Computer-Animated Character for Understanding Medical Illustrations

Recruiting at 1 trial location

Overseen By Timothy Bickmore, PhD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Northeastern University

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

Compensation: Varies

Number of Visits: 2

Duration: 30 minutes

300 Participants Needed

Trial Summary

Will I have to stop taking my current medications?

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

What data supports the effectiveness of the treatment Embodied Conversational Agent (ECA)?

Research shows that Embodied Conversational Agents (ECA) are effective in helping patients understand medical information, especially for those with low health literacy. Studies have found that these animated characters improve patient understanding of medical procedures and medication instructions, making them a useful tool for health education. ^{1 2 3 4 5}

Is it safe to use computer-animated characters to help understand medical information?

Research on using animated computer agents to explain medical documents has not reported any safety concerns, suggesting they are generally safe for helping people understand medical information. ^{1 2 5 6 7}

How is the Embodied Conversational Agent (ECA) treatment different from other treatments for understanding medical illustrations?

The Embodied Conversational Agent (ECA) is unique because it uses a computer-animated character to simulate face-to-face conversations, making it easier for patients with low health literacy to understand medical information. Unlike traditional methods, it provides automated health education and behavior change counseling, ensuring that complex medical documents are more accessible. ^{1 2 3 8 9}

What is the purpose of this trial?

The investigators will evaluate a computer-animated character that explains medical illustrations to people, comparing the character to having people understand the illustrations on their own, and also comparing the computer character on a computer display to one in immersive virtual reality. The investigators will determine which method leads to the best understanding and lowest anxiety.

Research Team

Timothy Bickmore, PhD

Principal Investigator

Northeastern University

Eligibility Criteria

This trial is for adults over 18 who speak English or Spanish fluently, can consent on their own, and have good enough vision (with glasses if needed) to read educational documents. There are no specific exclusion criteria listed.

Inclusion Criteria

Has adequate corrected vision to read patient education documents

I can make my own medical decisions.

I am over 18 years old.

Exclusion Criteria

Not applicable.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

Treatment

Participants engage with patient education documents using different methods: unaided, with a 2D ECA, or with a 3D ECA in virtual reality

30 minutes

1 session (in-person or virtual)

Follow-up

Participants are assessed for knowledge, anxiety, satisfaction, reading effort, and acceptability after the session

30 minutes

1 session (in-person or virtual)

Treatment Details

Interventions

• Embodied Conversational Agent (ECA)

Trial Overview The study tests an Embodied Conversational Agent (ECA), a computer-animated character that explains medical illustrations. It compares understanding with the ECA against self-explanation and also looks at the difference between viewing the ECA on a computer versus in virtual reality.

Participant Groups

Group I: ECA-3D Experimental Treatment 1 Intervention

Participants read a patient education document with the assistance of an embodied conversational agent in virtual reality.

Group II: ECA-2D Experimental Treatment 1 Intervention

Participants read a patient education document with the assistance of an embodied conversational agent rendered in 2D on a computer monitor.

Group III: CONTROL Active Control 1 Intervention

Participants read a patient education document without assistance.

Who Is Running the Clinical Trial?

Northeastern University

Lead Sponsor

Trials

103

Recruited

72,600+

Boston University

Collaborator

Trials

494

Recruited

9,998,000+

Tufts Medical Center

Collaborator

Trials

264

Recruited

264,000+

Findings from Research

A study evaluating responses to 200 medication-use questions found that a medication database provided more clinically correct, complete, safe, and useful answers than an AI chatbot, with 97% of questions answered by the database compared to 80% by the chatbot.

While the chatbot's clinical correctness was comparable to the database at 85%, it lagged behind in completeness (65%), safety (71%), and usefulness (68%), indicating a need for further improvements in chatbot technology for reliable clinical use.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Evaluation of inpatient medication guidance from an artificial intelligence chatbot. Beavers, J., Schell, RF., VanCleave, H., et al.[2023]

A focus group study involving 12 women with previous cesareans and 8 prenatal providers evaluated an Embodied Conversational Agent (ECA) designed to assist in decision-making about birth options, revealing that both groups found the ECA could effectively provide information and support during consultations.

Participants noted that while the ECA appeared somewhat 'robot-like,' improvements in its visual appeal and clarity regarding its role in the decision-making process are necessary for better integration into patient care.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The Perspectives of Women and Their Health-Care Providers Regarding Using an ECA to Support Mode of Birth Decisions. Chinkam, S., Steer-Massaro, C., Herbey, I., et al.[2022]

References

1. Ireland pubmed.ncbi.nlm.nih.gov

Using computer agents to explain medical documents to patients with low health literacy. [2022]

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

Animation-supported consent for urgent angiography and angioplasty: a service improvement initiative. [2021]

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

Usability of conversational agents by patients with inadequate health literacy: evidence from two clinical trials. [2022]

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

Using conversational agents to explain medication instructions to older adults. [2020]

5. England pubmed.ncbi.nlm.nih.gov

Impact of animation-supported consent on complaints and serious incidents due to failure to inform. [2022]

6. England pubmed.ncbi.nlm.nih.gov

Evaluation of a pictograph enhancement system for patient instruction: a recall study. [2021]

7. England pubmed.ncbi.nlm.nih.gov

Evaluation of inpatient medication guidance from an artificial intelligence chatbot. [2023]

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

Acceptability of a Virtual Patient Educator for Hispanic Women. [2021]

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

The Perspectives of Women and Their Health-Care Providers Regarding Using an ECA to Support Mode of Birth Decisions. [2022]