Empathetic Communication Practice Tool

Project phases

Published: October 17, 2025

Last Updated: 1 month ago.

Communication skills and empathy make a huge impact in disciplines, and careers, that involve patient interaction. To introduce new opportunities for practicing empathetic communication, two professors from the Faculty of Pharmaceutical Sciences at the University of British Columbia (UBC), and the UBC Cloud Innovation Centre (CIC), co-developed a real-time, voice-to-voice prototype that would allow students to practice communication skills with simulated patients, supported by an AI-powered empathy coach.

The tool demonstrates how generative AI and voice-technology could support practicing critical skills and offer a unique learning opportunity. As a complement to existing curriculum, this tool can create new interactive learning opportunities centred on sensitivity and compassion in clinical care, beyond instructor-supervised sessions in the classroom.

Approach

The web application is built on AWS Cloud Infrastructure and uses generative AI to support learning in pharmaceutical sciences. Leveraging multiple Large Language Models, enhanced with contextual data from Retrieval Augmented Generation, the tool simulates patient-interactions in real time and functions as an Empathy Coach, providing an evaluation of student performance.

The Empathy Coach provides real-time feedback during conversations, accessible via a dedicated panel. Students can track progress across interactions, review category-level scores, and compare cognitive versus affective empathy performance, while instructors can view aggregated class trends, analyze individual conversations, and integrate empathy performance into curriculum and grading. This structured feedback loop fosters consistent skill development, realistic patient interaction, and improved empathetic communication in healthcare education.

Click here to go directly to the project GitHub repository.

Screenshots of UI

This section outlines the core stages of the user journey, as represented through screenshots of the user interface.

STUDENT VIEW

_{After logging into the tool, students are taken to the dashboard, which displays the patient groups. Students must have an access code from their instructor to join a group.}

_{Selecting a group shows a list of patients, which also reveals the students’ learning progress, where completed LLM evaluations are marked as Complete. Selecting Review will take students to a page where a simulated conversation between the student and the LLM takes place.}

_{The student can answer the questions the LLM asks, either through text or voice.}

_{Once the student provides a cure or diagnosis, the LLM will evaluate the student. Above is an example of the Empathy Coach Summary view from the student’s side.}

INSTRUCTOR VIEW

_{Selecting a simulation group displays the analytics of each patient’s interactions.}

_{Selecting Edit Patients leads to a page where instructors can view a list of patients within the group, and can either remove or edit existing patient profiles or add new ones. Instructors can also toggle LLM Completion, depending on whether or not they want the LLM to evaluate the student.}

_{By clicking the session dropdown, instructors can view the chat history between that student and the LLM.}

_{Clicking the View Students tab leads to a page where the instructor can view all the students in this simulation group. The Access Code of the group is a special code that allows students to join the group. The instructor will have to send this code to them.}

ADMIN VIEW

_{Administrators can Add Instructors or select an instructor to view their details, including which group(s) they are active in.}

_{The Simulations Group tab displays the list of simulation groups available. The status of the simulation groups can be changed here.}

_{Clicking on Create Simulation Group allows the administrator to create a new group, specifying the name and description. Here, instructors can be assigned and the System Prompt for the LLM can be changed.}

Supporting Artifacts

Click below to see technical details of the solution, including the detailed Architecture. Or click here to go directly to the project GitHub repository.

Architecture Diagram

A detailed explanation of the diagram can be found on the project GitHub repository.

Technical Details

The platform is built on a secure, cloud-based foundation powered by AWS services to ensure scalability and deliver real-time interactions for students. The student interface is deployed via AWS Amplify, with Amazon API Gateway managing backend communications. Conversation data and embeddings are stored across Amazon DynamoDB and Amazon RDS, enabling context-aware and personalized responses during each learning experience.

Students can interact with virtual patients through both text and voice. Speech-to-speech conversations are powered by the Amazon Nova Sonic model, which supports real-time, natural dialogue using bidirectional audio streaming.

The prototype includes an Empathy Coach powered by Amazon Nova Pro, which evaluates how students communicate, measuring skills like perspective-taking, emotional resonance, and clarity. Feedback is given in real time, with practical suggestions for alternative responses, so students can strengthen both their empathy and clinical reasoning.

For more details, check out the solution on GitHub.

Acknowledgements

This project was created in collaboration with Jane Xia and Colleen Inglis from the UBC Faculty of Pharmaceutical Sciences.

Image from the Faculty of Pharmaceutical Sciences.

Student Team: Development by Sharon Marfatia and Zayan Sheikh. Project assistance by Anya Ameen.

About the University of British Columbia Cloud Innovation Centre (UBC CIC)

The UBC CIC is a public-private collaboration between UBC and Amazon Web Services (AWS). A CIC identifies digital transformation challenges, the problems or opportunities that matter to the community, and provides subject matter expertise and CIC leadership.

Using Amazon’s innovation methodology, dedicated UBC and AWS CIC staff work with students, staff and faculty, as well as community, government or not-for-profit organizations to define challenges, to engage with subject matter experts, to identify a solution, and to build a Proof of Concept (PoC). Through co-op and work-integrated learning, students also have an opportunity to learn new skills which they will later be able to apply in the workforce.

Projects