Pain Prediction Via Machine Learning: Electrical Thresholds and Interoception

The goal of this observational study is to predict (retrospective and prospective) musculoskeletal pain in university students using machine learning models based on electrical threshold measurements and interoceptive awareness. The main question it aims to answer is: Can electrical sensory, motor, and pain thresholds, along with interoceptive awareness scores, predict musculoskeletal pain status in young adults using machine learning algorithms? Participants will: Complete demographic, healthy lifestyle (physical activity, sitting time, meal frequency), and substance use (ASSIST v3.0) questionnaires. Complete self-report surveys including the Nordic Musculoskeletal Questionnaire (NMQ) and the Multidimensional Assessment of Interoceptive Awareness (MAIA-2). Undergo quantitative electrical threshold testing on their dominant hand, which includes 3 consecutive measurements of sensory threshold, motor threshold (after a 10-minute rest), and pain threshold (after another 10-minute rest).

Inclusion criteria: * Being healthy and aged 18-25 * Having the right hand as the dominant extremity * Being able to communicate effectively and understand the study procedure * Being willing to participate in the study and having signed the written informed consent Exclusion criteria: * Presence of continuous or periodic pain in the same region over the last 3 months (presence of chronic pain) * Presence of sleep problems * History of severe menstrual or abdominal pain * Diagnosis of an endocrinological, psychiatric, urogenital, neurological, dermatological, cardiorespiratory, or musculoskeletal disease and/or sleep disorder that could be related to the study outcomes * Being pregnant or the possibility of pregnancy Criteria for withdrawal from the study: * Deciding not to participate in the study and not wishing to complete the assessments * Experiencing discomfort due to the assessments and measurements and not wishing to complete them