Comparative study of clustering models for multivariate time series from connected medical devices

2023/12/28 by Violaine Courrier, Courrier, Violaine, Christophe Biernacki +5
Computer Science · #Advanced Clustering Algorithms Research #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2312.17286

openalex publication_date 2023/12/28 · openalex created_date 2024/01/02 · openalex updated_date 2026/07/28

Abstract

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 DGM² which allows the group affiliation of an individual to change over time (dynamic clustering).

Related

• Temporal Phenotyping using Deep Predictive Clustering of Disease Progression
• Temporal-Clustering Invariance in Irregular Healthcare Time Series
• Temporal Clustering with External Memory Network for Disease Progression Modeling
• 4TaStiC: Time and trend traveling time series clustering for classifying long-term type 2 diabetes patients
• Identifying Subgroups of ICU Patients Using End-to-End Multivariate Time-Series Clustering Algorithm Based on Real-World Vital Signs Data