A Feasibility Study of AI-Assisted Physiotherapy for Oromandibular and Neck-Shoulder Mobility in Oral Cancer Patients

This is a single-group, prospective, non-randomized pilot feasibility study. Oral cancer patients with trismus or neck-shoulder impairment will be trained to exercise their jaw or neck-shoulder muscles using an AI-assisted physiotherapy assessment system, which is reliable and valid. The study aims to recruit approximately 15 patients who meet the inclusion and exclusion criteria. This sample size is sufficient for the primary goal of assessing study procedures, recruitment rates, and study adherence of this supportive care intervention, rather than determining definitive treatment efficacy.

Participants will undergo a comprehensive clinical evaluation at baseline and post-intervention. The 4-to-6-week intervention features a daily automated assessment using a previously validated AI-assisted physiotherapy assessment system. Based on these assessments, an established system clinical workflow then dynamically generates a personalized exercise curriculum for that day. Participants will perform these exercise programs 3 to 4 times daily.

Key feasibility metrics, including recruitment rate, retention rate, intervention adherence, and system acceptability (SUS score), will be summarized using descriptive statistics. Adherence will be monitored automatically via server log data. Following the Intention-to-Treat (ITT) principle, technical dropouts who transition to face-to-face therapy will be documented as a feasibility outcome to identify technical barriers.

Preliminary efficacy will be evaluated by analyzing functional changes from baseline to endpoint, including Maximal Interincisal Opening (MIO), cervical and shoulder ROM, upper extremity function questionnaires, and quality-of-life questionnaires. Depending on data distribution, changes will be analyzed using the Paired t-test or the Wilcoxon Signed-Rank Test. Effect size estimates (Cohen's d) and their 95% confidence intervals will be calculated.

This study is expected to provide essential feasibility and safety evidence of an AI-assisted home-based exercise protocol, establishing a foundation and providing sample size calculations for a subsequent randomized controlled trial.