537
Vancouver
Lu B, Chen YR, Li RX, Zhang MK, Yan SZ, Chen GQ, et al. Deep Learning for AD Risk Screening and Progression Prediction. Advanced Science. 2026. doi:10.1002/advs.78537
BibTeX
@article{Lu2026,
author = {Lu, Bin and Chen, Yan-Rong and Li, Rui-Xian and Zhang, Ming-Kai and Yan, Shao-Zhen and Chen, Guan-Qun and Wang, Jing-Hua and Chai, Wen-Hui and Castellanos, Francisco Xavier and Thompson, Paul M and Lu, Jie and Han, Ying and Yan, Chao-Gan},
title = {Deep Learning for AD Risk Screening and Progression Prediction},
journal = {Advanced Science},
year = {2026},
doi = {10.1002/advs.78537}
}
EUVIMED