Painometry: Wearable and objective quantification system for acute postoperative pain

Hoang Truong, Nam Bui, Zohreh Raghebi, Marta Ceko, Nhat Pham, Phuc Nguyen, Anh Nguyen, Taeho Kim, Katrina Siegfried, Evan Stene, Taylor Tvrdy, Logan Weinman, Thomas Payne, Devin Burke, Thang Dinh, Sidney D'Mello, Farnoush Banaei-Kashani, Tor Wager, Pavel Goldstein, Tam Vu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Over 50 million people undergo surgeries each year in the United States, with over 70% of them filling opioid prescriptions within one week of the surgery. Due to the highly addictive nature of these opiates, a post-surgical window is a crucial time for pain management to ensure accurate prescription of opioids. Drug prescription nowadays relies primarily on self-reported pain levels to determine the frequency and dosage of pain drug. Patient pain self-reports are, however, influenced by subjective pain tolerance, memories of past painful episodes, current context, and the patient's integrity in reporting their pain level. Therefore, objective measures of pain are needed to better inform pain management. This paper explores a wearable system, named Painometry, which objectively quantifies users' pain perception based-on multiple physiological signals and facial expressions of pain. We propose a sensing technique, called sweep impedance profiling (SIP), to capture the movement of the facial muscle corrugator supercilii, one of the important physiological expressions of pain. We deploy SIP together with other biosignals, including electroencephalography (EEG), photoplethysmogram (PPG), and galvanic skin response (GSR) for pain quantification. From the anatomical and physiological correlations of pain with these signals, we designed Painometry, a multimodality sensing system, which can accurately quantify different levels of pain safely. We prototyped Painometry by building a custom hardware, firmware, and associated software. Our evaluations use the prototype on 23 subjects, which corresponds to 8832 data points from 276 minutes of an IRB-approved experimental pain-inducing protocol. Using leave-one-out cross-validation to estimate performance on unseen data shows 89.5% and 76.7% accuracy of quantification under 3 and 4 pain states, respectively.

Original languageEnglish
Title of host publicationMobiSys 2020 - Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services
PublisherAssociation for Computing Machinery, Inc
Pages419-433
Number of pages15
ISBN (Electronic)9781450379540
DOIs
StatePublished - 15 Jun 2020
Event18th ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2020 - Toronto, Canada
Duration: 15 Jun 202019 Jun 2020

Publication series

NameMobiSys 2020 - Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services

Conference

Conference18th ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2020
Country/TerritoryCanada
CityToronto
Period15/06/2019/06/20

Bibliographical note

Funding Information:
Acknowledgements. We thank Dr. Sung-Ju Lee for serving as the shepherd for the paper and the reviewers for their insightful comments. We also thank Mr. Art Atkison for his consultancy in the writing of this paper. Our research was partially funded by NSF CNS/CSR #1846541, NSF SCH #1602428.

Publisher Copyright:
© 2020 ACM.

Keywords

  • Impedance sensing
  • Opioid overdose
  • Pain quantification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Painometry: Wearable and objective quantification system for acute postoperative pain'. Together they form a unique fingerprint.

Cite this