Table 2.
Pain prediction results in varying pain scales on vital signs data (accuracy) as compared with additional medication data arranged from higher resolution to lower resolution.
Approach | 11 pain scores | 6 pain scores | 4 pain scores | 2 pain scores | |||||||
|
Vitals | Vitals+medicinal | Vitals | Vitals+medicinal | Vitals | Vitals+medicinal | Vitals | Vitals+medicinal | |||
Original data | 0.301 | 0.442 | 0.363 | 0.463 | 0.432 | 0.689a | 0.535 | 0.787b | |||
VAEc data | 0.343 | 0.476 | 0.391 | 0.493 | 0.472 | 0.706d | 0.603 | 0.828e |
aModel with original representations using both vital and medication data for the 4 pain score rating scale.
bModel with original representations using both vital and medication data for the 2 pain score rating scale.
cVAE: variational autoencoder.
dModel with deep representations using both vital and medication data for the 4 pain score rating scale.
eBest-performing model with deep representations using both vital and medication data for the 2 pain score rating scale.