Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain Aggregation

Early detection of mortality in intensive care units (ICUs) is significant to improve patient survival. Since heterogeneous data can be collected from the intensive care unit, there are meaningful static features (e.g., ICU type, gender, and ethnicity) that can enhance the performance of early detection of mortality. Although the characteristics of physiological representation for each patient can be different by static features, recently proposed mortality prediction models overlook these features and only rely on a one-size-fits-all model. In this paper, we propose a simple yet effective domain encoder named G-DAM (Graph-Domain Aggregation Module) that relies on a relational graph between each static feature to adapt to patient groups and capture the relationship. We show the importance of utilizing static features to predict ICU mortality through extensive experimental results. The experimental results demonstrate that our proposed G-DAM outperforms existing baseline methods not only in the major domains with dense populations but also in the minor domains with sparse populations. The ablative study also shows different sequential models can perform better combined with G-DAM.