AI Chatbot for Osteoarthritis

(CHAT-OA Trial)

Overseen By David Dallas-Orr, MD, MBA, MTM

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of California, Davis

Disqualifiers: Inability to read and write

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

Compensation: Varies

Number of Visits: 5

100 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

The goal of this clinical trial is to assess the use of a generative artificial intelligence large language model chatbot in improving decision making factors in patients with hip and knee osteoarthritis. The main questions it aims to answer are: Does the use of an artificial intelligence chatbot have an effect on decisional conflict and anxiety related to decision making? Are changes in decisional conflict correlated with changes in patient reported outcomes? Are changes in decisional conflict correlated with health literacy? Participants will interact with an artificial intelligence chatbot prior to their clinic visit with an orthopaedic surgeon, using a structured prompt.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

Is the AI Chatbot for Osteoarthritis safe for humans?

AI chatbots used in healthcare, like those for osteoarthritis, need to ensure safety by focusing on system security, patient safety, and user comfort. While specific safety data for osteoarthritis isn't mentioned, general safety concerns include data privacy, risk management, and ensuring accurate information is provided to users. ^{1 2 3 4 5}

How is the AI Chatbot treatment for osteoarthritis different from other treatments?

The AI Chatbot for osteoarthritis is unique because it uses artificial intelligence to enhance patient involvement in decision-making about surgical options, potentially helping patients avoid unnecessary surgeries by managing their condition with physical training instead. ^{2 6 7 8 9}

What data supports the effectiveness of the AI Chatbot treatment for osteoarthritis?

Research suggests that AI chatbots, like ChatGPT, can help improve patient communication and education in orthopedic care, which includes conditions like osteoarthritis. They can assist in providing information, supporting clinical decisions, and optimizing treatment plans, although their effectiveness specifically for osteoarthritis needs further study. ^{6 9 10 11 12}

Who Is on the Research Team?

Zachary C Lum, DO

Principal Investigator

University of California, Davis

Are You a Good Fit for This Trial?

This trial is for individuals with hip or knee osteoarthritis who are facing decisions about their healthcare. They should be comfortable interacting with an AI chatbot before meeting with an orthopedic surgeon.

Inclusion Criteria

Ability to read and write in English

I am 18 years old or older.

All races and ethnicities

Exclusion Criteria

Inability to read and write in English

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

AI Chatbot Interaction

Participants interact with an AI chatbot prior to their clinic visit to assess its effect on decision making factors

1 week

1 virtual interaction

Clinic Visit

Participants have a clinic visit with an orthopaedic surgeon after interacting with the AI chatbot

1 day

1 in-person visit

Follow-up

Participants are monitored for changes in decisional conflict, anxiety, and health literacy

6 months

3 follow-up assessments

What Are the Treatments Tested in This Trial?

Interventions

• Artificial Intelligence Chatbot

Trial Overview The study tests if a conversational AI chatbot can help reduce decisional conflict and anxiety in patients, improve patient outcomes, and enhance health literacy regarding treatment options for osteoarthritis.

How Is the Trial Designed?

Group I: Artificial Intelligence Chatbot Experimental Treatment 1 Intervention

This arm will interact with an artificial intelligence chatbot prior to their clinic visit.

Group II: Standard of care Active Control 1 Intervention

This arm will undergo standard clinical care without the intervention.

Who Is Running the Clinical Trial?

University of California, Davis

Lead Sponsor

Trials

958

Recruited

4,816,000+

Published Research Related to This Trial

The study analyzed 16,453 lines of dialog from 424 patients with inflammatory bowel diseases (IBD) to explore the feasibility of using natural language processing (NLP) for categorizing patient communications, demonstrating that NLP can effectively categorize patient data into relevant categories such as symptoms, medications, and appointments.

The categorization algorithm showed a high agreement with independent physician evaluations, with 95% of cases having minor or no differences, indicating that NLP can reliably assist in developing chatbots for chronic disease management, potentially improving patient monitoring and education.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

An Exploration Into the Use of a Chatbot for Patients With Inflammatory Bowel Diseases: Retrospective Cohort Study. Zand, A., Sharma, A., Stokes, Z., et al.[2020]

The study developed ADEpedia-on-OHDSI, an informatics platform that integrates FDA's Adverse Event Reporting System (FAERS) data into a standardized format, allowing for improved pharmacovigilance research with a total of 4,619,362 adverse event cases processed.

Mapping accuracy for drug names was high at 96%, and the platform successfully detected triptan-related vascular event signals, demonstrating that combining spontaneous reporting and electronic health record data can enhance signal detection in drug safety monitoring.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

ADEpedia-on-OHDSI: A next generation pharmacovigilance signal detection platform using the OHDSI common data model. Yu, Y., Ruddy, KJ., Hong, N., et al.[2020]

A new electronic health record (EHR)-based system allowed 26 clinicians to submit 217 adverse drug event (ADE) reports to the FDA in real-time, demonstrating an efficient method for reporting that took an average of just 53 seconds per report.

The system provided detailed clinical information about the ADEs, including comorbid conditions and concurrent medications, which could enhance the quality of data submitted to the FDA and potentially improve drug safety monitoring.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Secondary use of electronic health record data: spontaneous triggered adverse drug event reporting. Linder, JA., Haas, JS., Iyer, A., et al.[2019]

Citations

1. Canada pubmed.ncbi.nlm.nih.gov

An Exploration Into the Use of a Chatbot for Patients With Inflammatory Bowel Diseases: Retrospective Cohort Study. [2020]

2. England pubmed.ncbi.nlm.nih.gov

An AI-based patient-specific clinical decision support system for OA patients choosing surgery or not: study protocol for a single-centre, parallel-group, non-inferiority randomised controlled trial. [2023]

3. Germany pubmed.ncbi.nlm.nih.gov

Artificial intelligence and ChatGPT in Orthopaedics and sports medicine. [2023]

4. United States pubmed.ncbi.nlm.nih.gov

Use of an Artificial Intelligence Conversational Agent (Chatbot) for Hip Arthroscopy Patients Following Surgery. [2023]

5. Switzerland pubmed.ncbi.nlm.nih.gov

ChatGPT in orthopedics: a narrative review exploring the potential of artificial intelligence in orthopedic practice. [2023]

6. New Zealand pubmed.ncbi.nlm.nih.gov

ADE Eval: An Evaluation of Text Processing Systems for Adverse Event Extraction from Drug Labels for Pharmacovigilance. [2022]

7. United States pubmed.ncbi.nlm.nih.gov

Pros and Cons of Using Artificial Intelligence Chatbots for Musculoskeletal Rehabilitation Management. [2023]

8. United States pubmed.ncbi.nlm.nih.gov

ADEpedia-on-OHDSI: A next generation pharmacovigilance signal detection platform using the OHDSI common data model. [2020]

9. Netherlands pubmed.ncbi.nlm.nih.gov

Towards Safe Conversational Agents in Healthcare. [2023]

10. England pubmed.ncbi.nlm.nih.gov

Secondary use of electronic health record data: spontaneous triggered adverse drug event reporting. [2019]

11. Canada pubmed.ncbi.nlm.nih.gov

Chatbots for Symptom Screening and Patient Education: A Pilot Study on Patient Acceptability in Autoimmune Inflammatory Diseases. [2023]

12. United States pubmed.ncbi.nlm.nih.gov

Assessing ChatGPT Responses to Common Patient Questions Regarding Total Hip Arthroplasty. [2023]