Pain Assessment Using Facial Expressions : Machine VS expert physician

Pain Assessment Using Facial Expressions By Human And Machine

 Recently I came across this paper.
I wish I had this  machine in my clinic.
I will not have to keep second guessing who is a junkie after  his/her next fix and who is a genuine patient in pain.

 Sanjay Kumar Singh, V.Rastogi, I .L . Singh, S.K.Singh Department of Computer Science Engineering, IIT (BHU), Varanasi, India Department of Anaesthesiology, Institute of Medical Sciences, Banaras Hindu University, Varanasi-India Department of Psychology, Banaras Hindu University, Varanasi-India Tel.: +91 9452185948, E-mail address: sanjay.rs.cse12@itbhu.ac.in ABSTRACT: PAIN is the most common reason that patients go to visit doctors. Pain is not an easy sensation which will be simply accessed and could be directly measured. To make the right diagnosis and determine the most effective treatment plan for patients presenting with pain, systematic and precise pain assessment is required. The visual changes reflected on the face of a person in pain may be apparent for only a few seconds and occur instinctively. Tracking these changes is a time-consuming and difficult process in a clinical setting. This is often why it's motivating researchers and experts from medical, psychology and computer fields to conduct inter-disciplinary research in capturing facial expressions. The facial expressions of children's (0-2 years) in pain and in non-communicative patients need to be recognized as they are of utmost importance for proper diagnosis. The direct measurement of pain is related to the computation approach whereas indirect measurement is by observers ratings. The aim of this study is to correlate the results obtained from the observer, practitioner, and machine. The results showed that the experts often underestimated pain intensity in comparison to the observer and computational approaches used. This will cover both spheres of psychological vulnerability and resilience to pain along with the advanced techniques used in machine learning thereby improving the quality of care by increasing its accessibility to physicians.