Longitudinal Ensemble Integration for sequential classification with multimodal data

A BSTRACT Effectively modeling multimodal longitudinal data is a pressing need in various application areas, especially biomedicine. Despite this, few approaches exist in the literature for this problem, with most not adequately taking into account the multimodality of the data. In this study, we developed multiple configurations of a novel multimodal and longitudinal learning framework, Longitudinal Ensemble Integration (LEI), for sequential classification. We evaluated LEI's performance, and compared it against existing approaches, for the early detection of dementia, which is among the most studied multimodal sequential classification tasks. LEI outperformed these approaches due to its use of intermediate base predictions arising from the individual data modalities, which enabled their better integration over time. LEI's design also enabled the identification of features that were consistently important across time for the effective prediction of dementia-related diagnoses. Overall, our work demonstrates the potential of LEI for sequential classification from longitudinal multimodal data. 1 I NTRODUCTION Data that are both longitudinal/temporal and multimodal are increasingly being used in combination with machine learning for forecasting, especially in medical diagnosis (Brand et al., 2019; Zhang & Shen, 2012; Feis et al., 2019; Li et al., 2023). Recently, a number of promising approaches for sequential classification from such data have been introduced (Eslami et al., 2023; Zhang et al., 2011; Wang et al., 2016; Zhang et al., 2024). For instance, some approaches have used recurrent neural network (RNN)-based models applied to data sequences where the modalities at each time point have been concatenated into a long feature vector, sometimes referred to as early fusion (Nguyen et al., 2020; Olaimat et al., 2023; Maheux et al., 2023).