Alzheimer's disease classification using cluster-based labelling for graph neural network on heterogeneous data.

Autor: McCombe N; Intelligent Systems Research Centre School of Computing Engineering and Intelligent Systems Ulster University Derry∼Londonderry Northern Ireland UK., Bamrah J; Intelligent Systems Research Centre School of Computing Engineering and Intelligent Systems Ulster University Derry∼Londonderry Northern Ireland UK., Sanchez-Bornot JM; Intelligent Systems Research Centre School of Computing Engineering and Intelligent Systems Ulster University Derry∼Londonderry Northern Ireland UK., Finn DP; Pharmacology and Therapeutics, Galway Neuroscience Centre, Centre for Pain Research, and School of Medicine National University of Ireland Galway Galway Ireland., McClean PL; Northern Ireland Centre for Stratified Medicine, Biomedical Sciences Research Institute, Clinical Translational Research and Innovation Centre (C-TRIC) Ulster University Derry∼Londonderry Northern Ireland UK., Wong-Lin K; Intelligent Systems Research Centre School of Computing Engineering and Intelligent Systems Ulster University Derry∼Londonderry Northern Ireland UK.
Jazyk: angličtina
Zdroj: Healthcare technology letters [Healthc Technol Lett] 2022 Oct 20; Vol. 9 (6), pp. 102-109. Date of Electronic Publication: 2022 Oct 20 (Print Publication: 2022).
DOI: 10.1049/htl2.12037
Abstrakt: Biomarkers for Alzheimer's disease (AD) diagnosis do not always correlate reliably with cognitive symptoms, making clinical diagnosis inconsistent. In this study, the performance of a graphical neural network (GNN) classifier based on data-driven diagnostic classes from unsupervised clustering on heterogeneous data is compared to the performance of a classifier using clinician diagnosis as an outcome. Unsupervised clustering on tau-positron emission tomography (PET) and cognitive and functional assessment data was performed. Five clusters embedded in a non-linear uniform manifold approximation and project (UMAP) space were identified. The individual clusters revealed specific feature characteristics with respect to clinical diagnosis of AD, gender, family history, age, and underlying neurological risk factors (NRFs). In particular, one cluster comprised mainly diagnosed AD cases. All cases within this cluster were re-labelled AD cases. The re-labelled cases are characterized by high cerebrospinal fluid amyloid beta (CSF Aβ) levels at a younger age, even though Aβ data was not used for clustering. A GNN model was trained using the re-labelled data with a multiclass area-under-the-curve (AUC) of 95.2%, higher than the AUC of a GNN trained on clinician diagnosis (91.7%; p  = 0.02). Overall, our work suggests that more objective cluster-based diagnostic labels combined with GNN classification may have value in clinical risk stratification and diagnosis of AD.
Competing Interests: The authors have declared no conflict of interest.
(© 2022 The Authors. Healthcare Technology Letters published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.)
Databáze: MEDLINE
Externí odkaz: