Modeling Missing Data in Clinical Time Series with RNNs
This addresses data quality issues in clinical settings like pediatric intensive care, offering a practical improvement for healthcare analytics, though it is incremental as it builds on existing RNN methods.
The paper tackled missing data in clinical time series by treating missingness patterns as features, achieving superior predictive performance for multilabel diagnosis classification compared to imputation, with results showing that for some diseases, missingness patterns alone can be as predictive as actual test results.
We demonstrate a simple strategy to cope with missing data in sequential inputs, addressing the task of multilabel classification of diagnoses given clinical time series. Collected from the pediatric intensive care unit (PICU) at Children's Hospital Los Angeles, our data consists of multivariate time series of observations. The measurements are irregularly spaced, leading to missingness patterns in temporally discretized sequences. While these artifacts are typically handled by imputation, we achieve superior predictive performance by treating the artifacts as features. Unlike linear models, recurrent neural networks can realize this improvement using only simple binary indicators of missingness. For linear models, we show an alternative strategy to capture this signal. Training models on missingness patterns only, we show that for some diseases, what tests are run can be as predictive as the results themselves.