Abstract:

Pain is a subjective experience commonly measured through patient's self 
report. While there exist numerous situations in which automatic pain 
estimation methods may be preferred, inter-subject variability in physiological 
and behavioral pain responses has hindered the development of such methods. In 
this work, we address this problem by introducing a novel personalized 
multitask machine learning method for pain estimation based on individual 
physiological and behavioral pain response profiles, and show its advantages in 
a dataset containing multimodal responses to nociceptive heat pain.