Karan Sikka1, Alex A Ahmed1, Damaris Diaz2, Matthew S Goodwin3, Kenneth D Craig4, Marian S Bartlett5, Jeannie S Huang6. 1. Institute for Neural Computation, and. 2. Department of Pediatrics, University of California San Diego, San Diego, California; 3. Department of Health Sciences, Northeastern University, Boston, Massachusetts; 4. Department of Psychology, University of British Columbia, Vancouver, British Columbia, Canada; 5. Institute for Neural Computation, and Emotient, Inc., San Diego, California; and. 6. Department of Pediatrics, University of California San Diego, San Diego, California; Rady Children's Hospital, San Diego, California jshuang@ucsd.edu.
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.
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.
Authors: Umadevan Rajasagaram; David McD Taylor; George Braitberg; James P Pearsell; Bronwyn A Capp Journal: J Paediatr Child Health Date: 2009-04 Impact factor: 1.954
Authors: Ahmed Bilal Ashraf; Simon Lucey; Jeffrey F Cohn; Tsuhan Chen; Zara Ambadar; Kenneth M Prkachin; Patricia E Solomon Journal: Image Vis Comput Date: 2009-10 Impact factor: 2.818
Authors: Kara Hawley; Jeannie S Huang; Matthew Goodwin; Damaris Diaz; Virginia R de Sa; Kathryn A Birnie; Christine T Chambers; Kenneth D Craig Journal: Ethics Behav Date: 2018-04-30
Authors: Xiaojing Xu; Kenneth D Craig; Damaris Diaz; Matthew S Goodwin; Murat Akcakaya; Büşra Tuğçe Susam; Jeannie S Huang; Virginia R de Sa Journal: CEUR Workshop Proc Date: 2018-07
Authors: Xiaojing Xu; Büsra Tuğce Susam; Hooman Nezamfar; Damaris Diaz; Kenneth D Craig; Matthew S Goodwin; Murat Akcakaya; Jeannie S Huang; R de Sa Virginia Journal: CEUR Workshop Proc Date: 2018-07
Authors: Busra T Susam; Murat Akcakaya; Hooman Nezamfar; Damaris Diaz; Xiaojing Xu; Virginia R de Sa; Kenneth D Craig; Jeannie S Huang; Matthew S Goodwin Journal: Annu Int Conf IEEE Eng Med Biol Soc Date: 2018-07
Authors: Alzbeta Glancova; Quan T Do; Devang K Sanghavi; Pablo Moreno Franco; Neethu Gopal; Lindsey M Lehman; Yue Dong; Brian W Pickering; Vitaly Herasevich Journal: Appl Clin Inform Date: 2021-02-24 Impact factor: 2.342