Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals
© 2018 IEEE. Currently there is no validated objective measure of pain. Recent neuroimaging studies have explored the feasibility of using functional near-infrared spectroscopy (fNIRS) to measure alterations in brain function in evoked and ongoing pain. In this study, we applied multi-task machine l...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/138077 |
| _version_ | 1811078736779411456 |
|---|---|
| author | Lopez-Martinez, Daniel Peng, Ke Steele, Sarah C. Lee, Arielle J. Borsook, David Picard, Rosalind W. |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Lopez-Martinez, Daniel Peng, Ke Steele, Sarah C. Lee, Arielle J. Borsook, David Picard, Rosalind W. |
| author_sort | Lopez-Martinez, Daniel |
| collection | MIT |
| description | © 2018 IEEE. Currently there is no validated objective measure of pain. Recent neuroimaging studies have explored the feasibility of using functional near-infrared spectroscopy (fNIRS) to measure alterations in brain function in evoked and ongoing pain. In this study, we applied multi-task machine learning methods to derive a practical algorithm for pain detection derived from fNIRS signals in healthy volunteers exposed to a painful stimulus. Especially, we employed multi-task multiple kernel learning to account for the inter-subject variability in pain response. Our results support the use of fNIRS and machine learning techniques in developing objective pain detection, and also highlight the importance of adopting personalized analysis in the process. |
| first_indexed | 2024-09-23T11:04:40Z |
| format | Article |
| id | mit-1721.1/138077 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:04:40Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1380772024-08-09T20:23:48Z Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals Lopez-Martinez, Daniel Peng, Ke Steele, Sarah C. Lee, Arielle J. Borsook, David Picard, Rosalind W. Massachusetts Institute of Technology. Media Laboratory Harvard-MIT Program in Health Sciences and Technology © 2018 IEEE. Currently there is no validated objective measure of pain. Recent neuroimaging studies have explored the feasibility of using functional near-infrared spectroscopy (fNIRS) to measure alterations in brain function in evoked and ongoing pain. In this study, we applied multi-task machine learning methods to derive a practical algorithm for pain detection derived from fNIRS signals in healthy volunteers exposed to a painful stimulus. Especially, we employed multi-task multiple kernel learning to account for the inter-subject variability in pain response. Our results support the use of fNIRS and machine learning techniques in developing objective pain detection, and also highlight the importance of adopting personalized analysis in the process. 2021-11-09T21:23:05Z 2021-11-09T21:23:05Z 2018-08 2019-08-02T11:07:00Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/138077 Lopez-Martinez, Daniel, Peng, Ke, Steele, Sarah C., Lee, Arielle J., Borsook, David et al. 2018. "Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals." en 10.1109/icpr.2018.8545823 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Lopez-Martinez, Daniel Peng, Ke Steele, Sarah C. Lee, Arielle J. Borsook, David Picard, Rosalind W. Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals |
| title | Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals |
| title_full | Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals |
| title_fullStr | Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals |
| title_full_unstemmed | Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals |
| title_short | Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals |
| title_sort | multi task multiple kernel machines for personalized pain recognition from functional near infrared spectroscopy brain signals |
| url | https://hdl.handle.net/1721.1/138077 |
| work_keys_str_mv | AT lopezmartinezdaniel multitaskmultiplekernelmachinesforpersonalizedpainrecognitionfromfunctionalnearinfraredspectroscopybrainsignals AT pengke multitaskmultiplekernelmachinesforpersonalizedpainrecognitionfromfunctionalnearinfraredspectroscopybrainsignals AT steelesarahc multitaskmultiplekernelmachinesforpersonalizedpainrecognitionfromfunctionalnearinfraredspectroscopybrainsignals AT leeariellej multitaskmultiplekernelmachinesforpersonalizedpainrecognitionfromfunctionalnearinfraredspectroscopybrainsignals AT borsookdavid multitaskmultiplekernelmachinesforpersonalizedpainrecognitionfromfunctionalnearinfraredspectroscopybrainsignals AT picardrosalindw multitaskmultiplekernelmachinesforpersonalizedpainrecognitionfromfunctionalnearinfraredspectroscopybrainsignals |