Learning Representations of Missing Data for Predicting Patient Outcomes

Understand

Extracting actionable insight from Electronic Health Records (EHRs) poses several challenges for traditional machine learning approaches.

• Patients are often missing data relative to each other; the data comes in a variety of modalities, such as multivariate time series, free text, and categorical demographic information; important relationships among patients can be difficult to detect; and many others.
• In this work, we propose a novel approach to address these first three challenges using a representation learning scheme based on message passing.
• We show that our proposed approach is competitive with or outperforms the state of the art for predicting in-hospital mortality (binary classification), the length of hospital visits (regression) and the discharge destination (multiclass classification).