Any Chronic, Non-traumatic Orthopedic ConditionNCT07022769
Testing an AI Large Language Model Tool for Cognitive Debiasing in Musculoskeletal Care
A study testing LLM-facilitated cognitive debiasing aid in people with Any Chronic, Non-traumatic Orthopedic Condition, run by University of Texas at Austin at 1 site in United States.
Trial summary
The goal of this clinical trial is to find out whether using an artificial intelligence (AI) tool called a Large Language Model (LLM) can help patients think more clearly about their symptoms and improve their trust and experience during a visit to a musculoskeletal specialist. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Any Chronic, Non-traumatic Orthopedic Condition
- What is being tested?
- LLM-facilitated cognitive debiasing aid
- Type of treatment
- Pill or oral medicine, Lifestyle or therapy programme
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 150 participants
- Where
- 1 siteUnited States
- Study dates
- 23 Jun 2025to 31 Jul 2026
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- 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
- Pre-visit diagnosis of chronic, non-traumatic musculoskeletal condition (including, but not limited to: osteoarthritis, carpal tunnel syndrome, trigger digit, Dupuytren's, De Quervain's, lateral epicondylitis)
Who cannot join
- Any impairment preventing completion of surveys on a tablet
Trial locations and contacts
1 site in 1 country.
United States1 site
Dell Medical School, University of Texas at Austin
Austin, Texas, 78712
About this study
Official title: Comparison of a Large Language Model (LLM)-Facilitated Cognitive Debiasing Strategy Versus LLM-Generated Diagnostic Feedback Alone in Musculoskeletal Specialty Care: A Randomized Controlled Trial
The goal of this clinical trial is to find out whether using an artificial intelligence (AI) tool called a Large Language Model (LLM) can help patients think more clearly about their symptoms and improve their trust and experience during a visit to a musculoskeletal specialist.
The study will answer two main questions:
Read more
- Does an LLM-guided checklist that encourages patients to reflect on their beliefs about their symptoms improve their trust in the clinician (measured using the TRECS-7 scale)?
- Does the checklist improve how patients feel about their consultation overall?
Participants will be randomly assigned to one of two groups:
- One group will receive an LLM-guided checklist that helps them think more flexibly about their condition.
- The other group will receive an LLM-generated likely diagnosis and brief explanation of their symptoms.
In both groups, the information from the AI tool will be shared with both the patient and the clinician before the consultation.
Patients in the debiasing (intervention) group will:
- Complete a short set of questions with help from a researcher
- Receive a simple summary from the AI that reflects their beliefs and gently challenges any unhelpful thinking
- Attend their regular specialist appointment
- Complete a short survey afterwards capturing their thoughts, experience and basic demographics
Patients in the diagnosis-only (control) group will:
- Describe their symptoms to the AI LLM
- Receive a likely diagnosis and short explanation based on this description
- Attend their regular specialist appointment
- Complete a short survey afterwards capturing their thoughts, experience and basic demographics
Read the detailed description
A patient's experience of physical discomfort and incapability is closely tied to how they interpret bodily sensations. The human mind is a meaning-making system that rapidly forms stories and assumptions about internal experiences. When individuals experience musculoskeletal pain or dysfunction, their initial interpretations often fall into broad cognitive categories: (1) harm that requires rest and protection; (2) threat to valued roles and activities; or (3) the belief that symptom elimination is the sole path to recovery. These automatic, unconscious interpretations can be adaptive in acute or dangerous situations, but they may also lead to biased or inaccurate symptom appraisals. When misaligned with the underlying pathology, such heuristics can exacerbate emotional distress, delay accurate diagnosis, and drive unnecessary investigations or treatments. The challenge, therefore, lies in supporting patients to reframe these beliefs and engage with their symptoms more adaptively.
Cognitive debiasing strategies have emerged as a promising approach to address this concern. These strategies aim to slow down automatic thinking, challenge entrenched assumptions, and promote more flexible, reflective, and value-aligned reasoning. By encouraging a more nuanced understanding of bodily signals, cognitive debiasing may improve the quality of clinical decisions and overall patient experience-offering advantages over traditional educational or informational tools.
Recent advances in Artificial Intelligence (AI), particularly the rise of Large Language Models (LLMs), have opened new possibilities for enhancing cognitive debiasing interventions. LLMs such as ChatGPT can analyze and synthesize patient-reported symptoms and beliefs to generate supportive, plain-language summaries of their thinking. This process may help patients recognize their own interpretive patterns and consider alternative, less distressing explanations for their symptoms. In parallel, LLMs can assist clinicians by flagging potentially unhelpful or distorted beliefs prior to a consultation, allowing for more tailored and empathic communication.
This trial tests whether a structured, LLM-facilitated debiasing intervention can better support accurate symptom appraisal and enhance the clinical encounter, compared to LLM-generated diagnosis alone. This work builds on the recognition that there is wide variation in musculoskeletal care experience and decision-making, with existing tools such as decision aids and question prompt lists often falling short in challenging rigid or unhelpful thinking patterns.
- Being tested
- LLM-facilitated cognitive debiasing aid
- Keywords
- Musculoskeletal disorders, Orthopaedic care, Non-traumatic pain, Shared Decision-Making, Health Communication, Behavioural Intervention, Randomized Controlled Trial, Patient Experience, Cognitive Bias, Illness Perceptions, Artificial intelligence, Large Language Models, Patient-physician relationship
- Medical subject headings
- Musculoskeletal Diseases
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
LLM-facilitated cognitive debiasing aidBehavioural
As part of the intervention, patients first respond to a series of questions about their beliefs regarding their symptoms (e.g., "What's usually behind these symptoms?"), with responses transcribed verbatim via tablet. These responses are input into a Large Language Model (LLM), which generates a brief, supportive summary of the patient's beliefs, shared back with the patient to encourage self-awareness and reflection. Patients are then invited to consider prompts such as, "What emotions or circumstances might be influencing your thinking?" with their reflections again transcribed. The LLM analyzes these reflections to identify potential signs of emotional distress or maladaptive beliefs, and this output is again provided to the patient. The LLM summary of identified maladaptive beliefs is then also shown to the clinician ahead of the consultation to support more tailored, empathetic communication.
| Study group | Role | What they receive |
|---|---|---|
| LLM-Facilitated Cognitive Debiasing Aid | 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. Receives: Behavioral: LLM-facilitated cognitive debiasing aid |
| Usual Care | 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. |
What is being measured
The primary outcome is the main question the study is designed to answer.
Trust and Experience with the Clinician Scale (TRECS-7)
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.
Measured: Measured once, immediately following consultation with the musculoskeletal specialist
Secondary outcomes (1)
Subjective Experience Using the LLM
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.
Measured: Measured once, immediately following consultation with the musculoskeletal specialist
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted15 Jun 2025
- Study start23 Jun 2025
- Primary completion15 Mar 2026
- Study completion31 Jul 2026 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Any Chronic, Non-traumatic Orthopedic ConditionStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Supportive care
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- Treatment arm will be determined at time of presentation by a validated random number generator (random.org). Patients will be randomized to receive either an LLM-facilitated structured debiasing checklist (1) or LLM-facilitated diagnostic feedback (0) prior to consultation with the clinician.
- Masking
- None (open label)
- Enrolment
- 150 participants (estimated)
Sponsor and investigators
- Lead sponsor
- University of Texas at Austin
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, David Ring, University of Texas at Austin
- Investigators
- David Ring, MD, PhD, Study director, Dell Medical School, University of Texas at Austin, TX, United States
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07022769
- Sponsor's protocol ID
- STUDY00004831
- Status last verified
- Jun 2026
- First submitted
- 7 Jun 2025
- Last updated
- 9 Jun 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Study at a glance
From the registry record, last updated by the sponsor on 9 Jun 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Comparison of a Large Language Model (LLM)-Facilitated Cognitive Debiasing Strategy Versus LLM-Generated Diagnostic Feedback Alone in Musculoskeletal Specialty Care: A Randomized Controlled Trial
- ClinicalTrials.gov ID
- NCT07022769
- Acronym / sponsor ID
- STUDY00004831
- Keywords
- Musculoskeletal disorders, Orthopaedic care, Non-traumatic pain, Shared Decision-Making, Health Communication, Behavioural Intervention, Randomized Controlled Trial, Patient Experience
- Study type
- Interventional
- Recruitment status
- Active, not recruiting
- Enrolment
- 150 participants (estimated)
- Lead sponsor
- University of Texas at AustinUniversity, hospital or other
- Study start
- 23 Jun 2025 (actual)
- Primary completion
- 15 Mar 2026 (actual)
- Study completion
- 31 Jul 2026 (estimated)
- First posted
- 15 Jun 2025 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
The goal of this clinical trial is to find out whether using an artificial intelligence (AI) tool called a Large Language Model (LLM) can help patients think more clearly about their symptoms and improve their trust and experience during a visit to a musculoskeletal specialist.
The study will answer two main questions:
- Does an LLM-guided checklist that encourages patients to reflect on their beliefs about their symptoms improve their trust in the clinician (measured using the TRECS-7 scale)?
- Does the checklist improve how patients feel about their consultation overall?
Participants will be randomly assigned to one of two groups:
- One group will receive an LLM-guided checklist that helps them think more flexibly about their condition.
- The other group will receive an LLM-generated likely diagnosis and brief explanation of their symptoms.
In both groups, the information from the AI tool will be shared with both the patient and the clinician before the consultation.
Patients in the debiasing (intervention) group will:
- Complete a short set of questions with help from a researcher
- Receive a simple summary from the AI that reflects their beliefs and gently challenges any unhelpful thinking
- Attend their regular specialist appointment
- Complete a short survey afterwards capturing their thoughts, experience and basic demographics
Patients in the diagnosis-only (control) group will:
- Describe their symptoms to the AI LLM
- Receive a likely diagnosis and short explanation based on this description
- Attend their regular specialist appointment
- Complete a short survey afterwards capturing their thoughts, experience and basic demographics
Detailed description
A patient's experience of physical discomfort and incapability is closely tied to how they interpret bodily sensations. The human mind is a meaning-making system that rapidly forms stories and assumptions about internal experiences. When individuals experience musculoskeletal pain or dysfunction, their initial interpretations often fall into broad cognitive categories: (1) harm that requires rest and protection; (2) threat to valued roles and activities; or (3) the belief that symptom elimination is the sole path to recovery. These automatic, unconscious interpretations can be adaptive in acute or dangerous situations, but they may also lead to biased or inaccurate symptom appraisals. When misaligned with the underlying pathology, such heuristics can exacerbate emotional distress, delay accurate diagnosis, and drive unnecessary investigations or treatments. The challenge, therefore, lies in supporting patients to reframe these beliefs and engage with their symptoms more adaptively.
Cognitive debiasing strategies have emerged as a promising approach to address this concern. These strategies aim to slow down automatic thinking, challenge entrenched assumptions, and promote more flexible, reflective, and value-aligned reasoning. By encouraging a more nuanced understanding of bodily signals, cognitive debiasing may improve the quality of clinical decisions and overall patient experience-offering advantages over traditional educational or informational tools.
Recent advances in Artificial Intelligence (AI), particularly the rise of Large Language Models (LLMs), have opened new possibilities for enhancing cognitive debiasing interventions. LLMs such as ChatGPT can analyze and synthesize patient-reported symptoms and beliefs to generate supportive, plain-language summaries of their thinking. This process may help patients recognize their own interpretive patterns and consider alternative, less distressing explanations for their symptoms. In parallel, LLMs can assist clinicians by flagging potentially unhelpful or distorted beliefs prior to a consultation, allowing for more tailored and empathic communication.
This trial tests whether a structured, LLM-facilitated debiasing intervention can better support accurate symptom appraisal and enhance the clinical encounter, compared to LLM-generated diagnosis alone. This work builds on the recognition that there is wide variation in musculoskeletal care experience and decision-making, with existing tools such as decision aids and question prompt lists often falling short in challenging rigid or unhelpful thinking patterns.
Study design
- Primary purpose
- Supportive care
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Number of arms
- 2
- Model description
- Treatment arm will be determined at time of presentation by a validated random number generator (random.org). Patients will be randomized to receive either an LLM-facilitated structured debiasing checklist (1) or LLM-facilitated diagnostic feedback (0) prior to consultation with the clinician.
| Arm | Type | Receives |
|---|---|---|
| LLM-Facilitated Cognitive Debiasing Aid | Experimental | Behavioral: LLM-facilitated cognitive debiasing aidThe 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. |
| Usual Care | 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. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (5 listed)
- 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
- Pre-visit diagnosis of chronic, non-traumatic musculoskeletal condition (including, but not limited to: osteoarthritis, carpal tunnel syndrome, trigger digit, Dupuytren's, De Quervain's, lateral epicondylitis)
Key exclusion criteria (1 listed)
- Any impairment preventing completion of surveys on a tablet
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| LLM-facilitated cognitive debiasing aidAs part of the intervention, patients first respond to a series of questions about their beliefs regarding their symptoms (e.g., "What's usually behind these symptoms?"), with responses transcribed verbatim via tablet. These responses are input into a Large Language Model (LLM), which generates a brief, supportive summary of the patient's beliefs, shared back with the patient to encourage self-awareness and reflection. Patients are then invited to consider prompts such as, "What emotions or circumstances might be influencing your thinking?" with their reflections again transcribed. The LLM analyzes these reflections to identify potential signs of emotional distress or maladaptive beliefs, and this output is again provided to the patient. The LLM summary of identified maladaptive beliefs is then also shown to the clinician ahead of the consultation to support more tailored, empathetic communication. | Behavioural | LLM-Facilitated Cognitive Debiasing Aid |
Primary outcome
Trust and Experience with the Clinician Scale (TRECS-7)
Time frame: Measured once, immediately following consultation with the musculoskeletal specialist
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.
1 secondary outcome
Subjective Experience Using the LLM
Time frame: Measured once, immediately following consultation with the musculoskeletal specialist
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 9 Jun 2026.
- Individual participant dataSharing planned: No
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
David Ring, MD, PhD study director
Dell Medical School, University of Texas at Austin, TX, United States
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing LLM-facilitated cognitive debiasing aid in people with Any Chronic, Non-traumatic Orthopedic Condition, run by University of Texas at Austin at 1 site in United States.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 5 inclusion and 1 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: under way, not looking for participants, as of the sponsor's last update on 9 Jun 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in United States. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Trust and Experience with the Clinician Scale (TRECS-7) (time frame: Measured once, immediately following consultation with the musculoskeletal specialist). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 9 Jun 2026.