This exploratory interventional study aims at exploring the feasibility of using physiological signals recorded through wearable devices, together with artificial intelligence techniques, to assess pain automatically and objectively. Automatic methods to assess presence/absence of pain, discern nociceptive from neuropathic pain, and estimate the intensity of pain will be trained an tested on a population of multiple sclerosis patients undergoing neurorehabilitation.
In patients with Multiple Sclerosis (MS), pain is one of the most common symptoms. The pain described by MS patients is often diffuse, chronic, and debilitating, generally associated with psychological distress and decreased daily functioning. The presence of pain adversely affects the neurorehabilitation process itself. Patients with pain may refuse to participate in therapy sessions or request to terminate early. However, the link between the frequency and/or intensity of pain and the rehabilitation process is largely unexplored. This is also exacerbated by the different sources of pain experienced by MS patients who require neurorehabilitative interventions. In clinical practice, pain assessment is conducted mainly using self-administered questionnaires or scales. These tools however can be influenced by many factors, including emotional or cognitive aspects and cannot give an objective measure of the pain experience. To date, there are no objective and simple-to-use clinical methods that allow objective quantification of the painful experience and a diagnostic differentiation between the two main types of pain, which are nociceptive pain (arising from nociceptive stimuli), and neuropathic pain (caused by a lesion or a pathology of the somatosensory nervous system). In this sense, wearable technologies which can continuously monitor physiological parameters related to pain can be used for the quantification of physiological measures related to pain experience. AIMS: This study aims at exploring the feasibility of developing methods based on wearable sensors and artificial intelligence algorithms to assess pain objectively and automatically in patients undergoing neurorehabilitation. The specific objectives of this study are the following: * To assess the feasibility of developing a differential diagnosis method to evaluate the absence or presence of pain * To assess the feasibility of developing a regression model to evaluate the intensity of pain * To assess the feasibility of developing a differential diagnosis method to discern the type of pain (i.e., nociceptive vs. neuropathic pain)
Study Type
INTERVENTIONAL
Allocation
NA
Purpose
DIAGNOSTIC
Masking
NONE
Enrollment
15
The intervention consists of 48-h monitoring by using two types of monitoring: an objective monitoring, through a class IIa wearable medical device recording four physiological signals, and a subjective monitoring through a questionnaire developed with Microsoft Forms that can be compiled with a smartphone. The monitoring will be conducted during a motor neurorehabilitation treatment, 24 hours before and 24 hours after the treatment at the participant's home. Besides this monitoring, stratification questionnaires will be administered to each participant to be stratified in one of the three categories (absence of pain, nociceptive pain, or neuropathic pain) based on the following timeline: t0: baseline t1: pre-treatment t2: post-treatment t3: follow-up
Irccs - Istituto Delle Scienze Neurologiche
Bologna, Italy
RECRUITINGNumber of registrations
Number of concurrent physiological signal registrations and pain assessments through CRF monitoring questionnaire and CRF monitoring questionnaire-intervention. Diagnostic performance of the classifier (i.e., sensitivity, specificity, predictive value) against the gold standard (outcomes from CRF monitoring questionnaire and CRF monitoring questionnaire-intervention).
Time frame: The monitoring will be conducted during the intervention time frame [48 hours]
regression model - intensity of pain
Number of concurrent physiological signal registrations and pain assessments through CRF monitoring questionnaire and CRF monitoring questionnaire-intervention. Coefficient of determination of the regression model against the gold standard (outcomes from CRF monitoring questionnaires and CRF monitoring questionnaires-intervention).
Time frame: 24 hours before and 24 hours after the treatment at the participant's home
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.