Biomarkers for Musculoskeletal Pain Conditions: Use of Brain Imaging and Machine Learning

Abstract

Chronic musculoskeletal pain condition often shows poor correlations between tissue abnormalities and clinical pain. Therefore, classification of pain conditions like chronic low back pain, osteoarthritis, and fibromyalgia depends mostly on self report and less on objective findings like X-ray or magnetic resonance imaging (MRI) changes. However, recent advances in structural and functional brain imaging have identified brain abnormalities in chronic pain conditions that can be used for illness classification. Because the analysis of complex and multivariate brain imaging data is challenging, machine learning techniques have been increasingly utilized for this purpose. The goal of machine learning is to train specific classifiers to best identify variables of interest on brain MRIs (i.e., biomarkers). This report describes classification techniques capable of separating MRI-based brain biomarkers of chronic pain patients from healthy controls with high accuracy (70-92%) using machine learning, as well as critical scientific, practical, and ethical considerations related to their potential clinical application. Although self-report remains the gold standard for pain assessment, machine learning may aid in the classification of chronic pain disorders like chronic back pain and fibromyalgia as well as provide mechanistic information regarding their neural correlates.

Sensor Technologies to Manage the Physiological Traits of Chronic Pain: A Review

“…The characteristics of white matter (axonal integrity) or gray matter (integrity of neuronal bodies) are related to the structural characteristics of the brain assessed through fMRI [255]. Using this technique as a basis, alterations in white matter have been related to different chronic pain conditions [256,257].…”

“…As the evaluation of chronic pain is a complex task that often poses a challenge due to the amount of data to be managed, especially in the case of facial expression images, MRI, and multisensory approaches combining different approaches described so far, in recent years numerous machine learning algorithms have been proposed [253,255,282]. In a generic way, pain assessment is usually performed through procedures in which the following main stages can be distinguished:…”

Artificial Intelligence for Good Health: A Scoping Review of the Ethics Literature

“…These physicians stated that Watson's recommendations were too narrowly focused on American studies and physician expertise, and failed to account for international knowledge and contexts [50]. The distrust amongst HCPs was also raised with regards to machine learning programs being difficult to both understand and explain [51,52]. In contrast, a fear exists that some HCPs may place too much faith in the outputs of machine learning processes, even if the resulting reports, such as brain mapping results from AI systems, are inconclusive [47].…”

“…Illustrated in the literature reviewed were overarching ethical concerns about privacy, trust, accountability, and bias, each of which were both interdependent and mutually reinforcing. Accountability, for instance, was a noted concern when considering who ought to bear responsibility for AI errors in patient diagnoses [51,56,57], while also a recognized issue in protecting patient privacy within data sharing partnerships [2]. The security of confidential patient data, in turn, was identified as critical for eliciting patient trust in the use of AI technology for health [45].…”

The “Journal of Functional Morphology and Kinesiology” Journal Club Series: Highlights on Recent Papers in Musculoskeletal Disorders

“…Interestingly, a "multisensory" classifier, which was trained on non-painful stimulation, showed increased responses of the insula/operculum, posterior cingulate, and medial prefrontal regions and reduced responses of the primary and secondary sensory cortices, basal ganglia, and cerebellum [28]. Similarly, Boissoneault J et al [29] described classification ML techniques which are capable of separating MRI-based brain biomarkers of chronic pain patients from healthy controls with high accuracy. Finally, Sevel et al [30] used ML to compare the performance of structural MRI data and self-reported measures for distinguishing healthy from FM and CHS patients.…”