Skip to content
Preprint · CC-BY via OpenAlex

Benchmarking the AI-based diagnostic potential of plasma proteomics for neurodegenerative disease in 17,187 people

Lijun An, Alexa Pichet Binette, Inès Hristovska, Gabriele Vilkaite, Yu Xiao, Romina Zendehdel, Zijian Dong, Bart Smets, Rowan Saloner, Shinya Tasaki, Xu Ying, Varsha S. Krish, Farhad B. Imam, Shorena Janelidze, Danielle van Westen

medRxiv · 2025 · ▲ 3 citations

Abstract

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.

◌ CITATION ONLY
Full text is not openly licensed for redistribution here. Read it at the source:

Read at source →

Provenance

Source
OpenAlex
DOI
10.1101/2025.06.27.25330344
Canonical
link ↗
Fetched
2026-11-04 MST

Cite this

APA
An, L., Binette, A.P., Hristovska, I., Vilkaite, G., Xiao, Y., Zendehdel, R., Dong, Z., Smets, B., Saloner, R., Tasaki, S., Ying, X., Krish, V.S., Imam, F.B., Janelidze, S., Westen, D.V., Stomrud, E., Whelan, C.D., Palmqvist, S., Ossenkoppele, R., &amp; Mattsson, N. (2025). Benchmarking the AI-based diagnostic potential of plasma proteomics for neurodegenerative disease in 17,187 people. <em>medRxiv</em>. https://doi.org/10.1101/2025.06.27.25330344
Vancouver
An L, Binette AP, Hristovska I, Vilkaite G, Xiao Y, Zendehdel R, et al. Benchmarking the AI-based diagnostic potential of plasma proteomics for neurodegenerative disease in 17,187 people. medRxiv. 2025. doi:10.1101/2025.06.27.25330344.
BibTeX
@unpublished{lijun2025Benchm, title = {Benchmarking the AI-based diagnostic potential of plasma proteomics for neurodegenerative disease in 17,187 people}, author = {Lijun An and Alexa Pichet Binette and Inès Hristovska and Gabriele Vilkaite and Yu Xiao and Romina Zendehdel and Zijian Dong and Bart Smets and Rowan Saloner and Shinya Tasaki and Xu Ying and Varsha S. Krish and Farhad B. Imam and Shorena Janelidze and Danielle van Westen and Erik Stomrud and Christopher D. Whelan and Sebastian Palmqvist and Rik Ossenkoppele and Niklas Mattsson and Oskar Hansson and Jacob W. Vogel}, journal = {medRxiv}, year = {2025}, doi = {10.1101/2025.06.27.25330344}, }

Research neighborhood

References, citing works, and semantically nearest findings. Click a node to open it.

Related findings