Ability of Machine Learning to Cluster Patients With Idiopathic Neck Pain and Evaluate More Efficient Rehabilitation Using Kinaesthetic Training

What this Trial Is About

Researchers are evaluating whether a new kinematic training approach based on machine learning classification can reduce chronic neck pain and prevent its recurrence more effectively than conventional kinematic training in adults. The study focuses on grouping patients by head and neck movement patterns to tailor rehabilitation, aiming to improve clinical outcomes and reduce pain levels and recurrence. This research addresses the high societal burden of recurrent neck pain and explores personalized rehabilitation methods versus standard exercise protocols. Participants will be assigned to groups based on their specific movement deficits identified through advanced assessment of cervical sensorimotor control. Each group receives cluster-specific kinematic training focused on head and neck movements performed in a sitting position, with varying velocities, amplitudes, and directions adjusted to reach training accuracy targets. Sessions are 20 minutes long, conducted four times per week for four weeks. A control group will receive general kinematic training without subgroup tailoring, with all training programs matched for frequency and duration. During the study, participants will undergo detailed assessments including movement control tests tracking precision, underreaching, overreaching, smoothness, and position sense, along with eye movement evaluations and range of motion measurements. Pain intensity and disability will be measured at study start, after the training period, and at a three-month follow-up to assess lasting effects. Researchers will monitor adherence, symptom changes, and neuromuscular adaptations to determine if individualized training improves outcomes and reduces neck pain recurrence over time.

Kinematic Training in Patients With Neck Pain Based on Machine Learning Classification Approach