Machine-learning guided kinematic training for chronic neck pain
What is the Ability of Datamining Approaches to Cluster Patients With Idiopathic Neck Pain and Can Machine Learning Algorithms Provide More Efficient Rehabilitation and Less Recurrence Based on Kinaesthetic Training Protocols
This trial will see if grouping people by head and neck movement patterns with machine learning and giving tailored movement exercises reduces pain and prevents recurrence in adults with chronic neck pain.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 38 (estimated) |
| Ages | 18 Years to 65 Years |
| Sex | All |
| Sponsor | University of Ljubljana Academic / other |
| Locations | 1 site (Ljubljana) |
| Trial ID | NCT07418632 on ClinicalTrials.gov |
What this trial studies
Adults with chronic idiopathic neck pain will undergo detailed kinematic assessment of head and neck movements and be assigned to treatment groups based on clustered movement characteristics. Machine-learning clustering will guide assignment to one of several tailored kinematic training protocols (ranging from smaller to larger movement-deficit approaches) or to a control protocol. Interventions are delivered in-person with regular training sessions and follow-up, and outcomes include pain intensity (VAS), recurrence rates, and functional measures. The main comparison is whether cluster-specific, personalized kinematic training produces better short- and longer-term clinical outcomes than conventional kinematic training.
Who should consider this trial
Good fit: Ideal candidates are adults with chronic neck pain who rate their pain at least 3/10 on the VAS and have not received conventional physiotherapy in the past six months.
Not a fit: Patients with recent upper-extremity pain, diagnosed neurological or vestibular disorders, type 2 diabetes, psychiatric disorders, or recent medication or alcohol use are excluded and may not receive benefit from this protocol.
Why it matters
Potential benefit: If successful, this approach could reduce pain and future flare-ups by personalizing kinematic rehabilitation, improving long-term function and reducing healthcare use.
How similar studies have performed: Some prior subgroup-based and exercise programs have shown modest benefits for tailored rehabilitation, but applying machine-learning classification of kinematic patterns to guide training is novel and not yet widely validated.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * presence of neck pain * pain level minimum 3 of 10 on VAS * did not receive conventional physiotherapy in last 6 months Exclusion Criteria: * any upper extremity pain within last 2 years * any neurological or vestibular dissorders * type 2 diabetes * diagnosed psychiatric dissorders * medication or alcohol consumptin in last 30 hours
Where this trial is running
Ljubljana
- Faculty of Sport — Ljubljana, Slovenia (Recruiting)
Study contacts
- Study coordinator: Ziva Majcen rosker, PhD, PT
- Email: ziva.majcen-rosker@fsp.uni-lj.si
- Phone: 00386 51267383
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.