Predicting Alzheimer’s Disease Progression using Time-Decay LSTM Network with Multi-Condition Variational Autoencoder

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder, where early diagnosis is critical for slowing disease progression. Cognitive assessments, known for their high sensitivity and specificity, are essential tools for early detection. However, clinical data from AD patients are often incomplete, posing significant challenges in predicting cognitive scores and accurately assessing disease progression. This paper proposes a time-decay LSTM network combined with a Multi-Condition Variational Autoencoder (MC-VAE) to address these challenges. First, the MC-VAE with clustering is employed to effectively impute missing values, capturing the diversity of the data distribution while maintaining its discreteness during interpolation. Next, a multi-representation information encoder, composed of several MUST-Encoding components, encodes the imputed data. This process effectively captures the non-linear and non-periodic temporal patterns arising from irregular time series. Finally, the encoded information is input into a Time-Decay LSTM network. Experimental results validate that our model outperforms conventional methods in predicting AD progression for the ADNI and NACC public datasets.