AI Tool for Musculoskeletal Disorder

Overseen By Emily H Jaarsma, MD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Texas at Austin

Disqualifiers: Impairment preventing survey completion

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 1

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to determine if an AI tool can help patients better understand their symptoms and improve their trust and experience during visits to a musculoskeletal specialist. Participants will be divided into two groups: one will use an AI-guided checklist to consider their symptoms in new ways, while the other will receive an AI-generated diagnosis and explanation. The AI tool, which includes a large language model (LLM)-facilitated cognitive debiasing aid, will provide information to both the patient and the clinician before the consultation. Adults seeking care for chronic, non-injury-related joint or muscle issues, such as osteoarthritis or carpal tunnel syndrome, may be suitable for this trial. As an unphased trial, this study offers a unique opportunity for patients to contribute to innovative research that could enhance future healthcare experiences.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications, so it's best to check with the study team for guidance.

What prior data suggests that this AI tool is safe for improving patient trust and experience?

Research has shown that using a Large Language Model (LLM) to help patients consider their symptoms is generally safe. In earlier studies, patients using LLM tools did not experience any serious side effects. The AI tool is designed to enhance patients' understanding of their symptoms and build trust with their doctors.

This trial examines how the AI tool affects patient thinking and trust, focusing more on communication than medical treatment. Consequently, the safety risks are lower compared to drug trials. People who have used similar AI tools in the past did not report any harmful effects, and the technology aims to support better conversations between patients and doctors. Therefore, participants can feel confident that the AI tool is safe to use. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about this trial because it explores a new approach to diagnosing musculoskeletal disorders using artificial intelligence. Unlike traditional methods that rely heavily on clinician expertise and conventional diagnostic tools, this trial leverages a Large Language Model (LLM) to provide cognitive debiasing. The LLM-facilitated cognitive debiasing aid helps patients reflect on their beliefs about their symptoms, promoting more flexible thinking. This method could lead to more accurate diagnoses and personalized care by addressing cognitive biases that often affect both patients and clinicians. The anticipation is that this innovative tool will enhance communication and understanding between patients and healthcare providers, offering a fresh perspective on managing musculoskeletal disorders.

What evidence suggests that this AI tool is effective for improving patient trust and consultation experience in musculoskeletal disorder care?

In this trial, one arm uses an AI tool with a Large Language Model (LLM) to facilitate cognitive debiasing, helping patients rethink their muscle and joint symptoms. This tool encourages patients to reflect on their symptoms, leading to better understanding and improved trust with their doctor. Studies have found that when patients think more openly about their condition, they might feel more satisfied with their visit. The LLM also highlights common unhelpful beliefs, aiding doctors in communicating more kindly. This method has shown promise in helping patients understand their symptoms accurately and improving the overall clinic experience. Meanwhile, the control arm uses a tablet-based tool to provide diagnostic feedback without engaging in cognitive debiasing or reflection. ^{1 2 6 7 8}

Who Is on the Research Team?

David Ring, MD, PhD

Principal Investigator

Dell Medical School, University of Texas at Austin, TX, United States

Are You a Good Fit for This Trial?

This trial is for individuals with musculoskeletal disorders or arthritis. Participants should be willing to use an AI tool during their specialist visit and complete surveys before and after the appointment. Specific inclusion and exclusion criteria details are not provided.

Inclusion Criteria

Total combined score on the 6 feelings and thoughts items of > 10 (Appendix 3 of study protocol)

English-speaking

I am 18 years old or older.

Exclusion Criteria

Any impairment preventing completion of surveys on a tablet

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Participants use a tablet-based tool to interact with an LLM for cognitive debiasing or receive a likely diagnosis and explanation

1 day

1 visit (in-person)

Follow-up

Participants complete a survey capturing their thoughts, experience, and basic demographics after the consultation

Immediately following consultation

What Are the Treatments Tested in This Trial?

Interventions

• LLM-facilitated cognitive debiasing aid

Trial Overview The study tests if an AI Large Language Model (LLM) can improve patient trust in clinicians and overall consultation satisfaction. One group uses a debiasing checklist, while the other receives a diagnosis from the LLM, both shared with patients and doctors.

How Is the Trial Designed?

Group I: LLM-Facilitated Cognitive Debiasing Aid Experimental Treatment 1 Intervention

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: Usual Care Active Control 1 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 Is Running the Clinical Trial?

University of Texas at Austin

Lead Sponsor

Trials

387

Recruited

86,100+

Citations

1. jmir.org jmir.org/2024/1/e59439/

Mitigating Cognitive Biases in Clinical Decision-Making ... This study aimed to explore the role of large language models (LLMs) in mitigating these biases through the use of the multi-agent framework.

2. clinicaltrials.gov clinicaltrials.gov/study/NCT07022769

Testing an AI Large Language Model Tool for Cognitive ... This trial tests whether a structured, LLM-facilitated debiasing intervention can better support accurate symptom appraisal and enhance the clinical encounter, ...

3. patlynk.com patlynk.com/trial/NCT07022769

LLM-Facilitated Cognitive Debiasing in Musculoskeletal Care This study focuses on improving how patients interpret and manage musculoskeletal pain or dysfunction. Often, people quickly form beliefs about their ...

4. withpower.com withpower.com/trial/phase-musculoskeletal-diseases-5-2025-dd766

AI Tool for Musculoskeletal Disorder · Info for Participants ... facilitated cognitive debiasing aid will have tolerable side effects & efficacy for patients with Arthritis and Musculoskeletal Disorder. Learn more about the

5. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12134017/

The Role of Artificial Intelligence Large Language Models ... Large language models (LLMs) can contribute to treatment options and outcomes by assisting physiotherapists for conditions like osteoarthritis.

6. sigma.larvol.com sigma.larvol.com/facility.php?FacilityId=5186069&tab=trials

Dell Medical School, University of Texas at Austin Trials N/A. 150. US. LLM-facilitated cognitive debiasing aid. University of Texas at Austin. Any Chronic, Non-traumatic Orthopedic Condition. 12/25. 12/25. NCT07158892 ...

7. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12296254/

Harm Reduction Strategies for Thoughtful Use of Large ... The LLM generates a broad differential but highlights musculoskeletal pain and anxiety as most probable based on pattern frequency in its ...

8. aclanthology.org aclanthology.org/2024.findings-emnlp.814.pdf

Can LLMs Replace Clinical Doctors? Exploring Bias in ... As LLMs increasingly find applications in healthcare, understanding and addressing their biases be- comes paramount. This study focuses on this.