Journal Article

Autoencoder imputation of missing heterogeneous data for Alzheimer's disease classification

McClean, Paula L., Sanchez‐Bornot, Jose M., Haridas, Namitha Thalekkara, Wong‐Lin, KongFatt

2024

Overview

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. Denoising autoencoder imputation of key heterogenous Alzheimer's disease (AD) data features, with extreme proportion of missingness, leads to high AD predictive performance. Machine learning prediction using machine‐selected features, including autoencoder's latent features, outperforms the prediction using the original complete dataset.

• Publisher: John Wiley & Sons, Inc,John Wiley and Sons Inc,Wiley
• Subject: Algorithms / Alzheimer's disease / Classification / Cognitive ability / data mining / data reduction / Datasets / decision support systems / Deep learning / Dementia / Disease management / Family medical history / feature extraction / Feature selection / learning (artificial intelligence) / Letter / Machine learning / medical diagnostic computing / Medical imaging / Memory / Missing data / neural nets / Neuroimaging / Neuropsychology / Regression analysis / Regular / Sociodemographics / Variables