Chatbot Communication Training for Communication

Not yet recruiting at 2 trial locations

Overseen By Jenny KR Francis, MD, MPH

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Texas Southwestern Medical Center

Disqualifiers: Non-English/Spanish speakers

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

Compensation: Varies

Number of Visits: 2

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests a new chatbot training tool to help pediatricians, including medical residents and fellows, improve their discussions about reproductive health with teens and their parents. The goal is to boost doctors' confidence and skills in these crucial conversations, aiding adolescents in delaying pregnancy until adulthood. Doctors will practice with avatar simulations, similar to virtual role-plays, to enhance their communication skills. The study seeks medical providers from the Adolescent and Young Adult Medicine Clinic in Dallas who can speak or read English or Spanish. As an unphased trial, it offers a unique opportunity to contribute to enhancing healthcare communication skills.

Will I have to stop taking my current medications?

The trial information does not specify whether participants need to stop taking their current medications.

What prior data suggests that this chatbot communication training is safe for use in medical education?

Research has shown that chatbots have been safely used in various training settings. Studies have found positive results when chatbots enhance safety management and training. These tools increase user awareness and compliance without any reported harm.

In another study, chatbots improved hazard awareness, and participants found them beneficial. However, some privacy concerns exist because conversations with chatbots might be used for further training. Users should understand these privacy risks.

Overall, using chatbots for communication training appears well-received, with no major safety issues reported. This suggests a safe experience for those considering joining the trial. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about the Chatbot Communication Training because it offers an innovative way to enhance communication skills in healthcare. Unlike traditional methods that rely on lectures or role-playing, this training uses an interactive avatar tool to simulate real-life scenarios. This approach allows physician learners to practice and improve their skills in shared decision-making and person-centered contraceptive counseling in a controlled, safe environment. By providing instant feedback and allowing for repeated practice, the tool aims to boost confidence and effectiveness in communication with patients, which is a crucial part of delivering quality care.

What evidence suggests that this chatbot communication training is effective for improving clinician communication skills?

Research has shown that AI chatbots can serve as effective learning tools. They often enhance learning by providing personalized experiences, boosting confidence, and increasing engagement. One study found that these chatbots helped students improve their speaking skills and confidence. Another study demonstrated that chatbots can enhance learning success and performance. Although these studies primarily focus on schools, the positive results suggest that chatbot communication training, such as the Avatar training in this trial, can effectively build skills and confidence. This is crucial for medical residents learning to discuss reproductive health with teens and parents. ^{6 7 8 9 10}

Who Is on the Research Team?

Jenny KR Francis, MD

Principal Investigator

UTSouthwestern

Are You a Good Fit for This Trial?

This trial is for pediatricians (residents, fellows, attendings) from the Adolescent and Young Adult Medicine Clinic at Children's Medical Center of Dallas. It also includes adolescents aged 14-21 and one caregiver attending with them.

Inclusion Criteria

Pediatricians (residents, fellows, attendings) recruited from the Adolescent and Young Adult (AYA) Medicine Clinic at Children's Medical Center of Dallas

I am 18-21 years old and a patient at the AYA Clinic in Dallas.

Caregiver (1) of recruited patients who attend the encounter with the patients recruited from the Adolescent and Young Adult (AYA) Medicine Clinic at Children's Medical Center of Dallas

Exclusion Criteria

I cannot speak or read in Spanish or English.

Adolescent/young adult is not an active patient

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

Training

Medical residents undergo avatar communication training to improve SDM and PCCC skills

2 hours

1 session (virtual)

Evaluation

Participants' SDM and PCCC skills are evaluated through pre- and post-training assessments

2 hours

1 session (virtual)

Follow-up

Participants are monitored for changes in confidence and skills post-training

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• Chatbot Communication Training

Trial Overview

The study is testing a chatbot communication training tool designed to help pediatricians improve their discussions about contraception with adolescent patients and their mothers through simulated interactions.

How Is the Trial Designed?

Group I: Avatar training Experimental Treatment 1 Intervention

One hundred physician learners will train with the avatar communication training tool as a behavioral intervention. Before the training (T0), the learners will complete a pre-survey to assess their baseline confidence. At the start of training, after a brief introduction and orientation to the tool, the learners will complete a 10-min uninterrupted scenario with a teen-parent avatar dyad about a contraception scenario. After the initial scenario (T1), the learner will pause and complete an assessment to evaluate use of SDM (Shared decision making) skills and PCCC (person-centered contraceptive counseling). Then, the learner will train for an hour with the tool. At the end (T2), the learner will complete another uninterrupted scenario and evaluate their confidence, SDM, and PCCC skills.

Who Is Running the Clinical Trial?

University of Texas Southwestern Medical Center

Lead Sponsor

Trials

1,102

Recruited

1,077,000+

Published Research Related to This Trial

The web-based adverse event tracking system (eAETS) has effectively supported 175 clinical protocols over four years, capturing 2,440 adverse event reports, including minor symptoms that could indicate serious issues.

Out of the reported AEs, 1,053 did not align with the initial risk profiles, leading to corrective recommendations in 13% of the protocols, highlighting the system's role in enhancing subject safety by identifying unanticipated patterns.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The impact of minor adverse event tracking on subject safety: a web-based system. Shenvi, NV., Gebhart, SS.[2009]

A proof-of-concept study using recurrent neural networks (RNNs) showed promise for automating the classification of adverse event (AE) terminology from FDA's FAERS and structured product labels (SPLs), which could improve regulatory efficiency.

The model performed well on SPL data, matching or exceeding conventional methods, but had mixed results on FAERS data, suggesting that more extensive data sets are needed for better generalization and validation of AE detection.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Utilizing Deep Learning for Detecting Adverse Drug Events in Structured and Unstructured Regulatory Drug Data Sets. Knisely, BM., Hatim, Q., Vaughn-Cooke, M.[2022]

AdEPro is an interactive app designed to simplify the exploration of adverse event data from clinical trials, allowing users to visualize data on individual subjects and treatment groups without needing extensive programming skills.

The app serves as a 'hypothesis generator' for users to quickly investigate questions about adverse events, such as their onset and severity, while ensuring that patient data is processed locally for privacy and security.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

AdEPro: Animation of Adverse Event Profiles-Presentation of an Easy-to-Use App for Visually Exploring Individual Study Data. Mentenich, N., Tasto, C., Becker, B.[2021]

The study identified three types of adverse events in communication skills training (CST) for physicians, including emotional trauma from personal experiences, lack of empathetic feedback, and referrals for remedial training as a risk management strategy.

To enhance the safety and effectiveness of CST, it is crucial for facilitators to recognize emotional cues and risk factors early, and to master specific feedback techniques that can prevent potential adverse events.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Averting adverse events in communication skills training: a case series. Levin, T., Horner, J., Bylund, C., et al.[2010]

Citations

1.

nature.com

nature.com/articles/s41539-025-00311-8

Effects of different AI-driven Chatbot feedback on learning ...

We investigated how metacognitive, affective, and neutral feedback from an educational chatbot affected learning outcomes and brain activity.

2.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC10290125/

Systematic review and meta-analysis of the effectiveness of ...

The key findings of our study are that chatbot interventions targeting physical activity, fruit and vegetable consumption, sleep duration, and ...

3.

sciencedirect.com

sciencedirect.com/science/article/pii/S2666920X24000316

A systematic review of AI-powered chatbots for English as ...

The study provides insights into the effectiveness of AI chatbots in enhancing students' English-speaking learning outcomes, confidence, engagement and ...

4.

educationaltechnologyjournal.springeropen.com

educationaltechnologyjournal.springeropen.com/articles/10.1186/s41239-023-00426-1

Role of AI chatbots in education: systematic literature review

We found that students primarily gain from AI-powered chatbots in three key areas: homework and study assistance, a personalized learning experience, and the ...

5.

ijem.com

ijem.com/pedagogical-influence-of-ai-chatbots-on-learning-outcomes-a-systematic-review

Pedagogical Influence of AI-Chatbots on Learning Outcomes

Chatbots can be effective learning aids that increase learning achievement and academic performance compared to traditional methods, especially in virtual ...

6.

hai.stanford.edu

hai.stanford.edu/news/be-careful-what-you-tell-your-ai-chatbot

Be Careful What You Tell Your AI Chatbot | Stanford HAI

A Stanford study reveals that leading AI companies are pulling user conversations for training, highlighting privacy risks and a need for ...

7.

digiqt.com

digiqt.com/blog/chatbots-in-safety-management/

Chatbots in Safety Management: Proven Positive Gains

Chatbots in Safety Management improve reporting, training, compliance, and incident response. Explore features, use cases, ROI, integrations ...

8.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC9749401/

Can a chatbot enhance hazard awareness in the construction ...

The results showed that Telegram chatbot training enhanced the hazard awareness of participants with less onsite experience and in less complex scenarios.

9.

news.mit.edu

news.mit.edu/2024/faster-better-way-preventing-ai-chatbot-toxic-responses-0410

A faster, better way to prevent an AI chatbot from giving ...

Researchers create a curious machine-learning model that finds a wider variety of prompts for training a chatbot to avoid hateful or harmful output.

10.

aiha.org

aiha.org/news/240521-how-good-are-chatbots-at-summarizing-oehs-regulations

How Good Are Chatbots at Summarizing OEHS Regulations?

Someone unfamiliar with the regulations could be lulled into a false sense of security that the chatbot is answering a question accurately.