Analyzing Patient Daily Movement Behavior Dynamics Using Two-Stage Encoding Model
This work addresses the challenge of interpreting fine-grained time-series data for personalized healthcare in Dementia patients, but it appears incremental as it combines existing methods like language models and PageRank in a novel application.
The study tackled the problem of analyzing patient behavior patterns in remote healthcare monitoring by proposing a two-stage self-supervised learning approach on home activity records from people with Dementia, resulting in quantitative assessment of behavioral patterns and identification of activity biases to support personalized care interventions.
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.