Bayesian temporal biclustering with applications to multi-subject neuroscience studies

TL;DR

This paper introduces a Bayesian temporal biclustering model for multivariate time series data from multiple subjects, enabling the discovery of dynamic, interpretable patterns and changepoints in neuroscience datasets.

Contribution

It proposes a novel Bayesian nested partition model with efficient MCMC inference for identifying subject and measurement clusters over time.

Findings

Accurately identifies ground-truth clusters in simulated data.

Effectively detects changepoints in measurement partitions.

Demonstrates interpretability and dynamic pattern discovery in neuroscience data.

Abstract

We consider the problem of analyzing multivariate time series collected on multiple subjects, with the goal of identifying groups of subjects exhibiting similar trends in their recorded measurements over time as well as time-varying groups of associated measurements. To this end, we propose a Bayesian model for temporal biclustering featuring nested partitions, where a time-invariant partition of subjects induces a time-varying partition of measurements. Our approach allows for data-driven determination of the number of subject and measurement clusters as well as estimation of the number and location of changepoints in measurement partitions. To efficiently perform model fitting and posterior estimation with Markov Chain Monte Carlo, we derive a blocked update of measurements' cluster-assignment sequences. We illustrate the performance of our model in two applications to functional magnetic resonance imaging data and to an electroencephalogram dataset. The results indicate that the proposed model can combine information from potentially many subjects to discover a set of interpretable, dynamic patterns. Experiments on simulated data compare the estimation performance of the proposed model against ground-truth values and other statistical methods, showing that it performs well at identifying ground-truth subject and measurement clusters even when no subject or time dependence is present.