Scholarlink

<p>Neurodegenerative diseases like Alzheimer’s, Parkinson’s, vascular dementia, and frontotemporal dementia are difficult to detect early due to noisy or missing Mini-Mental State Examination (MMSE) data and uninterpretable prediction models. A Disentangled Conditional Variational Autoencoder (D-CVAE) Fusion model with a novel stage-aligned disentanglement loss addresses these issues. Clinically interpretable representations are achieved by separating cognitive decline components from other latent variations. The model reconstructs lost MMSE data and improves feature representation by conditioning the encoder-decoder architecture on cognitive stage. Using disentangled latent embeddings, an integrated Multi-Layer Perceptron (MLP) classifier accurately identifies cognitive impairment levels from no impairment to moderate impairment. Our D-CVAE Fusion model has 94.52% accuracy, resilience with 30% missing data, and clinically significant latent dimensions (e.g. z₁ shows strong correlation with MMSE score, <i>r</i> = − 0.94). Clinical decision support systems for cognitive evaluation and early-stage neurodegenerative disease diagnosis can use the suggested paradigm with confidence and interpretability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Stage-aware disentangled conditional VAE for interpretable prediction of cognitive decline

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月1日

查看全文
  • Sergey Yarushev,
  • S. Neelakandan,
  • N. Banupriya,
  • S. Velmurugan

摘要

Neurodegenerative diseases like Alzheimer’s, Parkinson’s, vascular dementia, and frontotemporal dementia are difficult to detect early due to noisy or missing Mini-Mental State Examination (MMSE) data and uninterpretable prediction models. A Disentangled Conditional Variational Autoencoder (D-CVAE) Fusion model with a novel stage-aligned disentanglement loss addresses these issues. Clinically interpretable representations are achieved by separating cognitive decline components from other latent variations. The model reconstructs lost MMSE data and improves feature representation by conditioning the encoder-decoder architecture on cognitive stage. Using disentangled latent embeddings, an integrated Multi-Layer Perceptron (MLP) classifier accurately identifies cognitive impairment levels from no impairment to moderate impairment. Our D-CVAE Fusion model has 94.52% accuracy, resilience with 30% missing data, and clinically significant latent dimensions (e.g. z₁ shows strong correlation with MMSE score, r = − 0.94). Clinical decision support systems for cognitive evaluation and early-stage neurodegenerative disease diagnosis can use the suggested paradigm with confidence and interpretability.