This study aims to evaluate the effects of rehabilitation programs supported by artificial intelligence-based large language models (LLMs), specifically ChatGPT and DeepSeek, in individuals with subacromial pain syndrome (SAPS). Participants will be randomly assigned to one of three groups: standard physiotherapy, standard physiotherapy plus ChatGPT-guided exercises, and standard physiotherapy plus DeepSeek-guided exercises. Outcomes including pain, disability, quality of life, muscle strength, and joint range of motion will be assessed before and after a 6-week intervention. The results will help determine whether AI-generated exercise recommendations can enhance clinical outcomes when combined with conventional physiotherapy.

This completed randomized controlled trial investigated the clinical effects of integrating AI-generated exercise recommendations into conventional physiotherapy for individuals with subacromial pain syndrome (SAPS). A total of 82 individuals were assessed for eligibility; 7 were excluded for not meeting inclusion criteria. Seventy-five participants provided consent and were randomized in a 1:1:1 ratio to 3 groups (n=25 each): (1) conventional physiotherapy plus a conventional exercise program, (2) conventional physiotherapy plus ChatGPT-guided exercises, and (3) conventional physiotherapy plus DeepSeek-guided exercises. The allocation sequence was generated using simple computer-based randomization by an independent staff member and was revealed after completion of baseline assessments. Interventions were delivered over 6 weeks (3 supervised sessions/week). Six participants discontinued the intervention due to scheduling conflicts (2 per group). Sixty-nine participants completed the 6-week intervention and were included in the final analysis (n=23 per group). The primary outcome was shoulder pain and disability (Shoulder Pain and Disability Index, SPADI), assessed at baseline and 6 weeks. Secondary outcomes included pain intensity (Numeric Pain Rating Scale, NPRS), health-related quality of life (Short Form-12, SF-12), upper limb function (Disabilities of the Arm, Shoulder and Hand, Quick DASH), range of motion, isometric strength, kinesiophobia, catastrophizing, emotional status, and disease-specific quality of life.

Inclusion Criteria:

• Being between the ages of 18 and 65
• Having been diagnosed with Subacromial Pain Syndrome (SAPS) for at least four weeks, diagnosed through clinical and physical examination
• Actively maintaining shoulder range of motion
• Being cognitively and physically capable of participating in an exercise program
• Agreeing to participate voluntarily in the research process and providing written consent

Exclusion Criteria:

• Presence of other shoulder pathologies such as rotator cuff tear, frozen shoulder, glenohumeral instability, or labrum tear
• Presence of conditions included in the differential diagnosis such as cervical radiculopathy, neurological disorders, rheumatological diseases, or fibromyalgia
• History of shoulder surgery within the last 6 months
• Pregnancy
• History of systemic or neuromuscular disease
• Refusal to consent to voluntary participation

Individual participant data (IPD) will not be shared due to ethical restrictions and institutional policy. The study was not designed with external data sharing in scope.

Participants were informed that they would receive one of several supervised exercise-based rehabilitation programmes for subacromial pain syndrome, but were not informed of their specific group assignment or the use of large language models. The physician establishing the diagnosis and the physiotherapist performing all outcome assessments are blinded to group allocation. Treating physiotherapists are aware of group assignment but are not involved in outcome assessments or data analysis.