Kim, Y.-g. | Search bioRxiv

bioRxiv2023

Temporal Generative Models for Learning Heterogeneous Group Dynamics of Ecological Momentary Data

SO_SCPLOWUMMARYC_SCPLOWOne of the goals of precision psychiatry is to characterize mental disorders in an individualized manner, taking into account the underlying dynamic processes. Recent advances in mobile technologies have enabled the collection of Ecological Momentary Assessments (EMAs) that capture multiple responses in real-time at high frequency. However, EMA data is often multi-dimensional, correlated, and hierarchical. Mixed-effects models are commonly used but may require restrictive assumptions about the fixed and random effects and the correlation structure. The Recurrent Temporal Restricted Boltzmann Machine (RTRBM) is a generative neural network that can be used to model temporal data, but most existing RTRBM approaches do not account for the potential heterogeneity of group dynamics within a population based on available covariates. In this paper, we propose a new temporal generative model, the Heterogeneous-Dynamics Restricted Boltzmann Machine (HDRBM), to learn the heterogeneous group dynamics and demonstrate the effectiveness of this approach on simulated and real-world EMA data sets. We show that by incorporating covariates, HDRBM can improve accuracy and interpretability, explore the underlying drivers of the group dynamics of participants, and serve as a generative model for EMA studies.

bioinformatics↗

bioRxiv2023

Explaining Deep Learning-Based Representations of Resting State Functional Connectivity Data: Focusing on Interpreting Nonlinear Patterns in Autism Spectrum Disorder

BackgroundResting state Functional Magnetic Resonance Imaging fMRI (rs-fMRI) has been used to study brain function in psychiatric disorders, yielding insight into brain organization. However, the high dimensionality of the rs-fMRI data presents challenges, and requires dimensionality reduction before applying machine learning techniques. Neural networks, specifically variational autoencoders (VAEs), have been instrumental in extracting low-dimensional latent representations of resting state functional connectivity patterns, addressing the complex nonlinear structure of rs-fMRI. However, interpreting those latent representations remains a challenge. This paper aims to address this gap by creating explainable VAE models and testing their utility using rs-fMRI data in autism spectrum disorder (ASD). MethodsOne-thousand one hundred and fifty participants (601 HC and 549 patients with ASD) were included in the analysis. We extracted functional connectivity correlation matrices from the preprocessed rs-fMRI data using Power atlas with 264 ROIs. Then VAEs were trained in an unsupervised fashion. Lastly, we introduce our latent contribution scores to explain the relationship between estimated representations and the original rs-fMRI brain measures. ResultsWe quantified the latent contribution scores for the ASD and control groups at the network level. We found that both ASD and control groups share the top network connectivity that contribute to all estimated latent components. For example, latent 0 was driven by resting state functional connectivity patterns (rsFC) within ventral attention network in both the ASD and control. However, significant differences in the latent contribution scores between the ASD and control groups were discovered within the ventral attention network in latent 0 and the sensory/somatomotor network in latent 2. ConclusionThis study introduced latent contribution scores to interpret nonlinear patterns identified by VAEs. These scores effectively capture changes in each observed rsFC features as estimated latent representation changes, enabling an explainable deep learning model to better understand the underlying neural mechanism of ASD.

neuroscience↗