PainTrain-AI Pilot: Feasibility, Usability (SUS) and Concept-Shift in Primary Care and a Specialized Setting (PT-AI Pilot)

Feasibility and Usability of a Digital Clinical Simulation (PainTrain AI) for Chronic Pain Training in Health Professionals: A Multicenter Pilot in Primary Care (ICS) and a Specialized Comparative Setting

This pilot will assess feasibility and usability (SUS) and explore concept shift (reduction of neurophysiology misconceptions) after exposure to a behavioral educational intervention (PainTrain AI), a digital clinical simulation "fenced" by evidence (RAG) for safe, non diagnostic training. The study will be conducted in Primary Care and in a specialized comparative setting, without patient data collection. Primary endpoint: SUS score. Secondary endpoints: concept shift, adherence to micromodules, and interaction latency as friction metric. The platform does not generate clinical advice; it retrieves validated teaching content.

Study Overview

• Status: Not yet recruiting
• Conditions: Chronic Musculoskeletal Pain
• Intervention / Treatment: Behavioral: PainTrain-AI Behavioral Training

Detailed Description

This feasibility pilot will evaluate the use of PainTrain AI, a behavioral educational intervention designed to improve clinical reasoning about chronic pain through simulated dialogues with virtual standardized patients. The platform uses a Retrieval Augmented Generation (RAG) safety architecture that restricts all generated responses to validated pedagogical content and does not provide clinical advice. No patient information is collected.

The study includes health professionals from Primary Care and a specialized comparative setting. Participants will complete a baseline assessment and then interact with the PainTrain AI simulation for a defined training period. Usability will be assessed using the System Usability Scale (SUS). Concept shift will be measured as the reduction in predefined neurophysiology misconceptions scored through a standardized rubric. Additional metrics include adherence to micromodules and interaction latency as indicators of technological friction.

This pilot aims to determine feasibility, acceptability, and preliminary signals of educational effectiveness to inform a future implementation trial in Primary Care. The intervention is educational only, non diagnostic, and GDPR compliant.

• Study Type: Interventional
• Enrollment (Estimated): 40
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Fran Valenzuela-Pascual, Dr; Phone Number: +34 973 702 459; Email: fran.valenzuela@udl.cat

Study Locations

• Spain
  • Lleida
    • Lleida, Lleida, Spain, 25198
      • Universitat de Lleida
      • Contact: Fran Valenzuela-Pascual, Dr.; Phone Number: +34 973 702 459; Email: fran.valenzuela@udl.cat
      • Contact: Fran; Email: fran.valenzuela@udl.cat

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Health professionals in Primary Care (medicine, physiotherapy, nursing, psychology, nutrition) and specialized setting; willingness to use the platform; institutional approval.

Exclusion Criteria:

• lack of institutional access; unavailability during pilot window

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Experimental: PainTrain-AI Behavioral Training; Participants in this arm will receive the behavioral educational intervention PainTrain-AI, a digital clinical simulation that uses a retrieval-augmented generation (RAG) safety architecture to deliver evidence-based teaching content. The platform provides simulated dialogues with virtual standardized patients to train biopsychosocial reasoning about chronic pain. All participants receive the same intervention; there is no control group.

Behavioral: PainTrain-AI Behavioral Training; PainTrain-AI is a behavioral educational intervention delivered through a digital clinical simulation platform. The system uses a retrieval-augmented generation (RAG) safety architecture to ensure that all responses are generated only from validated pedagogical content. Participants engage in simulated dialogues with virtual standardized patients to practice biopsychosocial reasoning about chronic pain. The intervention is non-diagnostic, does not provide clinical advice, and does not involve patient data. All participants receive the same intervention.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Usability (SUS, 0-100)	Usability will be assessed using the System Usability Scale (SUS), a validated 10-item questionnaire that yields a score from 0 to 100. Higher scores indicate better usability. Participants will complete the SUS after interacting with the PainTrain-AI educational simulation for the predefined training period. The primary feasibility criterion is achieving a mean SUS score ≥75, indicating good usability.	4-8 weeks after onboarding

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Concept Shift	Concept-shift will be assessed as the change in the proportion of predefined misconceptions about pain neurophysiology identified in a standardized scoring rubric. Participants will complete a brief conceptual test before and after exposure to the PainTrain-AI educational simulation. Concept-shift is calculated as the reduction in incorrect or outdated statements related to chronic pain mechanisms. Higher improvement reflects better conceptual understanding. No patient data are involved.	4-8 weeks.
Adherence	Adherence will be measured as the proportion of scheduled training modules or simulation sessions that each participant completes within the study period. Adherence is calculated as the percentage of completed sessions relative to the total number of modules assigned. Higher values indicate greater engagement with the PainTrain-AI educational intervention. No patient data are involved.	4-8 weeks
Latency/friction	Latency will be measured as the average system response time (in seconds) during user interactions with the PainTrain-AI digital simulation. Latency is calculated automatically from platform logs as the time elapsed between a user input and the system's generated response. Higher latency indicates greater technological friction. This outcome evaluates technical feasibility and user experience. No patient data are involved.	4-8 weeks

Collaborators and Investigators

• Sponsor: Francesc Valenzuela Pascual
• Investigators: Principal Investigator: Fran Valenzuela-Pascual, Dr., Institut de Recerca Biomèdica de Lleida (IRBLleida) / Universitat de Lleida (UdL)

Study record dates

Study Major Dates

• Study Start (Estimated): January 1, 2027
• Primary Completion (Estimated): January 1, 2028
• Study Completion (Estimated): September 1, 2028

Study Registration Dates

• First Submitted: March 23, 2026
• First Submitted That Met QC Criteria: March 23, 2026
• First Posted (Actual): March 27, 2026

Study Record Updates

• Last Update Posted (Actual): April 2, 2026
• Last Update Submitted That Met QC Criteria: March 28, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: chronic musculoskeletal pain; educational intervention; digital training; clinical simulation; usability (SUS); concept shift; primary care professionals
• Other Study ID Numbers: PT-AI-PILOT-2026

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: No IPD will be shared because the study does not involve patient data or clinical individual-level information. Only anonymized usage datasets and aggregated concept-shift scores may be shared according to a FAIR plan (anonymized logs + codebooks), deposited in public repositories after embargo per grant policy.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No