Towards a Physiology-Based Measure of Pain: Patterns of Human Brain Activity Distinguish Painful from Non-Painful Thermal Stimulation

Abstract

Pain often exists in the absence of observable injury; therefore, the gold standard for pain assessment has long been self-report. Because the inability to verbally communicate can prevent effective pain management, research efforts have focused on the development of a tool that accurately assesses pain without depending on self-report. Those previous efforts have not proven successful at substituting self-report with a clinically valid, physiology-based measure of pain. Recent neuroimaging data suggest that functional magnetic resonance imaging (fMRI) and support vector machine (SVM) learning can be jointly used to accurately assess cognitive states. Therefore, we hypothesized that an SVM trained on fMRI data can assess pain in the absence of self-report. In fMRI experiments, 24 individuals were presented painful and nonpainful thermal stimuli. Using eight individuals, we trained a linear SVM to distinguish these stimuli using whole-brain patterns of activity. We assessed the performance of this trained SVM model by testing it on 16 individuals whose data were not used for training. The whole-brain SVM was 81% accurate at distinguishing painful from non-painful stimuli (p<0.0000001). Using distance from the SVM hyperplane as a confidence measure, accuracy was further increased to 84%, albeit at the expense of excluding 15% of the stimuli that were the most difficult to classify. Overall performance of the SVM was primarily affected by activity in pain-processing regions of the brain including the primary somatosensory cortex, secondary somatosensory cortex, insular cortex, primary motor cortex, and cingulate cortex. Region of interest (ROI) analyses revealed that whole-brain patterns of activity led to more accurate classification than localized activity from individual brain regions. Our findings demonstrate that fMRI with SVM learning can assess pain without requiring any communication from the person being tested. We outline tasks that should be completed to advance this approach toward use in clinical settings.

Brain imaging tests for chronic pain: medical, legal and ethical issues and recommendations

“…Machine learning and statistical techniques are often used to identify patterns in these data, and are optimized to jointly predict patient status, the experience of pain, analgesia, and other outcomes. These approaches have been successfully used to decode some aspects of stimulus-evoked acute pain from patterns of brain activity, at least to some extent 51,[61][62][63][64][65][66][67][68][69][70][71] …”

Assessment of Patient Comfort During Palliative Sedation: Is it always Reliable?

“…Some scales have been developed for non-communicative patients as well, including the Critical Care Pain Observational Tool (CCPOT) [9], the Behavioral Pain Scale (BPS) [10], and the Richmond Agitation-Sedation Scale (RASS) [11] but several problems have been reported. A well-documented problem is that these scales cannot detect pain and awareness in all patients, for example because they depend on inferences made from patients' motor responses [12,13].…”

“…Paradoxically, the inability to report distress might also be aggravated or even blocked by the use of drugs that may abolish potential further communication and even facial expressions [12]. Hence, some patients might have subjective phenomenological awareness or suffering with very limited, fluctuating or absent behavioral motor signs of distress [13].…”

Stability of Pain Measures in a Different Stimuli Context

“…There are numerous methods of pain inducement but chemical 15 , mechanical 16 , thermal 17 and electrical 18 stimuli are most frequently used -none without its limitations. Additionally, while still in search for an accurate physiology-based pain measures 19 , a number of subjective pain measurement methods are availablepain threshold and tolerance along with the assessment of pain intensity and unpleasantness are just a few of many, commonly used in the experimental settings. All of them, much like the pain-inducement methods, have their advantages and disadvantages, and some researchers advocate the use of the multi-method approach 20 in order to get a better insight into the complex phenomenon of the pain perception.…”