PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
April 12, 2026Machine Learning and Knowledge ExtractionOpen Access

KS-VAE: A Novel Variational Autoencoder Framework for Understanding Alzheimer’s Disease Progression Using Kolmogorov–Smirnov Guidance

View Full Paper
Ask AI
Bookmark
Share

Authors

CMCristina MartínezBPBlanca PosadaOZOlivia Zulaica

Discussion

Loading...

Member takes

Overview

Novel framework integrates Kolmogorov–Smirnov guidance to reveal significant brain features in Alzheimer’s disease.

Key Points

  • The aim is to enhance understanding of Alzheimer’s disease progression through an improved modeling framework.
  • Developed a novel variational autoencoder framework, KS-VAE.
  • Integrated Kolmogorov–Smirnov test into the latent space for feature discrimination.
  • Analyzed resting-state functional MRI data from 220 subjects.
  • Generated synthetic samples to simulate transitions between health and pathology.
  • Achieved classification accuracy of 84.5% for distinguishing Alzheimer's disease from normal cognition.
  • Demonstrated robust class separation between cognitively normal and Alzheimer’s subjects.
  • Provided clinically consistent synthetic transitions that preserved anatomical plausibility.

Cite This Study

Martínez et al. (2026) studied this question.

synapsesocial.com/papers/69db37404fe01fead37c53c8https://doi.org/10.3390/make8040095
View Full Paper
Ask AI
Bookmark
Share