TY - JOUR
T1 - Temporal generative models for learning heterogeneous group dynamics of ecological momentary assessment data
AU - Kim, Soohyun
AU - Kim, Young Geun
AU - Wang, Yuanjia
N1 - Publisher Copyright:
© The Author(s) 2024. Published by Oxford University Press on behalf of The International Biometric Society.
PY - 2024/10/3
Y1 - 2024/10/3
N2 - One 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 that capture multiple responses in real-time at high frequency. However, ecological momentary assessment data are often multi-dimensional, correlated, and hierarchical. Mixed-effect 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 HDRBM, to learn the heterogeneous group dynamics and demonstrate the effectiveness of this approach on simulated and real-world ecological momentary assessment datasets. 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 ecological momentary assessment studies.
AB - One 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 that capture multiple responses in real-time at high frequency. However, ecological momentary assessment data are often multi-dimensional, correlated, and hierarchical. Mixed-effect 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 HDRBM, to learn the heterogeneous group dynamics and demonstrate the effectiveness of this approach on simulated and real-world ecological momentary assessment datasets. 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 ecological momentary assessment studies.
UR - http://www.scopus.com/inward/record.url?scp=85206281410&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85206281410&partnerID=8YFLogxK
U2 - 10.1093/biomtc/ujae115
DO - 10.1093/biomtc/ujae115
M3 - Article
C2 - 39400260
AN - SCOPUS:85206281410
SN - 0006-341X
VL - 80
JO - Biometrics
JF - Biometrics
IS - 4
ER -