Vision-Based Prediction of ICU Mobility Care Activities using Recurrent Neural Networks

Gabriel M Bianconi, Rishab Mehra, Serena Yeung, Francesca Salipur, Jeffrey Jopling, Lance Downing, Albert Haque, Alexandre Alahi, Brandi Campbell, Kayla Deru, William Beninati, Arnold Milstein, L. Fei-Fei

Abstract:

Intensive Care Units (ICUs) are among the highest-density areas of patient care
activities in hospitals, yet documentation and understanding of the occurrence of
these activities remains sub-optimal due in part to already-demanding patient care
workloads of nursing staff. Computer vision algorithms applied to visual data
captured from mounted sensors in patient rooms have the ability to automatically
predict and document patient care activities. In this work, we introduce an approach
based on recurrent neural networks to temporally model and predict the occurrence
of ICU care activities related to mobility, and demonstrate its effectiveness on data
collected from a simulation room in an adult ICU ward.