Pain level recognition using kinematics and muscle activity for physical rehabilitation in chronic pain

Abstract

People with chronic musculoskeletal pain would benefit from technology that provides run-time personalized feedback and help adjust their physical exercise plan. However, increased pain during physical exercise, or anxiety about anticipated pain increase, may lead to setback and intensified sensitivity to pain. Our study investigates the possibility of detecting pain levels from the quality of body movement during two functional physical exercises. By analyzing recordings of kinematics and muscle activity, our feature optimization algorithms and machine learning techniques can automatically discriminate between people with low level pain and high level pain and control participants while exercising. Best results were obtained from feature set optimization algorithms: 94% and 80% for the full trunk flexion and sit-to-stand movements respectively using Support Vector Machines. As depression can affect pain experience, we included participants' depression scores on a standard questionnaire and this improved discrimination between the control participants and the people with pain when Random Forests were used.

Human Observer and Automatic Assessment of Movement Related Self-Efficacy in Chronic Pain: From Exercise to Functional Activity

“…guarding). Among the most recent works are the studies of [39] and [40] [41]. Using, motion capture sensors mounted on screws inserted in the spine during surgery, [39] automatically classified 11 points of pain intensities of people with chronic pain with maximum error of 0.25 points.…”

Methods for Person-Centered Continuous Pain Intensity Assessment From Bio-Physiological Channels

“…Chu et al [13] used blood volume pulse (BVP), electrocardiogram (ECG) and skin conductance level (SCL) in combination with linear discriminant analysis (LDA) as a classifier in order to discriminate between seven physiological states including five levels of pain. Olugbade et al [14] used electromyography (EMG) paired with the analysis of body movements in combination with Random Forests (RF) and Support Vector Machines (SVM) as classifiers to distinguish between three different pain states. However, the latter focuses on an offline scenario where the entire dataset is completely pre-processed before the analysis and classification processes are undertaken.…”

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

“…By definition, chronic pain lasts over 3-6 months [7] and is not solved with treatment [8]. Its origin may be nociceptive or neuropathic [7,9], and it can be triggered by various causes (chronic musculoskeletal pain [10,11], chronic low back pain [12], fibromyalgia [13], tension-type headache [14], osteoarthritis [15], whiplash [16], heart and respiratory systems [7,17], endometriosis [18], etc.). Once developed, it may become resistant to standard treatments, greatly affecting patient quality of life [4].…”

“…Chronic pain is an important health challenge, as it represents 80% of physician visits [8]. 10% to 55% people in the world suffer chronic pain [7] (19% adults in Europe and 30% in the United States) [11]. It has been associated with great morbidity [8] and has also been proved to cause depression, neuroticism, sleep disorders, and anxiety [7].…”