TADPOLE: Alzheimer's Disease Prediction with Cognitive, Neuroimaging, and Genetic Features

The Alzheimer’s Disease Prediction of Longitudinal Evolution (TADPOLE) dataset contains patient trajectories for Alzheimer's disease research. It includes cognitive, neuroimaging, genetic, and demographic data, with three diagnostic classes: Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and AD. The dataset, 5.5 KB in size and last updated in April 2026, was used in an ablation study by author Emad Al-anbari to evaluate a novel model integrating Neural Processes and Normalizing Flows.

Use Cases

• Training classification models to predict Alzheimer's disease progression based on cognitive and demographic features mentioned in the description
• Evaluating time-series models for capturing temporal dependencies in patient trajectories described in the study
• Benchmarking novel neural architectures, like the SNP-NF model described, against traditional approaches for medical prediction
• Analyzing the relationship between genetic markers and disease classification as indicated by the dataset's feature types

Strengths

• Includes multiple data modalities: cognitive, neuroimaging, genetic, and demographic features as described
• License is CC-BY-4.0, allowing for broad reuse and sharing
• Dataset was used in a published model comparison, showing improvements in mAUC, Precision, and Recall

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• Dataset is very small at 5.5 KB, indicating a likely subset or processed summary rather than raw source data

Provenance

Source

TADPOLE (Alzheimer’s Disease Prediction of Longitudinal Evolution) dataset

Collection Method

Selected features for model building, as described in the study

Time Range

null

Freshness

Last updated 2026-04-20 17:47:28; freshness should be verified

Geography

null