Clinical validatiOn of an AI-based DEcision Support System for Robotic Upper Limb Rehabilitation in Patients With Stroke. A CO-AIDER Study.

Evaluation of usability and acceptability for therapists will be conducted through ad hoc questionnaires and the System Usability Scale (SUS). The SUS is a standardized tool developed to assess the perceived usability of systems, devices, or services. It consists of 10 items rated on a 5-point Likert scale, covering aspects such as ease of use, complexity, and learnability. The SUS provides a global usability score ranging from 0 to 100, where higher scores indicate better usability.

The Fugl-Meyer Assessment (FMA) is a stroke-specific, performance-based impairment index. It is designed to assess motor functioning, balance, sensation and joint functioning in patients with post-stroke hemiplegia. The upper extremity motor function domain includes items assessing movement, coordination, and reflex action of the shoulder, elbow, forearm, wrist, and hand. It ranges from 0 (hemiplegia) to 66 (normal motor performance).

The National Institutes of Health Stroke Scale (NIHSS) is a validated tool for assessing stroke severity. The score ranges from 0 to 42, with higher scores indicating more severe neurological deficit.

The Motricity Index (MI) is an ordinal method of measuring limb strength. For the upper extremity, shoulder abduction, elbow flexion, and pinch grip are considered; for the lower extremity, hip flexion, knee extension, and ankle dorsiflexion are considered. It ranges from 0 (worse) to 100 (normal strength).

The Modified Ashworth Scale (MAS) is a revised version of the original Ashworth Scale that measures spasticity in patients with lesions to the central nervous system. MAS is an assessment that is used to measure the increase in muscle tone. MAS assigns a grade of spasticity from a 0 to 4 ordinal scale. The grade is assigned by moving a joint/muscle through a high velocity quick stretch. The lower the score, the lower the spasticity. Upper and lower joints spasticity is assessed.

The Douleur Neuropathique 4 (DN4) questionnaire is a validated clinician-administered screening tool for neuropathic pain. It ranges from 0 to 10; higher values means higher neuropathic pain probability.

The Numerical Rating Scale for Pain(NRS) is a tool used to assess pain intensity. It is a subjective measure in which individuals rate their pain on an eleven-point numerical scale, from 0 (no pain) to 10 (worst pain imaginable).

The modified Barthel Index for Activities of Daily Living is a validated ordinal scale which measures a person's ability to complete activities of daily living (ADL). Scores range from 0 (total dependence) to 100 (total independence).

The Frenchay Arm Test (FAT) assesses motor skills during activities of daily living (ADL) in patients with upper extremity impairments due to neurological conditions, using five practical tasks. Each task is scored 0 (unable) or 1 (able), for a total score of 0-5. Higher scores indicate better arm and hand function.

The Action Research Arm Test (ARAT) is a 19 item observational measure used to assess upper extremity performance (coordination, dexterity and functioning). The 19 items comprising the ARAT are scored using a 4 point ordinal scale. Scores on the ARAT may range from 0-57 points, with a maximum score of 57 points indicating better performance.

The Short-Form Health Survey (SF-36) is a questionnaire that assesses a person's health status. It includes 36 items across eight domains: physical functioning, role limitations due to physical health, bodily pain, general health, vitality, social functioning, role limitations due to emotional health, and mental health. Each domain is scored from 0 to 100, with higher scores indicating better health or functioning.

The Montreal Cognitive Assessment (MoCA) is a widely used screening assessment for detecting cognitive impairment. It ranges from 0 (worst) to 30 (best).

The Symbol Digit Modalities Test evaluates information processing speed. It consists of a simple task of replacing symbols with numbers. Using a reference key, the patient has 90 seconds to match a sequence of symbols with the correspondent numbers as rapidly as possible. Both written or oral administration can be used. For each correct answer, a point is assigned. The higher the score, the faster the information processing speed.

A cost-effectiveness analysis of the CO-AIDER software will be carried out in terms of the added value of the solution, defined as the ratio between Delta_Outcome (i.e., the difference in clinical outcomes obtained with and without the support of the CO-AIDER software) and Delta_Cost (i.e., the difference in treatment costs with and without the support of the CO-AIDER software).

Assessment of therapist satisfaction and technology acceptance using the Technology Acceptance Model (TAM). The TAM is a questionnaire used with the primary aim of identifying the determinants involved in the acceptance of Robotic and Allied Technology. The questionnaire consists of 4 sections (perceived usefulness, ease of use, compatibility, intention to use); each question includes a 7-point Likert scale, from 1 (worst) to 7 (best). The scoring is calculated for each section and is given by the average of the responses in that section, ranging from 1 (worst) to 7 (best).

Assessment of patient satisfaction and technology acceptance using the Technology Acceptance Model (TAM). The TAM is a questionnaire used with the primary aim of identifying the determinants involved in the acceptance of Robotic and Allied Technology. The questionnaire consists of 4 sections (perceived usefulness, ease of use, compatibility, intention to use); each question includes a 7-point Likert scale, from 1 (worst) to 7 (best). The scoring is calculated for each section and is given by the average of the responses in that section, ranging from 1 (worst) to 7 (best).