The Impact of Extraneous Variables on the Performance of Recurrent Neural Network Models in Clinical Tasks
This addresses the challenge of variable selection in clinical prediction tasks for healthcare practitioners, but it is incremental as it confirms existing assumptions about RNN robustness.
The study examined how adding extraneous variables to Electronic Medical Records (EMR) data affects Recurrent Neural Network (RNN) performance in predicting clinical outcomes like in-ICU mortality, finding that performance degradation was negligible.
Electronic Medical Records (EMR) are a rich source of patient information, including measurements reflecting physiologic signs and administered therapies. Identifying which variables are useful in predicting clinical outcomes can be challenging. Advanced algorithms such as deep neural networks were designed to process high-dimensional inputs containing variables in their measured form, thus bypass separate feature selection or engineering steps. We investigated the effect of extraneous input variables on the predictive performance of Recurrent Neural Networks (RNN) by including in the input vector extraneous variables randomly drawn from theoretical and empirical distributions. RNN models using different input vectors (EMR variables; EMR and extraneous variables; extraneous variables only) were trained to predict three clinical outcomes: in-ICU mortality, 72-hour ICU re-admission, and 30-day ICU-free days. The measured degradations of the RNN's predictive performance with the addition of extraneous variables to EMR variables were negligible.