Automated Assessment of Children’s Postoperative Pain Using Computer Vision

Abstract

BACKGROUND: Current pain assessment methods in youth are suboptimal and vulnerable to bias and underrecognition of clinical pain. Facial expressions are a sensitive, specific biomarker of the presence and severity of pain, and computer vision (CV) and machine-learning (ML) techniques enable reliable, valid measurement of pain-related facial expressions from video. We developed and evaluated a CVML approach to measure pain-related facial expressions for automated pain assessment in youth. METHODS:A CVML-based model for assessment of pediatric postoperative pain was developed from videos of 50 neurotypical youth 5 to 18 years old in both endogenous/ongoing and exogenous/transient pain conditions after laparoscopic appendectomy. Model accuracy was assessed for self-reported pain ratings in children and time since surgery, and compared with by-proxy parent and nurse estimates of observed pain in youth.RESULTS: Model detection of pain versus no-pain demonstrated good-to-excellent accuracy (Area under the receiver operating characteristic curve 0.84-0.94) in both ongoing and transient pain conditions. Model detection of pain severity demonstrated moderate-to-strong correlations (r = 0.65-0.86 within; r = 0.47-0.61 across subjects) for both pain conditions. The model performed equivalently to nurses but not as well as parents in detecting pain versus no-pain conditions, but performed equivalently to parents in estimating pain severity. Nurses were more likely than the model to underestimate youth self-reported pain ratings. Demographic factors did not affect model performance.CONCLUSIONS: CVML pain assessment models derived from automatic facial expression measurements demonstrated good-to-excellent accuracy in binary pain classifications, strong correlations with patient self-reported pain ratings, and parent-equivalent estimation of children's pain levels over typical pain trajectories in youth after appendectomy. WHAT'S KNOWN ON THIS SUBJECT:Clinical pain assessment methods in youth are vulnerable to underestimation bias and underrecognition. Facial expressions are sensitive, specific biomarkers of the presence and severity of pain. Computer vision-based pattern recognition enables measurement of painrelated facial expressions from video. WHAT THIS STUDY ADDS:This study demonstrates initial validity for developing computer vision algorithms for automated pain assessment in children. The system developed and tested in this study could provide standardized, continuous, and valid patient monitoring that is potentially scalable. Mr Sikka performed the machine learning under the guidance of Dr Bartlett, drafted the initial manuscript, and reviewed and revised the manuscript; Mr Ahmed carried out a portion of the initial analyses and reviewed and revised the manuscript; Dr Diaz performed data collection, performed a portion of the initial analyses, and reviewed and revised the manuscript; Drs Craig and Goodwin reviewed all analyses, and critically reviewed and revised the manuscript; Drs Bartlett and Huang concep...

Learning Pain from Action Unit Combinations: A Weakly Supervised Approach via Multiple Instance Learning

“…Chen et al [4] used a simple rulebased method to model temporal dynamics of AUs to study pain of patients suffering from lung cancer in the Wilkie's dataset. Sikka et al [19] employed a CVML-based model to assess pediatric postoperative pain on a video dataset of neurotypical youth. A total of 14 single AUs are extracted under 3 statistics to form a 42-dimensional descriptor for each pain event which serves as the input to logistic regression models of both binary pain classification and pain intensity estimation.…”

An Algorithm for Automatically Detecting Dyslexia on the Fly

“…The authors argue that phone sensors offer the opportunity to monitor mental health conditions such as depression. In another study by Sikka et al [27], the authors developed a prototype for automatically detecting and assessing pain in children. The authors argue that through "computer vision" and machine learning, software programs can assess and measure pain using facial recognition.…”

Pain expression as a biometric: Why patients' self-reported pain doesn't match with the objectively measured pain?

“…The details of this scale can be found in [10]. The authors of the UNBC-McMaster database provides FACS coded information for the video frames in the database [7], [8]. By employing the aforementioned sum rule on these FACS values for the frames we can calculate the pain intensity level of each frame in PSPI scale.…”

“…It can also provide the information about the severity of pain that can be assessed by using the Facial Action Coding System (FACS) of Ekman and Friesen [7], [8]. The FACS has long been used for measuring facial expression appearance and intensity.…”