Person-Centred AI Support in Interdisciplinary Rehabilitation for Chronic Pain

A person-centred composite score based on eight validated domains: pain intensity (NRS; 0-10), sleep problems (ISI; 0-28), physical health (SF-36 PF; 0-100), mental health (SF-36 MH; 0-100), depression and anxiety (HADS-A/D; 0-21), work ability (WAI single item; 0-10), and pain interference (single item; 0-10). At baseline, participants prioritize these domains together with the interdisciplinary treatment (IDT) team. The Clinical Decision Support System (CDSS) stores these weights. Each domain is normalized to 0-100 and combined into a weighted composite. Higher scores indicate better health-related well-being. Although composed of several scales, the outcome is reported as a single, aggregated primary measure.

Measured using the Numeric Rating Scale (NRS, 0-10), where 0 = no pain and 10 = worst imaginable pain. Participants report average pain over the last seven days. A reduction in score indicates clinical improvement.

The ISI assesses perceived sleep difficulties through seven items. Total scores range from 0 to 28, with higher values indicating more severe insomnia. A lower score reflects improved sleep quality.

Measured using the SF-36 Physical Functioning subscale (10 items). Scores range from 0 to 100, with higher scores representing better physical functioning.

Measured using the SF-36 Mental Health subscale (5 items). Scores range from 0 to 100; higher values indicate better mental well-being.

The HADS includes two 7-item subscales for anxiety and depression. Each subscale ranges from 0 to 21; higher scores indicate greater emotional distress.

Assessed via the single-item WAI: "Current work ability compared to lifetime best", scored from 0 (completely unable to work) to 10 (work ability at its best).

Measured using validated items adapted from the Multidimensional Pain Inventory or equivalent, reflecting the extent to which pain disrupts everyday activities. Scores are standardized from 0 (no interference) to 100 (maximum interference).

The EVS includes two questions: (1) days per week of moderate-to-strenuous activity, and (2) average minutes per day. The product gives total minutes/week. Validated against objective activity measures.

A single-item self-report question regarding the individual's expectation of treatment benefit, rated on a Likert scale from "no improvement expected" to "complete recovery expected".

Self-reported current sick leave status (full-time, part-time, or not on leave). Changes over time reflect return-to-work or ongoing sick leave status.

Captured through a validated web-based tool. Participants report medication name (text), dose (mg), frequency (time/day), and form (e.g. tablet). Variables are analyzed separately using descriptive statistics and longitudinal methods to assess changes in medication use over time.

Measured in Quality-Adjusted Life Years (QALYs) derived from the EuroQol 5-Dimension 5-Level (EQ-5D-5L) instrument using standard value sets. The Incremental Cost-Effectiveness Ratio (ICER) will be calculated as the ratio of the difference in costs to the difference in health outcomes (QALYs gained), comparing the intervention to the control. ICER provides a summary measure of the additional cost required to gain one additional unit of health benefit.

EQ-5D index scores typically range from below zero (e.g., -0.594 in the UK value set) to 1.000, or from 0.296 to 1.000 using the Swedish experience-based value set, where higher values indicate better health-related quality of life.

Measured using the RAND 36-Item Health Survey (RAND SF-36), which assesses physical and mental health across eight domains. Each domain score ranges from 0 to 100, with higher scores indicating better health status. A cost-utility analysis will also be performed using utility estimates derived from RAND SF-36, and an ICER will be calculated accordingly. ICER will be interpreted as the additional cost per unit of utility gained, based on mapped utility values. (Note: Mapping algorithms may be applied to derive utility weights from RAND SF-36, subject to validation.)

Data obtained from the Swedish Social Insurance Agency (MiDAS) detailing sickness absence (full- or part-time) in number of net days. Fewer days indicate clinical or occupational improvement. Scores range from 0 to an open upper limit, where 0 indicates no sickness absence and higher values indicate more days of absence.

Data will be extracted from the Swedish Prescribed Drug Register. Medication volume will be calculated using the Defined Daily Dose (DDD) methodology, as defined by the World Health Organization (WHO). For each prescribed medication, the total number of dispensed units will be converted into DDDs based on the standard daily maintenance dose for its main indication in adults. The total DDDs per individual will be summed across all medications to reflect overall pharmacological treatment intensity. Scores range from 0 to no predefined upper limit, where higher values indicate greater medication burden.

Comorbidity burden will be derived from the Swedish National Patient Register using established ICD-10 codes. A validated multimorbidity index (e.g., the Charlson Comorbidity Index or a count of chronic conditions) will be calculated for each individual at multiple time points. Higher scores reflect a greater burden of comorbid disease. Scores typically range from 0 (no comorbid conditions) to 15 or more, depending on the index used and the number/severity of conditions present.

Self-reported pain drawings will be analyzed to determine the number of distinct anatomical pain locations reported by each participant. This measure reflects the spatial complexity of pain presentation. Scores range from 0 (no reported pain) to approximately 36, based on a standardized body map divided into predefined regions. Higher scores indicate more widespread or complex pain distribution.

CPAQ-8 includes 8 items (score 0-6 per item), total score 0-48. Higher scores represent greater acceptance of pain.

TSK (13 items) total score range: 13-52. Higher scores indicate greater fear of movement. Decreases reflect improvement in pain-related fear.

Measured using the Pain Catastrophizing Scale (PCS). Scores range from 0 to 52; higher scores denote greater catastrophizing.

Assessed using the Pain Self-Efficacy Questionnaire (PSEQ), score range 0-60. Higher scores reflect greater confidence in functioning despite pain.