Recruiting soon

LLM-Facilitated Cognitive Debiasing in Musculoskeletal Care

0 criteria met from your profileSee at a glance how your profile meets each eligibility criteria.
What is being tested

LLM-facilitated cognitive debiasing aid

Behavioral
Who is being recruted

Any Chronic, Non-traumatic Orthopedic Condition

Over 18 Years
+6 Eligibility Criteria

See all eligibility criteria

How is the trial designed

Supportive Care Study

Interventional
Study Start: June 2025

See protocol details

Summary

Principal SponsorUniversity of Texas at Austin
Study ContactEmily H Jaarsma, MD
Last updated: June 26, 2025
Sourced from a government-validated database.Claim as a partner
Study start date: June 23, 2025Actual date on which the first participant was enrolled.

This study focuses on improving how patients interpret and manage musculoskeletal pain or dysfunction. Often, people quickly form beliefs about their symptoms that may not align with the actual medical condition, leading to unnecessary stress and medical procedures. The trial aims to test whether using a Large Language Model (LLM)-facilitated cognitive debiasing strategy can help patients understand their symptoms better compared to just receiving LLM-generated diagnostic feedback. This approach could lead to more accurate symptom evaluation and improve the overall healthcare experience by addressing the common challenge of misinterpretation in musculoskeletal care. Participants in this study will engage with an LLM, such as ChatGPT, which processes their symptom descriptions and beliefs to create clear summaries that help them identify and reconsider their thought patterns. The LLM can also assist healthcare providers by highlighting any potentially unhelpful beliefs before consultations, promoting better communication. The study compares this structured debiasing intervention with standard LLM-generated diagnostic feedback to see which method more effectively supports accurate symptom understanding and improves patient care. There are no specified risks or benefits outlined for participants, but the study aims to enhance the quality of decision-making and patient experiences.

Official TitleComparison of a Large Language Model (LLM)-Facilitated Cognitive Debiasing Strategy Versus LLM-Generated Diagnostic Feedback Alone in Musculoskeletal Specialty Care: A Randomized Controlled Trial 
Principal SponsorUniversity of Texas at Austin
Study ContactEmily H Jaarsma, MD
Last updated: June 26, 2025
Sourced from a government-validated database.Claim as a partner

Protocol

This section provides details of the study plan, including how the study is designed and what the study is measuring.
Design Details
150 patients to be enrolledTotal number of participants that the clinical trial aims to recruit.
Supportive Care Study
These studies explore ways to improve comfort and daily life for people living with a condition. They may focus on easing symptoms, reducing treatment side effects, or supporting overall well-being.

How participants are assigned to different groups/arms
In this clinical study, participants are placed into groups randomly, like flipping a coin. This ensures that the study is fair and unbiased, making the results more reliable. By assigning participants by chance, researchers can better compare treatments without external influences.

Other Ways to Assign Participants
Non-randomized allocation: Participants are assigned based on specific factors, such as their medical condition or a doctor's decision.
None (Single-arm trial): If the study has only one group, all participants receive the same treatment, and no allocation is needed.

How treatments are given to participants
Participants are divided into different groups, each receiving a specific treatment at the same time. This helps researchers compare how well different treatments work against each other.

Other Ways to Assign Treatments
Single-group assignment: Everyone gets the same treatment.
Cross-over assignment: Participants switch between treatments during the study.
Factorial assignment: Participants receive different combinations of treatments.
Sequential assignment: Participants receive treatments one after another in a specific order, possibly based on individual responses.
Other assignment: Treatment assignment does not follow a standard or predefined design.

How the effectiveness of the treatment is controlled
In a non placebo-controlled study, no participants receive an inert substance (placebo) to compare outcomes. Instead, all participants receive either the experimental treatment or an alternative treatment (often the Standard of Care). This method allows researchers to compare the effects of the experimental treatment with those of a different active intervention, rather than a placebo.

Other Options
Placebo-Controlled: A placebo is used to compare the effects of the experimental treatment with those of an inert substance, isolating the true treatment effect.

How the interventions assigned to participants is kept confidential
Everyone involved in the study knows which treatment is being given. This is typically used when it's not possible or necessary to hide the treatment details from participants or researchers.

Other Ways to Mask Information
Single-blind: Participants do not know which treatment they are receiving, but researchers do.
Double-blind: Neither participants nor researchers know which treatment is given.
Triple-blind: Participants, researchers, and outcome assessors do not know which treatment is given.
Quadruple-blind: Participants, researchers, outcome assessors, and care providers all do not know which treatment is given.

Eligibility

Researchers look for people who fit a certain description, called eligibility criteria: person's general health condition or prior treatments.
Conditions
Criteria
Any sexBiological sex of participants that are eligible to enroll.
Over 18 YearsRange of ages for which participants are eligible to join.
Healthy volunteers not allowedIf individuals who are healthy and do not have the condition being studied can participate.
Conditions
Pathology
Any Chronic, Non-traumatic Orthopedic Condition
Criteria
5 inclusion criteria required to participate
Adults (18+)
New or return patient seeking musculoskeletal specialty care at an Orthopedic outpatient clinic
Total combined score on the 6 feelings and thoughts items of > 10\* (Appendix 3 of study protocol)
English-speaking

Show More Criteria

1 exclusion criteria prevent from participating
Any impairment preventing completion of surveys on a tablet

Study Plan

Find out more about all the medication administered in this study, their detailed description and what they involve.
Treatment Groups
Study Objectives
2 intervention groups 

are designated in this study

This study does not include a placebo group 

Treatment Groups
Group I
Experimental
The intervention is a four-part, tablet-based cognitive debiasing aid that uses a Large Language Model (LLM) to help patients reflect on and re-evaluate their beliefs about their symptoms prior to a musculoskeletal specialty care visit. Patient responses are summarized by the LLM in supportive language to promote flexible thinking, and a separate LLM-generated summary of potential unhelpful beliefs is shared with the clinician to guide empathic, individualized communication.
Group II
No Intervention
In the control arm, patients use a tablet-based tool to describe their presenting musculoskeletal symptom, which is transcribed and input into a Large Language Model (LLM). The LLM generates a likely diagnosis with a brief neutral description, which is shared with both the patient and the clinician before the consultation. This approach offers diagnostic feedback without engaging in cognitive debiasing or reflection.
Study Objectives
Primary Objectives

The Trust and Experience with the Clinician Scale (TRECS-7) is a validated 7-item scale that measures patients' trust in and experience with their clinician during a medical consultation. Designed to minimize ceiling effects, it enables more sensitive detection of variation in patient experience across different clinical interactions (Brinkman et al.). Each of 7 statements is scored from 0-4 (strongly disagree, disagree, neutral, agree, strongly agree), resulting in a total score between 0 and 28. Higher scores indicate greater perceived trust in the clinician. Source: Brinkman N, Looman R, Jayakumar P, Ring D, Choi S. Is It Possible to Develop a Patient-reported Experience Measure With Lower Ceiling Effect? Clin Orthop Relat Res. 2025 Apr 1;483(4):693-703.
Secondary Objectives

Subjective experience will be assessed using three custom items rated on a 0-100 scale, capturing participants' perceptions of the AI interaction. These items evaluate whether the computer provided an accurate summary, promoted a healthy mindset, and increased confidence in self-management, respectively. Higher scores will indicate more positive experience while lower scores will indicate more negative experience ratings.

Study Centers

These are the hospitals, clinics, or research facilities where the trial is being conducted. You can find the location closest to you and its status.
This study has 1 location
Suspended
Dell Medical School, University of Texas at AustinAustin, United StatesSee the location
Recruiting soonOne Study Center