Improving Interpretability in Alzheimer's Prediction via Joint Learning of ADAS-Cog Scores

TL;DR

This study introduces a multi-task learning framework using transformer architectures to jointly predict global and sub-scores of ADAS-Cog, enhancing interpretability and understanding of cognitive decline in Alzheimer's disease.

Contribution

It presents a novel joint learning approach that incorporates sub-score analysis and multimodal data fusion for improved Alzheimer's prediction interpretability.

Findings

Incorporating sub-scores improves global score prediction accuracy.

Certain sub-scores like Word Recall and Delayed Recall dominate global score predictions.

Model instability is linked to clinical feature dominance and high prediction errors for some sub-scores.

Abstract

Accurate prediction of clinical scores is critical for early detection and prognosis of Alzheimers disease (AD). While existing approaches primarily focus on forecasting the ADAS-Cog global score, they often overlook the predictive value of its sub-scores (13 items), which capture domain-specific cognitive decline. In this study, we propose a multi task learning (MTL) framework that jointly predicts the global ADAS-Cog score and its sub-scores (13 items) at Month 24 using baseline MRI and longitudinal clinical scores from baseline and Month 6. The main goal is to examine how each sub scores particularly those associated with MRI features contribute to the prediction of the global score, an aspect largely neglected in prior MTL studies. We employ Vision Transformer (ViT) and Swin Transformer architectures to extract imaging features, which are fused with longitudinal clinical inputs to model cognitive progression. Our results show that incorporating sub-score learning improves global score prediction. Subscore level analysis reveals that a small subset especially Q1 (Word Recall), Q4 (Delayed Recall), and Q8 (Word Recognition) consistently dominates the predicted global score. However, some of these influential sub-scores exhibit high prediction errors, pointing to model instability. Further analysis suggests that this is caused by clinical feature dominance, where the model prioritizes easily predictable clinical scores over more complex MRI derived features. These findings emphasize the need for improved multimodal fusion and adaptive loss weighting to achieve more balanced learning. Our study demonstrates the value of sub score informed modeling and provides insights into building more interpretable and clinically robust AD prediction frameworks. (Github repo provided)