Autoencoder imputation of missing heterogeneous data for Alzheimer's disease classification
Healthcare Technology Letters · 2024-12 · 11 (6) · 452-460
DOI: 10.1049/htl2.12091 ↗Kurz gefasst
Fachartikel in der Zeitschrift Healthcare Technology Letters, online erschienen am 15.09.2024. Verfasst von Namitha Thalekkara Haridas und 4 weiteren Autor:innen. Beteiligte Einrichtung: Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems Ulster University, Magee campus Derry∼Londonderry North…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Themen: Demenz
Abstract (Originalsprache)
Missing Alzheimer's disease (AD) data is prevalent and poses significant challenges for AD diagnosis. Previous studies have explored various data imputation approaches on AD data, but the systematic evaluation of deep learning algorithms for imputing heterogeneous and comprehensive AD data is limited. This study investigates the efficacy of denoising autoencoder‐based imputation of missing key features of heterogeneous data that comprised tau‐PET, MRI, cognitive and functional assessments, genotype, sociodemographic, and medical history. The authors focused on extreme (≥40%) missing at random of key features which depend on AD progression; identified as the history of a mother having AD, APoE ε4 alleles, and clinical dementia rating. Along with features selected using traditional feature selection methods, latent features extracted from the denoising autoencoder are incorporated for subsequent classification. Using random forest classification with 10‐fold cross‐validation, robust AD predictive performance of imputed datasets (accuracy: 79%–85%; precision: 71%–85%) across missingness levels, and high recall values with 40% missingness are found. Further, the feature‐selected dataset using feature selection methods, including autoencoder, demonstrated higher classification score than that of the original complete dataset. These results highlight the effectiveness and robustness of autoencoder in imputing crucial information for reliable AD prediction in AI‐based clinical decision support systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems Ulster University, Magee campus Derry∼Londonderry Northern Ireland UK.
- Personalised Medicine Centre, School of Medicine Ulster University, Magee campus Derry∼Londonderry Northern Ireland UK.
ORCID-Profile: KongFatt Wong-Lin
Zitieren
APA
Haridas, N. T., Sanchez-Bornot, J. M., McClean, P. L., Wong-Lin, K., & Alzheimer's Disease Neuroimaging Initiative (ADNI) (2024). Autoencoder imputation of missing heterogeneous data for Alzheimer's disease classification. Healthcare Technology Letters, 11(6), 452-460. https://doi.org/10.1049/htl2.12091
Vancouver
Haridas NT, Sanchez-Bornot JM, McClean PL, Wong-Lin K, Alzheimer's Disease Neuroimaging Initiative (ADNI). Autoencoder imputation of missing heterogeneous data for Alzheimer's disease classification. Healthcare Technology Letters. 2024;11(6):452-460. doi:10.1049/htl2.12091
BibTeX
@article{Haridas2024,
author = {Haridas, Namitha Thalekkara and Sanchez-Bornot, Jose M and McClean, Paula L and Wong-Lin, KongFatt and Alzheimer's Disease Neuroimaging Initiative (ADNI), Alzheimer's Disease Neuroimaging Initiative (ADNI)},
title = {Autoencoder imputation of missing heterogeneous data for Alzheimer's disease classification},
journal = {Healthcare Technology Letters},
year = {2024},
volume = {11},
number = {6},
pages = {452--460},
doi = {10.1049/htl2.12091}
}
EUVIMED