Personalized Brain Decoding of Spontaneous Pain in Individuals with Chronic Pain
Poster No:
2507
Submission Type:
Abstract Submission
Authors:
Jae-Joong Lee1, Choong-Wan Woo2
Institutions:
1Institute for Basic Science (IBS), Suwon-si, Korea, Republic of, 2Sungkyunkwan University, Suwon-si, Gyeonggi-do
First Author:
Co-Author:
Introduction:
Current assessment of chronic pain lacks objective biomarkers. Neuroimaging has shown the potential as surrogates of subjective pain reports in healthy population, but whether this measurement has validity for single individuals with chronic pain remains unclear.
Methods:
We studied a series of patients with fibromyalgia, characterized as chronic widespread pain. For extensive sampling of brain activity within individuals, participants underwent longitudinal sessions of functional magnetic resonance imaging (fMRI) scan on different days. Each session consisted of the three runs of 10 min fMRI scan, where we recorded the participants' whole-brain activity with their concurrent self-reports of spontaneous pain ratings. Machine learning algorithms were used to identify the personalized fMRI biomarkers that can decode continuous fluctuation of spontaneous pain.
·Figure 1. Study Overview.
Results:
Two out of three enrolled participants completed more than 15 required sessions of fMRI scan (Participant 1: 23 sessions; Participant 2: 28 sessions). The personalized biomarkers predicted changes in spontaneous pain ratings across sessions, runs, and minutes (Participant 1: Prediction-outcome correlation r = 0.40-0.61; Participant 2: r = 0.51-0.65), and discriminated the median-dichotomized high pain vs. low pain (Participant 1: Area under the curve [AUC] = 0.71-0.90; Participant 2: AUC = 0.76-0.94) with cross-validation. These biomarkers relied on individually unique patterns of whole-brain interaction for decoding, and were not predictive of the other participant's pain.
·Figure 2. Prediction Performances.
Conclusions:
Neuroimaging can be used to decode spontaneous pain in single individuals with chronic pain.
Modeling and Analysis Methods:
Classification and Predictive Modeling 2
fMRI Connectivity and Network Modeling
Perception, Attention and Motor Behavior:
Perception: Pain and Visceral 1
Keywords:
Emotions
FUNCTIONAL MRI
Machine Learning
Multivariate
Pain
Somatosensory
1|2Indicates the priority used for review
Provide references using author date format
Gordon, E. M., T. O. Laumann, A. W. Gilmore, D. J. Newbold, D. J. Greene, J. J. Berg, M. Ortega, C. Hoyt-Drazen, C. Gratton, H. Sun, J. M. Hampton, R. S. Coalson, A. L. Nguyen, K. B. McDermott, J. S. Shimony, A. Z. Snyder, B. L. Schlaggar, S. E. Petersen, S. M. Nelson and N. U. F. Dosenbach (2017). "Precision Functional Mapping of Individual Human Brains." Neuron 95(4): 791-807 e797.
Lee, J., I. Mawla, J. Kim, M. L. Loggia, A. Ortiz, C. Jung, S. T. Chan, J. Gerber, V. J. Schmithorst, R. R. Edwards, A. D. Wasan, C. Berna, J. Kong, T. J. Kaptchuk, R. L. Gollub, B. R. Rosen and V. Napadow (2019). "Machine learning-based prediction of clinical pain using multimodal neuroimaging and autonomic metrics." Pain 160(3): 550-560.
Lee, J. J., H. J. Kim, M. Ceko, B. Y. Park, S. A. Lee, H. Park, M. Roy, S. G. Kim, T. D. Wager and C. W. Woo (2021). "A neuroimaging biomarker for sustained experimental and clinical pain." Nat Med 27(1): 174-182.
Mayr, A., P. Jahn, A. Stankewitz, B. Deak, A. Winkler, V. Witkovsky, O. Eren, A. Straube and E. Schulz (2022). "Patients with chronic pain exhibit individually unique cortical signatures of pain encoding." Hum Brain Mapp 43(5): 1676-1693.
Wager, T. D., L. Y. Atlas, M. A. Lindquist, M. Roy, C. W. Woo and E. Kross (2013). "An fMRI-based neurologic signature of physical pain." N Engl J Med 368(15): 1388-1397.