Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 1, 2025IEEE Journal of Biomedical and Health Informatics

Generative Neural Networks for Data Imputation in Longitudinal Epidemiological Studies

View Full Paper
Ask AI
Bookmark
Share

Authors

CKChristoph KillingKEKira ElsberndMWMaximilian Wekerle

Discussion

Loading...

Member takes

Overview

Generative neural networks improve data imputation in longitudinal studies, suggesting enhanced accuracy in handling missing data and time series information.

Key Points

  • Missing data can undermine statistical power in longitudinal epidemiological studies, complicating accurate analysis.
  • Imputation methods leveraging generative neural networks showed superior performance, enhancing data quality and reliability.
  • The approach employs a variational autoencoder to reconstruct missing values effectively across various time series scenarios.
  • These findings highlight the importance of advanced imputation techniques for improving health outcome evaluations.

Cite This Study

Killing et al. (2025) studied this question.

synapsesocial.com/papers/6925573bc0ce034ddc35b275https://doi.org/10.1109/jbhi.2025.3632647
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A survey of missing data imputation techniques: statistical methods, machine learning models, and GAN-based approaches2025
  2. 2A Generative Model For Evaluating Missing Data Methods in Large Epidemiological Cohorts2024 · 2 citations
  3. 3Missing Data Imputation for Health Care Big Data using Denoising Autoencoder with Generative Adversarial Network2024 · 2 citations
  4. 4Deep Regression Modeling for Imbalanced and Incomplete Time-Series Data2024 · 1 citations
  5. 5Improving Regression Analysis with Imputation in a Longitudinal Study of Alzheimer’s Disease2024 · 2 citations