Test-retest reliability of pain-related brain activity in healthy controls undergoing experimental thermal pain

Abstract

Although functional magnetic resonance imaging (fMRI) has been proposed as a method to elucidate pain-related biomarkers, little information exists related to psychometric properties of fMRI findings. This knowledge is essential for potential translation of this technology to clinical settings. The purpose of this study was to assess the test-retest reliability of pain-related brain activity and how it compares to the reliability of self-report. Twenty-two healthy controls (mean age = 22.6 years, standard deviation = 2.9) underwent 3 runs of an fMRI paradigm that used thermal stimuli to elicit experimental pain. Functional MRI summary statistics related to brain activity during thermal stimulation periods were extracted from bilateral anterior cingulate cortices and anterior insula. Intraclass correlations (ICCs) were conducted on these summary statistics and generally showed "good" test-retest reliability in all regions of interest (ICC range = .32-.88; mean = .71); however, these results did not surpass ICC values from pain ratings, which fell within the "excellent" range (ICC range = .93-.96; mean = .94). Findings suggest that fMRI is a valuable tool for measuring pain mechanisms but did not show an adequate level of test-retest reliability for fMRI to potentially act as a surrogate for individuals' self-report of pain.

Perspective: This study is one of the first reports to demonstrate the test-retest reliability of fMRI findings related to pain processing and provides a comparison to the reliability of subjective reports of pain. This information is essential for determining whether fMRI technology should be potentially translated for clinical use.

Keywords: Functional magnetic resonance imaging; anterior cingulate cortex; insula; test-retest reliability.

Figure 1

Three fMRI runs were collected. The paradigm for each run included 16 4-second thermal pulses with a 12-second interstimulus interval. The temperature used for the thermal pulses was specific to each participant, based on quantitative sensory testing prior to scanning. Participants rated pain intensity using a computerized VAS subsequent to each stimulus.

Figure 2

A group-level contrast was calculated to examine brain activity associated with painful thermal stimuli compared to no stimulus (orange). Results showed significant activity within our a priori ROIs of bilateral ACC and aINS (p_FDR < .001 and p_FDR < .05, respectively). Anatomical ROIs used to extract individual-level fMRI summary statistics are overlaid on the activation map in purple.