Analyzing Patient Daily Movement Behavior Dynamics Using Two-Stage Encoding Model

TL;DR

This paper introduces a two-stage self-supervised learning approach to analyze patient movement patterns from time series data, aiding personalized healthcare for dementia patients.

Contribution

It presents a novel two-stage encoding model that transforms time series into text and analyzes behavioral dynamics using PageRank, enhancing remote healthcare monitoring.

Findings

Effective encoding of activity data into text for pattern analysis

Identification of behavioral state transitions and activity biases

Potential to support personalized care interventions

Abstract

In the analysis of remote healthcare monitoring data, time series representation learning offers substantial value in uncovering deeper patterns of patient behavior, especially given the fine temporal granularity of the data. In this study, we focus on a dataset of home activity records from people living with Dementia. We propose a two-stage self-supervised learning approach. The first stage involves converting time-series activities into text strings, which are then encoded by a fine-tuned language model. In the second stage, these time-series vectors are bi-dimensionalized for applying PageRank method, to analyze latent state transitions to quantitatively assess participants behavioral patterns and identify activity biases. These insights, combined with diagnostic data, aim to support personalized care interventions.