{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T22:25:40Z","timestamp":1794435940240,"version":"4.9.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Pain is a highly unpleasant sensory and emotional experience, and no objective diagnosis test exists to assess it. In clinical practice there are two main methods for the estimation of pain, a patient\u2019s self-report and clinical judgement. However, these methods are highly subjective and the need of biomarkers to measure pain is important to improve pain management, reduce risk factors, and contribute to a more objective, valid, and reliable diagnosis. Therefore, in this study we propose the use of functional near-infrared spectroscopy (fNIRS) and machine learning for the identification of a possible biomarker of pain. We collected pain information from 18 volunteers using the thermal test of the quantitative sensory testing (QST) protocol, according to temperature level (cold and hot) and pain intensity (low and high). Feature extraction was completed in three different domains (time, frequency, and wavelet), and a total of 69 features were obtained. Feature selection was carried out according to three criteria, information gain (IG), joint mutual information (JMI), and Chi-squared (<jats:italic>\u03c7<\/jats:italic><jats:sup>2<\/jats:sup>). The significance of each feature ranking was evaluated using three learning models separately, linear discriminant analysis (LDA), the K-nearest neighbour (K-NN) and support vector machines (SVM) using the linear and Gaussian and polynomial kernels. The results showed that the Gaussian SVM presented the highest accuracy (94.17%) using only 25 features to identify the four types of pain in our database. In addition, we propose the use of the top 13 features according to the JMI criteria, which exhibited an accuracy of 89.44%, as promising biomarker of pain. This study contributes to the idea of developing an objective assessment of pain and proposes a potential biomarker of human pain using fNIRS.<\/jats:p>","DOI":"10.1038\/s41598-019-42098-w","type":"journal-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T10:04:10Z","timestamp":1554372250000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":102,"title":["A Machine Learning Approach for the Identification of a Biomarker of Human Pain using fNIRS"],"prefix":"10.1038","volume":"9","author":[{"given":"Raul","family":"Fernandez Rojas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keng-Liang","family":"Ou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"42098_CR1","doi-asserted-by":"crossref","unstructured":"Jain, K. K. & Jain, K. K. The handbook of biomarkers (Springer, 2010).","DOI":"10.1007\/978-1-60761-685-6"},{"key":"42098_CR2","unstructured":"Marieb, E. N. Human Anatomy & Physiology (Benjamin-Cummings Publishing Company, 1989)."},{"key":"42098_CR3","doi-asserted-by":"publisher","first-page":"1326","DOI":"10.1093\/brain\/awf137","volume":"125","author":"K Bornh\u00f6vd","year":"2002","unstructured":"Bornh\u00f6vd, K. et al. Painful stimuli evoke different stimulus\u2013response functions in the amygdala, prefrontal, insula and somatosensory cortex: a single-trial fmri study. Brain 125, 1326\u20131336 (2002).","journal-title":"Brain"},{"key":"42098_CR4","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1111\/anae.13018","volume":"70","author":"R Cowen","year":"2015","unstructured":"Cowen, R., Stasiowska, M. K., Laycock, H. & Bantel, C. Assessing pain objectively: the use of physiological markers. Anaesth. 70, 828\u2013847 (2015).","journal-title":"Anaesth."},{"key":"42098_CR5","unstructured":"Gregory, J. How can we assess pain in people who have difficulty communicating? a practice development project identifying a pain assessment tool for acute care. Int. Pract. Dev. J. 2 (2012)."},{"key":"42098_CR6","doi-asserted-by":"publisher","first-page":"e0166976","DOI":"10.1371\/journal.pone.0166976","volume":"11","author":"EM Sobas","year":"2016","unstructured":"Sobas, E. M. et al. Reliability of potential pain biomarkers in the saliva of healthy subjects: Inter-individual differences and intersession variability. PloS one 11, e0166976 (2016).","journal-title":"PloS one"},{"key":"42098_CR7","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1002\/art.23223","volume":"58","author":"RE Harris","year":"2008","unstructured":"Harris, R. E. et al. Dynamic levels of glutamate within the insula are associated with improvements in multiple pain domains in fibromyalgia. Arthritis & Rheum. Off. J. Am. Coll. Rheumatol. 58, 903\u2013907 (2008).","journal-title":"Arthritis & Rheum. Off. J. Am. Coll. Rheumatol."},{"key":"42098_CR8","doi-asserted-by":"crossref","unstructured":"Rojas, R. F., Huang, X., Romero, J. & Ou, K.-L. fnirs approach to pain assessment for non-verbal patients. In International Conference on Neural Information Processing, 778\u2013787 (Springer, 2017).","DOI":"10.1007\/978-3-319-70093-9_83"},{"key":"42098_CR9","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1139\/h04-031","volume":"29","author":"M Ferrari","year":"2004","unstructured":"Ferrari, M., Mottola, L. & Quaresima, V. Principles, techniques, and limitations of near infrared spectroscopy. Can. journal applied physiology 29, 463\u2013487 (2004).","journal-title":"Can. journal applied physiology"},{"key":"42098_CR10","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1255\/jnirs.1239","volume":"24","author":"RF Rojas","year":"2016","unstructured":"Rojas, R. F., Huang, X. & Ou, K.-L. Region of interest detection and evaluation in functional near infrared spectroscopy. J. Near Infrared Spectrosc. 24, 317\u2013326 (2016).","journal-title":"J. Near Infrared Spectrosc."},{"key":"42098_CR11","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1016\/j.neuroimage.2010.11.004","volume":"56","author":"S Lemm","year":"2011","unstructured":"Lemm, S., Blankertz, B., Dickhaus, T. & M\u00fcller, K.-R. Introduction to machine learning for brain imaging. Neuroimage 56, 387\u2013399 (2011).","journal-title":"Neuroimage"},{"key":"42098_CR12","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1097\/j.pain.0000000000001118","volume":"159","author":"J L\u00f6tsch","year":"2018","unstructured":"L\u00f6tsch, J. & Ultsch, A. Machine learning in pain research. Pain 159, 623 (2018).","journal-title":"Pain"},{"key":"42098_CR13","doi-asserted-by":"publisher","first-page":"e24124","DOI":"10.1371\/journal.pone.0024124","volume":"6","author":"JE Brown","year":"2011","unstructured":"Brown, J. E., Chatterjee, N., Younger, J. & Mackey, S. Towards a physiology-based measure of pain: patterns of human brain activity distinguish painful from non-painful thermal stimulation. PLoS One 6, e24124 (2011).","journal-title":"PLoS One"},{"key":"42098_CR14","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.1002\/ejp.734","volume":"19","author":"M Gram","year":"2015","unstructured":"Gram, M., Graversen, C., Olesen, A. E. & Drewes, A. Machine learning on encephalographic activity may predict opioid analgesia. Eur. J. Pain 19, 1552\u20131561 (2015).","journal-title":"Eur. J. Pain"},{"key":"42098_CR15","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.neuroimage.2013.05.017","volume":"81","author":"G Huang","year":"2013","unstructured":"Huang, G. et al. A novel approach to predict subjective pain perception from single-trial laser-evoked potentials. Neuroimage 81, 283\u2013293 (2013).","journal-title":"Neuroimage"},{"key":"42098_CR16","doi-asserted-by":"crossref","unstructured":"Guyon, I. & Elisseeff, A. An introduction to feature extraction. Featur. extraction 1\u201325 (2006).","DOI":"10.1007\/978-3-540-35488-8_1"},{"key":"42098_CR17","first-page":"70","volume":"69","author":"P Sondhi","year":"2009","unstructured":"Sondhi, P. Feature construction methods: a survey. sifaka. cs. uiuc. edu 69, 70\u201371 (2009).","journal-title":"sifaka. cs. uiuc. edu"},{"key":"42098_CR18","unstructured":"Zheng, A. Mastering feature engineering: Principles and techniques for data scientists (2016)."},{"key":"42098_CR19","doi-asserted-by":"crossref","unstructured":"Krusienski, D. J., McFarland, D. J., Principe, J. C. &Wolpaw, E. Bci signal processing: feature extraction. Brain\u2013computer interfaces: principles practice. Oxf. Univ. Press. New York 123\u2013146 (2012).","DOI":"10.1093\/acprof:oso\/9780195388855.003.0007"},{"key":"42098_CR20","doi-asserted-by":"crossref","unstructured":"Mokhlesabadifarahani, B. & Gunjan, V. K. EMG Signals Characterization in Three States of Contraction by Fuzzy Network and Feature Extraction (Springer, 2015).","DOI":"10.1007\/978-981-287-320-0"},{"key":"42098_CR21","doi-asserted-by":"crossref","unstructured":"Rojas, R. F., Huang, X. & Ou, K.-L. Toward a functional near-infrared spectroscopy-based monitoring of pain assessment for nonverbal patients. J. Biomed. Opt. 22, 22 \u2013 22 \u2013 12 (2017).","DOI":"10.1117\/1.JBO.22.10.106013"},{"key":"42098_CR22","first-page":"1388","volume":"368","author":"TD Wager","year":"2013","unstructured":"Wager, T. D. et al. An fmri-based neurologic signature of physical pain. New Engl. J. Medicine 368, 1388\u20131397 (2013).","journal-title":"J. Medicine"},{"key":"42098_CR23","doi-asserted-by":"publisher","first-page":"e0165226","DOI":"10.1371\/journal.pone.0165226","volume":"11","author":"CM Aasted","year":"2016","unstructured":"Aasted, C. M. et al. Frontal lobe hemodynamic responses to painful stimulation: a potential brain marker of nociception. PLoS One 11, e0165226 (2016).","journal-title":"PLoS One"},{"key":"42098_CR24","doi-asserted-by":"publisher","first-page":"2758","DOI":"10.1109\/78.650102","volume":"45","author":"B Scholkopf","year":"1997","unstructured":"Scholkopf, B. et al. Comparing support vector machines with gaussian kernels to radial basis function classifiers. IEEE transactions on Signal Process. 45, 2758\u20132765 (1997).","journal-title":"IEEE transactions on Signal Process."},{"key":"42098_CR25","doi-asserted-by":"crossref","unstructured":"Ben-Hur, A. & Weston, J. A user\u2019s guide to support vector machines. In Data mining techniques for the life sciences, 223\u2013239 (Springer, 2010).","DOI":"10.1007\/978-1-60327-241-4_13"},{"key":"42098_CR26","doi-asserted-by":"crossref","unstructured":"Lee, C.-H. et al. Analysis for distinctive activation patterns of pain and itchy in the human brain cortex measured using near infrared spectroscopy (nirs) (2014).","DOI":"10.1371\/journal.pone.0075360"},{"key":"42098_CR27","doi-asserted-by":"publisher","first-page":"031405","DOI":"10.1117\/1.NPh.3.3.031405","volume":"3","author":"I Tachtsidis","year":"2016","unstructured":"Tachtsidis, I. & Scholkmann, F. False positives and false negatives in functional near-infrared spectroscopy: issues, challenges, and the way forward. Neurophotonics 3, 031405\u2013031405 (2016).","journal-title":"Neurophotonics"},{"key":"42098_CR28","doi-asserted-by":"publisher","first-page":"011014","DOI":"10.1117\/1.1852552","volume":"10","author":"Y Zhang","year":"2005","unstructured":"Zhang, Y., Brooks, D. H., Franceschini, M. A. & Boas, D. A. Eigenvector-based spatial filtering for reduction of physiological interference in diffuse optical imaging. J. biomedical optics 10, 011014\u201301101411 (2005).","journal-title":"J. biomedical optics"},{"key":"42098_CR29","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3390\/s19020394","volume":"19","author":"R Fernandez Rojas","year":"2019","unstructured":"Fernandez Rojas, R., Liao, M., Romero, J., Huang, X. & Ou, K.-L. Cortical network response to acupuncture and the effect of the hegu point: An fnirs study. Sensors 19, 394 (2019).","journal-title":"Sensors"},{"key":"42098_CR30","unstructured":"Rojas, R. F., Huang, X., Hernandez-Juarez, J. & Ou, K.-L. Physiological fluctuations show frequency-specific networks in fnirs signals during resting state. In Engineering in Medicine and Biology Society (EMBC), 2017 39th Annual International Conference of the IEEE, 2550\u20132553 (IEEE, 2017)."},{"key":"42098_CR31","doi-asserted-by":"crossref","unstructured":"Molavi, B., Dumont, G. & Shadgan, B. Motion artifact removal from muscle nir spectroscopy measurements. In Electrical and Computer Engineering (CCECE), 2010 23rd Canadian Conference on, 1\u20134 (IEEE, 2010).","DOI":"10.1109\/CCECE.2010.5575241"},{"key":"42098_CR32","unstructured":"Duda, R. O., Hart, P. E. & Stork, D. G. Pattern classification (John Wiley & Sons, 2012)."},{"key":"42098_CR33","unstructured":"Zhao, Z. et al. Advancing feature selection research. ASU feature selection repository 1\u201328 (2010)."},{"key":"42098_CR34","doi-asserted-by":"crossref","unstructured":"Novakovi\u0107, J. Toward optimal feature selection using ranking methods and classification algorithms. Yugosl. J. Oper. Res. 21 (2016).","DOI":"10.2298\/YJOR1101119N"},{"key":"42098_CR35","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.pain.2006.01.041","volume":"123","author":"R Rolke","year":"2006","unstructured":"Rolke, R. et al. Quantitative sensory testing in the german research network on neuropathic pain (dfns): standardized protocol and reference values. Pain 123, 231\u2013243 (2006).","journal-title":"Pain"},{"key":"42098_CR36","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1088\/0031-9155\/47\/7\/309","volume":"47","author":"T Yamamoto","year":"2002","unstructured":"Yamamoto, T. & Kato, T. Paradoxical correlation between signal in functional magnetic resonance imaging and deoxygenated haemoglobin content in capillaries: a new theoretical explanation. Phys. medicine biology 47, 1121 (2002).","journal-title":"Phys. medicine biology"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-019-42098-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-019-42098-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-019-42098-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T08:26:18Z","timestamp":1671265578000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-019-42098-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,12]]}},"alternative-id":["42098"],"URL":"https:\/\/doi.org\/10.1038\/s41598-019-42098-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"8 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"5645"}}