Medical Records Analysis refers to the examination and modeling of multivariate time series data derived from electronic health records (EHRs). This analysis aims to forecast future health outcomes based on incomplete historical data. By addressing the challenges of sparsity and individual processing of time series, the proposed generative model enhances the ability to predict future values by capturing dynamic clustering structures within the data. This approach allows for more robust forecasting and improved decision-making in healthcare applications, ultimately benefiting patient care and treatment planning.

4o mini

Posts

Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series

/in /by

Forecasting on Sparse Multivariate Time Series Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging applications. However, most existing methods process MTS’s individually, and do not leverage the dynamic distributions underlying the MTS’s, leading to sub-optimal results when the sparsity is high. To address this challenge, we propose a novel generative model, which tracks the transition of latent clusters, instead of isolated feature representations, to achieve robust modeling. It is characterized by a newly designed dynamic Gaussian mixture distribution, which captures the dynamics of clustering structures, and is used for emitting time series. The generative model is parameterized by neural networks. A structured inference network is also designed for enabling inductive analysis. A gating mechanism is further introduced to dynamically tune the Gaussian mixture distributions. Extensive experimental results on a variety of real-life datasets demonstrate the effectiveness of our method.

Read more