Predicting Longitudinal Outcomes of Alzheimer's Disease via a Tensor-Based Joint Classification andRegression Model

Lodewijk Brand, Kai Nichols, Hua Wang, Heng Huang, Li Shen

Introduction

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder typically monitored through longitudinal clinical visits. These visits generate diverse data types, including structural MRI scans, genetic profiles (Single Nucleotide Polymorphisms, or SNPs), and cognitive test scores. Despite the richness of this multi-modal, time-series data, most existing machine learning approaches for AD biomarker discovery analyze data from only a single time-point. Furthermore, these methods often treat clinical diagnosis (e.g., Healthy vs. AD) and cognitive score prediction as independent tasks, failing to exploit the inherent correlations between a patient's cognitive decline and their clinical status.

Methodology

To address these limitations, this research introduces a unified regularized joint learning model that utilizes tensors to represent multi-dimensional longitudinal data. The input features are organized into a tensor $\mathcal{X}$ (samples $\times$ features $\times$ time), while the targets are represented by an output tensor $\mathcal{Y}$ (scores/diagnoses $\times$ time).

The proposed tensor-based joint learning framework integrates multi-modal longitudinal data (MRI, SNP) to simultaneously predict cognitive scores and clinical diagnoses.

The model's objective function combines multivariate regression for cognitive scores with multi-class Support Vector Machines (SVM) for clinical diagnosis. To ensure robustness and biological relevance, three key regularizations are applied:

  1. $\ell_{2,1}$-norm: Promotes longitudinal consistency by selecting features that are predictive across all time points.
  2. Group $\ell_1$-norm: Manages the relative importance of different data modalities (e.g., MRI vs. SNP).
  3. Trace norm (Nuclear norm): Captures inter-modal relationships, reflecting how different cognitive measures often degrade in tandem.

Given the complexity of the resulting non-convex objective function, the authors developed a custom optimization algorithm based on the Multi-Block Alternating Direction Method of Multipliers (ADMM) to iteratively solve the coupled sub-problems.

Data and Evaluation

The model was validated using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI-1). The study cohort included 412 subjects with complete data across four time points: Baseline, Month 6, Month 12, and Month 24.

  • Input Features: 90 regional gray matter measures extracted from MRI scans via FreeSurfer and SNP genotypes.
  • Targets: Rey’s Auditory Verbal Learning Test (RAVLT) scores (regression) and clinical diagnoses (AD, MCI, or Healthy Control) (classification).

Results and Discussion

The joint learning approach significantly outperformed standard baselines in both tasks. In the regression task, the model achieved a Root Mean Squared Error (RMSE) of 12.7 $\pm$ 1.05 for the RAVLT_TOT metric, substantially better than Ridge regression (18.9) or Lasso (19.4). In classification, the model reached a superior overall F1 score of 0.459 $\pm$ 0.0125, with particularly strong performance in identifying AD (F1: 0.496) and Healthy Controls (F1: 0.477).

Axial heatmap showing brain regions identified by the model as stable, longitudinal biomarkers for AD.

Beyond predictive accuracy, the model demonstrated high clinical interpretability. The $\ell_{2,1}$-norm successfully identified biomarkers that remained stable over the 24-month period. The model independently highlighted known AD-related regions such as the hippocampus, entorhinal cortex, and amygdala. Furthermore, it correctly identified the APOE-$\epsilon$4 linked SNP (rs429358) as the most significant genetic predictor of the disease.

Conclusion

While the model excels at identifying clear AD and Healthy cases, it faced challenges with the intermediate Mild Cognitive Impairment (MCI) category, where standard Logistic Regression showed a slight advantage. This is likely due to the lack of normalization between the one-vs-all multi-class SVMs within the tensor framework. Future work will focus on refining these classification components and providing a more detailed mathematical breakdown of the optimization process.

Summary updated

Abstract

Alzheimer's disease (AD) is a serious neurodegenerative condition that affects millions of people across the world. Recently machine learning models have been used to predict the progression of AD, although they frequently do not take advantage of the longitudinal and structural components associated with multi-modal medical data. To address this, we present a new algorithm that uses the multi-block alternating direction method of multipliers to optimize a novel objective that combines multi-modal longitudinal clinical data of various modalities to simultaneously predict the cognitive scores and diagnoses of the participants in the Alzheimer's Disease Neuroimaging Initiative cohort. Our new model is designed to leverage the structure associated with clinical data that is not incorporated into standard machine learning optimization algorithms. This new approach shows state-of-the-art predictive performance and validates a collection of brain and genetic biomarkers that have been recorded previously in AD literature.
BibTeX
@inproceedings{brand2020predicting,
  author = {Lodewijk Brand and Kai Nichols and Hua Wang and Heng Huang and Li Shen},
  title = {{Predicting Longitudinal Outcomes of Alzheimer's Disease via a Tensor-Based Joint Classification andRegression Model}},
  booktitle = {PSB},
  year = {2020},
  url = {https://openreview.net/forum?id=GaovsxxFO3UC},
}
Figure