MediGreet: ER Welcome Bot

Screen Capture of the User Interface

Inspiration

The inspiration for MediGreet came the immense pressure ER receptionists face daily. Often, these front-line workers are met with the stress, frustration, and anger of patients in distress. We wanted to create a solution that could alleviate this burden, providing a calming presence to manage these initial interactions while allowing receptionists to focus on other critical tasks.

What it does

MediGreet is an ER Welcome Bot designed to serve as the first point of contact for patients entering the emergency room. It calmly gathers essential information from patients, de-escalates tense situations, and ensures that patients feel heard and cared for from the moment they walk through the door. By handling these challenging interactions, MediGreet frees up receptionists to focus on their other important duties, improving the overall efficiency and atmosphere of the ER.

How we built it

We built MediGreet using Unreal Engine for the user interface, Google TTS API for natural, clear verbal communication, and the ChatGPT 4 AI model to handle patient interactions. To connect the Unreal Engine interface with the Python backend, where the TTS and AI functionalities were implemented, we used WebSockets. Our development process also focused on prompting the AI model to respond empathetically, especially in high-stress scenarios common in the ER.

Challenges we ran into

One of the major challenges we faced was ensuring that MediGreet could handle a wide range of patient emotions without escalating the situation. Training the AI to maintain a calm and professional demeanor while managing complex interactions was a significant hurdle.

Accomplishments that we're proud of

We are proud of successfully creating a system that not only meets the technical requirements but also truly addresses the emotional needs of patients. We are also proud of overcoming the technical challenges of integrating AI, TTS, and real-time data systems into a unified solution.

What we learned

Throughout this project, we learned a great deal about the complexities of human-AI interaction, particularly in high-stress environments like an ER. We gained valuable insights into the importance of empathy in AI responses. This experience has deepened our understanding of how technology can be used to improve real-world interactions in meaningful ways.

What's next for MediGreet: ER Welcome Bot

The next steps for MediGreet include refining the AI to handle even more complex scenarios and expanding its integration capabilities with hospital management systems. Additionally, another avenue that we could explore is incorporating XR technologies, such as Virtual Reality (VR) and Augmented Reality (AR), into the system to make the experience more immersive for patients since Unreal Engine has native support for these technologies.