Patient Perceived Empathy of an AI Chatbot for Atrial Fibrillation Education

NCT06684457 | Completed

• 1 other identifier: STUDY24010018
• Study Type: interventional
• Target: 40
• Locations: 1 country
• Sites: 1

Brief Summary

Atrial Fibrillation is a chronic disease with significant health consequences like increased risk of stroke, heart failure, heart attack and death. Educating patients about the disease is important for them to be able to understand the condition better, feel empowered and take an active part in their care plan. AI technology can potentially be used to impart such education. However, doing so with care and empathy is equally important. Therefore, it is necessary to ensure when AI technology is used to impart education about atrial fibrillation to patients, the humane aspects of the interaction are rigorously tested. This study examines a way to impart atrial fibrillation education through interaction with an AI chatbot, that uses text and links to educational videos. To participate in this study, people need to be age 18 or older and have a history of newly diagnosed atrial fibrillation. Approximately 40 individuals will be asked to take part in this study. The first step to the study will be reading through, understanding, and signing an informed consent. People who then agree to join the study will have a one-time interaction with the AI chatbot and structured educational material by using an iPad provided to them for the approximately 1 hour duration of the study. People in the study will obtain atrial fibrillation education by typing one by one on the iPad, up to 10 questions about the disease. Answers will include text and links to videos. Before and after atrial fibrillation education, people who join this study will be asked to fill out a survey. The study team will teach patients how to use the iPad and type in questions.

Conditions

Atrial Fibrillation (AF)

Keywords

education; lifestyle modification; atrial fibrillation; generative AI; chatbot; artificial intelligence

Outcome Measures

Primary Outcomes (1)

• Empathy

  Assess patient perceived degree of empathy exhibited by chatbot responses. The degree of empathy will be measured using a pre- and post- chatbot interaction 7 point Likert scale survey, with a higher score suggesting a higher level of perceived empathy. The title of the survey will be "Likert scale based survey for perceived empathy and trust," with the lowest score being 4 and the highest score being 28. Survey form available upon reasonable request.

  From enrollment to end of interaction with chatbot, approximately an hour

Secondary Outcomes (2)

• Knowledge

  From enrollment to end of interaction with chatbot, approximately an hour

• Trust

  From enrollment to end of interaction with chatbot, approximately an hour

Study Arms (1)

Pilot interventional arm

EXPERIMENTAL

Single arm, wherein all consenting participants undergoing interaction with chatbot for atrial fibrillation education.

Behavioral: Atrial Fibrillation Education

Interventions

Atrial Fibrillation Education BEHAVIORAL

Atrial fibrillation education rendered through a generative AI chatbot, using an iPAD. The intervention itself is an approximately 1 hour long interaction with the chatbot or approximately 10 questions about atrial fibrillation, for 1 single interaction.

Pilot interventional arm

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Age greater than18 yrs
• Known diagnosis of atrial fibrillation

You may not qualify if:

• Inability to text/use an electronic device
• Inability to read English

Sponsors & Collaborators

• University of Pittsburgh: lead

Study Sites (1)

UPMC Heart and Vascular Institute

Pittsburgh, Pennsylvania, 15213, United States

Location

MeSH Terms

Conditions

Atrial Fibrillation

Condition Hierarchy (Ancestors)

Arrhythmias, Cardiac; Heart Diseases; Cardiovascular Diseases; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Samir Saba, MD

  UPMC Heart and Vascular Institute

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: PREVENTION
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Model Details: Study design: A single center, cross sectional, uncontrolled, open-label, non-randomized, single arm, experimental pilot study using an LLM based prompt-engineered education chatbot, to impart a Q and A format atrial fibrillation education to patients, prior to their first appointment with a cardiologist or a cardiac electrophysiologist. The prompt-engineered chatbot is built on LLM capabilities yet tailored with the help of physician provided, vetted, open source atrial fibrillation educational material as well as empathy enhancing scripts, and simplified language to a 6th-8th grade reading level. The chatbot would be utilized to enhance the patient-provider interaction by providing empathetic education to patients regarding atrial fibrillation, and empower them with the knowledge they would need to ask informed questions during their patient visit. The chatbot will also be able to direct patients to Heart Rhythm Society's open source educational videos for atrial fibrillation (UpBeat

Study Record Dates

• First Submitted: November 8, 2024
• First Posted: November 12, 2024
• Study Start: November 25, 2024
• Primary Completion: May 2, 2025
• Study Completion: May 2, 2025
• Last Updated: July 8, 2025

Record last verified: 2024-11

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)