Multi-task neural networks for personalized pain recognition from physiological signals

Pain is a complex and subjective experience that poses a number of measurement challenges. While self-report by the patient is viewed as the gold standard of pain assessment, this approach fails when patients cannot verbally communicate pain intensity or lack normal mental abilities. Here, we presen...

Full description

Bibliographic Details
Main Authors: Lopez Martinez, Daniel, Picard, Rosalind W.
Other Authors: Massachusetts Institute of Technology. Institute for Medical Engineering & Science
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE) 2019
Online Access:https://hdl.handle.net/1721.1/121967
_version_ 1826199873992523776
author Lopez Martinez, Daniel
Picard, Rosalind W.
author2 Massachusetts Institute of Technology. Institute for Medical Engineering & Science
author_facet Massachusetts Institute of Technology. Institute for Medical Engineering & Science
Lopez Martinez, Daniel
Picard, Rosalind W.
author_sort Lopez Martinez, Daniel
collection MIT
description Pain is a complex and subjective experience that poses a number of measurement challenges. While self-report by the patient is viewed as the gold standard of pain assessment, this approach fails when patients cannot verbally communicate pain intensity or lack normal mental abilities. Here, we present a pain intensity measurement method based on physiological signals. Specifically, we implement a multi-task learning approach based on neural networks that accounts for individual differences in pain responses while still leveraging data from across the population. We test our method in a dataset containing multi-modal physiological responses to nociceptive pain.
first_indexed 2024-09-23T11:27:28Z
format Article
id mit-1721.1/121967
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T11:27:28Z
publishDate 2019
publisher Institute of Electrical and Electronics Engineers (IEEE)
record_format dspace
spelling mit-1721.1/1219672022-09-27T19:40:15Z Multi-task neural networks for personalized pain recognition from physiological signals Lopez Martinez, Daniel Picard, Rosalind W. Massachusetts Institute of Technology. Institute for Medical Engineering & Science Harvard University--MIT Division of Health Sciences and Technology Massachusetts Institute of Technology. Media Laboratory Pain is a complex and subjective experience that poses a number of measurement challenges. While self-report by the patient is viewed as the gold standard of pain assessment, this approach fails when patients cannot verbally communicate pain intensity or lack normal mental abilities. Here, we present a pain intensity measurement method based on physiological signals. Specifically, we implement a multi-task learning approach based on neural networks that accounts for individual differences in pain responses while still leveraging data from across the population. We test our method in a dataset containing multi-modal physiological responses to nociceptive pain. 2019-08-02T19:37:08Z 2019-08-02T19:37:08Z 2018-02 2017-10 2019-08-02T11:19:28Z Article http://purl.org/eprint/type/ConferencePaper 978-1-5386-0680-3 https://hdl.handle.net/1721.1/121967 Lopez-Martinez, Daniel and Rosalind Picard. "Multi-task neural networks for personalized pain recognition from physiological signals." Seventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), October 2017, San Antonio, Texas, USA, IEEE, Febraury 2018 © 2017 IEEE en http://dx.doi.org/10.1109/ACIIW.2017.8272611 Seventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv
spellingShingle Lopez Martinez, Daniel
Picard, Rosalind W.
Multi-task neural networks for personalized pain recognition from physiological signals
title Multi-task neural networks for personalized pain recognition from physiological signals
title_full Multi-task neural networks for personalized pain recognition from physiological signals
title_fullStr Multi-task neural networks for personalized pain recognition from physiological signals
title_full_unstemmed Multi-task neural networks for personalized pain recognition from physiological signals
title_short Multi-task neural networks for personalized pain recognition from physiological signals
title_sort multi task neural networks for personalized pain recognition from physiological signals
url https://hdl.handle.net/1721.1/121967
work_keys_str_mv AT lopezmartinezdaniel multitaskneuralnetworksforpersonalizedpainrecognitionfromphysiologicalsignals
AT picardrosalindw multitaskneuralnetworksforpersonalizedpainrecognitionfromphysiologicalsignals