Imputation with Inter-Series Information from Prototypes for Healthcare Time Series

Time series with missing values are ubiquitous in healthcare scenarios, presenting significant challenges for analysis. Despite existing methods addressing imputation, they predominantly focus on leveraging intra-series information, neglecting the potential benefits that inter-series information could provide, such as reducing uncertainty and memorization effect. To bridge this gap, we propose PRIME, Prototype Recurrent Imputation ModEl, which integrates both intra-series and inter-series information for imputing missing values in irregularly sampled time series. PRIME comprises a prototype memory module for learning inter-series information, a bidirectional gated recurrent unit utilizing prototype information for imputation, and an attentive prototypical refinement module for adjusting imputations. We conduct extensive experiments on four datasets, and the results underscore PRIME’s superiority over the state-of-the-art models by up to 26% relative improvement in mean square error. Our code is available at https://jcst.ict.ac.cn/news/382.