Autoencoder Imputation of Missing Heterogeneous Data for Alzheimer's Disease Classification
Bibliographic record
Abstract
Accurate diagnosis of Alzheimer's disease (AD) relies heavily on the availability of complete and reliable data. Yet, missingness of heterogeneous medical and clinical data are prevalent and pose significant challenges. Previous studies have explored various data imputation strategies and methods on heterogeneous data, but the evaluation of deep learning algorithms for imputing heterogeneous AD data is limited. In this study, we addressed this by investigating the efficacy of denoising autoencoder-based imputation of missing key features of a heterogeneous data that comprised tau-PET, MRI, cognitive and functional assessments, genotype, sociodemographic, and medical history. We focused on extreme (40-70%) missing at random of key features which depend on AD progression; we identified them as history of mother having AD, APoE ε4 alleles, and clinical dementia rating. Along with features selected using traditional feature selection methods, we included latent features extracted from the denoising autoencoder for subsequent classification. Using random forest classification with 10-fold cross-validation, we evaluated the AD predictive performance of imputed datasets and found robust classification performance, with accuracy of 79-85% and precision of 71-85% across different levels of missingness. Additionally, our results demonstrated high recall values for identifying individuals with AD, particularly in datasets with 40% missingness in key features. Further, our 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".