ICF-Based Biopsychosocial Assessment With AI-Assisted Profile Prediction: Trapeziometacarpal Osteoarthritis Model

Measured using a Jamar dynamometer. The participant performs the test in a seated position with the elbow flexed at 90 degrees. Unit of Measure: Kilograms

Measured using a pinchmeter to assess tip-to-tip and key pinch strength. Unit of Measure: Kilograms

Assessment of thumb opposition using the Kapandji score, which ranges from 0 to 10. Higher scores indicate better thumb opposition and mobility.

Measured using a Visual Analog Scale (VAS) ranging from 0 (no pain) to 10 (worst imaginable pain). Higher scores indicate greater pain intensity.

Total duration of thumb pain reported by the participant.

Evaluation of the trapeziometacarpal joint osteoarthritis stage based on the Eaton-Littler classification (Stages I through IV).

Radiographic measurement of the radial subluxation of the metacarpal base on the trapezium.

Measured using the Quick Disabilities of the Arm, Shoulder and Hand (QuickDASH) questionnaire. The score ranges from 0 to 100, where higher scores indicate greater disability and symptoms.

Assessment of thumb-related disability. Scores range from 0 to 100, with higher scores indicating greater functional impairment.

Assessment of generalized joint laxity using the Beighton score. The total score ranges from 0 to 9, where higher scores indicate greater hypermobility.

Active range of motion of the thumb joints measured using a goniometer. Unit of Measure: Degrees

Clinical assessment using metacarpal adduction and extension tests to provoke symptoms. Presence or absence of pain (Binary: Yes/No)

Qualitative assessment of the participant's family support and the presence of ergonomic adaptations in their daily environment.

Measured using the Hospital Anxiety and Depression Scale (HADS), which consists of two subscales: Anxiety (HADS-A) and Depression (HADS-D). Each subscale ranges from 0 to 21, where higher scores indicate greater levels of anxiety or depression (worse outcome).

Measured using the 17-item Tampa Scale of Kinesiophobia (TSK-17) to assess the fear of movement or re-injury. Total scores range from 17 to 68, where higher scores indicate greater kinesiophobia (worse outcome).

Measured using the Patterns of Activity Measure-Pain (POAM-P) questionnaire to classify participants into three patterns: avoidance, overdoing, and pacing. Each subscale score indicates the frequency of that specific activity pattern. Higher scores on each subscale indicate a more frequent use of that specific activity pattern.

Assessed using the Pain Beliefs Questionnaire (PBQ), which evaluates two dimensions: Organic and Psychological pain beliefs. Scores range from 1 to 6 for each subscale, where higher scores indicate a stronger belief in that specific dimension (e.g., higher organic scores mean a stronger belief that pain is due to physical damage).

Measured using the Pain Coping Questionnaire (PCQ) to assess the frequency of different coping strategies (e.g., information seeking, problem solving, distraction). Higher scores indicate a more frequent use of the respective coping strategy.

Performance comparison of four large language models (Claude, ChatGPT, Gemini, LLaMA) on 40 clinical questions. Evaluated by two independent blinded experts using a 4-point Likert scale (1: Completely Incorrect, 4: Completely Correct). Higher scores indicate better accuracy.

Assessment of content consistency between two repeated queries of the same questions. Evaluated based on the percentage of agreement between the two sets of responses.

Evaluation of how thoroughly the model covers the necessary clinical details. Measured on a 5-point scale (1: Very Poor, 5: Very Good). Higher scores indicate more comprehensive answers.

Assessment of the practical utility of the responses for clinical practice. Measured on a 5-point scale (1: Not Relevant, 5: Highly Relevant). Higher scores indicate greater clinical utility.

The readability of the generated responses will be calculated using the Flesch Reading Ease Score. Scores typically range from 0 to 100, where higher scores indicate that the text is easier to read.

Prediction accuracy of the best-performing LLM (identified in WP2) in estimating continuous clinical scores (e.g., Grip Strength, QuickDASH scores) from core clinical predictors. Accuracy will be measured using the Intraclass Correlation Coefficient (ICC) to evaluate the agreement between LLM-predicted values and actual clinical assessment results.

Prediction accuracy of the best-performing LLM in estimating categorical patient profiles (e.g., Eaton-Littler Stage, POAM-P activity patterns). Accuracy will be measured using Cohen's Kappa coefficient to evaluate the agreement between LLM-predicted categories and actual expert-diagnosed categories.

This measure evaluates the correlation between the subscale scores of the Patterns of Activity Measure-Pain (POAM-P) questionnaire (Avoidance, Overdoing, and Pacing) and clinical parameters, including pain intensity (VAS), grip strength (kg), upper extremity disability (QuickDASH), and emotional status (HADS). Correlation will be analyzed using Spearman's or Pearson's correlation coefficients depending on the data distribution. Unit of Measure: Correlation Coefficient

Level of fear of movement or re-injury will be assessed using the unabbreviated 17-item Tampa Scale of Kinesiophobia (TSK-17). Total scores range from a minimum of 17 to a maximum of 68. Higher scores indicate a greater level of kinesiophobia (worse outcome).

This measure assesses the patients' beliefs about the cause of their pain using the unabbreviated Pain Beliefs Questionnaire (PBQ). The PBQ consists of two subscales: Organic Beliefs and Psychological Beliefs. Each subscale score is evaluated, and their correlation with coping strategies and emotional status is analyzed. For each subscale, scores range from 1 to 6 (calculated as an average of items), where higher scores indicate a stronger belief in that specific dimension (e.g., higher organic scores mean a stronger belief that pain has a physical cause).

Emotional status will be assessed using the Hospital Anxiety and Depression Scale (HADS). The scale consists of two subscales: HADS-Anxiety (HADS-A) and HADS-Depression (HADS-D). Each subscale ranges from 0 to 21, where higher scores indicate greater levels of anxiety or depression (worse outcome).

Evaluation of the various methods used by participants to manage their pain using the unabbreviated Pain Coping Questionnaire (PCQ). The questionnaire assesses different subscales such as Information Seeking, Problem Solving, and Distraction. Each subscale is scored, and higher scores indicate a more frequent use of that specific coping strategy (higher scores generally represent better or more active coping, depending on the specific subscale).