Comparative study of clustering models for multivariate time series from connected medical devices
This work addresses the challenge of analyzing sparse healthcare data for patient profiling, but it is incremental as it compares existing methods without introducing new techniques.
The study tackled the problem of creating patient profiles from multivariate time series data from connected medical devices by comparing two clustering models, M AGMAC LUST and DGM^2, to predict future values and form latent clusters, with results evaluated based on predictive performance on Withing's datasets.
In healthcare, patient data is often collected as multivariate time series, providing a comprehensive view of a patient's health status over time. While this data can be sparse, connected devices may enhance its frequency. The goal is to create patient profiles from these time series. In the absence of labels, a predictive model can be used to predict future values while forming a latent cluster space, evaluated based on predictive performance. We compare two models on Withing's datasets, M AGMAC LUST which clusters entire time series and DGM${}^2$ which allows the group affiliation of an individual to change over time (dynamic clustering).