Table 3 Summary of RNN vs MEWS performances on hard outcomes using both wearable and EHR data sources

From: Development and validation of a clinical wearable deep learning based continuous inhospital deterioration prediction model

 

Wrbl RNN-ACC.(Correct/Total)

EMR RNN-ACC.(Correct/Total)

VC MEWS-ACC.(Correct/Total)

EMR MEWS-ACC.(Correct/Total)

Cardiac Arrest

100.0 (1/1)

0.0 (0/1)

0.0 (0/1)

0.0 (0/1)

Expiration

100.0 (1/1)

0.0 (0/1)

0.0 (0/1)

0.0 (0/1)

ICU Transfer

83.3 (5/6)

50.0 (3/6)

16.7 (1/6)

0.0 (0/6)

RRT

50.0 (1/2)

100.0 (2/2)

0.0 (0/2)

0.0 (0/2)

Ventilation/Intubation

100.0 (1/1)

100.0 (1/1)

0.0 (0/1)

0.0 (0/1)

  1. Wrbl Wearable Device Data, RNN Recurrent Neural Network, ACC Accuracy, EMR Electronic Medical Record, MEWS Modified Early Warning Score, ICU Intensive Care Unit, RRT Rapid Response Team.
Back to article page