Training recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modeling
This work addresses the challenge of incomplete data in longitudinal studies for Alzheimer's disease progression modeling, offering a robust method that improves prediction accuracy and diagnostic performance.
The authors tackled the problem of disease progression modeling with incomplete longitudinal data by proposing a generalized training rule for LSTM networks that handles missing values without imputation, achieving significantly lower mean absolute error (MAE) in predicting Alzheimer's disease biomarkers and an AUC of 0.90 for clinical diagnosis.
Disease progression modeling (DPM) using longitudinal data is a challenging machine learning task. Existing DPM algorithms neglect temporal dependencies among measurements, make parametric assumptions about biomarker trajectories, do not model multiple biomarkers jointly, and need an alignment of subjects' trajectories. In this paper, recurrent neural networks (RNNs) are utilized to address these issues. However, in many cases, longitudinal cohorts contain incomplete data, which hinders the application of standard RNNs and requires a pre-processing step such as imputation of the missing values. Instead, we propose a generalized training rule for the most widely used RNN architecture, long short-term memory (LSTM) networks, that can handle both missing predictor and target values. The proposed LSTM algorithm is applied to model the progression of Alzheimer's disease (AD) using six volumetric magnetic resonance imaging (MRI) biomarkers, i.e., volumes of ventricles, hippocampus, whole brain, fusiform, middle temporal gyrus, and entorhinal cortex, and it is compared to standard LSTM networks with data imputation and a parametric, regression-based DPM method. The results show that the proposed algorithm achieves a significantly lower mean absolute error (MAE) than the alternatives with p < 0.05 using Wilcoxon signed rank test in predicting values of almost all of the MRI biomarkers. Moreover, a linear discriminant analysis (LDA) classifier applied to the predicted biomarker values produces a significantly larger AUC of 0.90 vs. at most 0.84 with p < 0.001 using McNemar's test for clinical diagnosis of AD. Inspection of MAE curves as a function of the amount of missing data reveals that the proposed LSTM algorithm achieves the best performance up until more than 74% missing values. Finally, it is illustrated how the method can successfully be applied to data with varying time intervals.