Project number
26004
Organization
UA College of Medicine - Phoenix
Offering
ENGR498-F2025-S2026
Project Scope
The goal of this project is to develop an AI-driven tool that simulates oral board-style examinations for surgical residents and space medicine fellows. The tool will allow users to engage in interactive, case-based scenarios where they can demonstrate their clinical reasoning, decision-making, and communication skills—key competencies required for success in surgical training, practice, and deep space cognitive skill maintenance.
This project includes the following requirements:
1. Understand Current Assessment Methods: Work with medical educators and surgical faculty to understand the structure and grading criteria of current oral board exams. Gather insights into how these exams are conducted, what types of questions are asked, and how performance is evaluated.
2. Evaluate Existing AI Tools: Research and evaluate existing large language models (LLMs) and AI tools that can simulate conversational or examination-style interactions. Assess their ability to handle complex surgical case scenarios, provide meaningful feedback, and adapt to different levels of expertise.
3. Design the AI System: Develop a system architecture for an AI tool capable of:
o Presenting realistic, accurate surgical cases (e.g., patient histories, physical exams, imaging, lab results).
o Engaging in dynamic, conversational interactions with users, posing follow-up questions based on their responses.
o Avoiding hallucinations that would train the learner with incorrect information.
o Providing constructive feedback on clinical reasoning and communication skills.
o Update based on user feedback.
o Tracking user progress over time.
***This project is conducting remote interviews. Please visit https://bit.ly/4oOOXcN to schedule a time to speak to the sponsor***
The goal of this project is to develop an AI-driven tool that simulates oral board-style examinations for surgical residents and space medicine fellows. The tool will allow users to engage in interactive, case-based scenarios where they can demonstrate their clinical reasoning, decision-making, and communication skills—key competencies required for success in surgical training, practice, and deep space cognitive skill maintenance.
This project includes the following requirements:
1. Understand Current Assessment Methods: Work with medical educators and surgical faculty to understand the structure and grading criteria of current oral board exams. Gather insights into how these exams are conducted, what types of questions are asked, and how performance is evaluated.
2. Evaluate Existing AI Tools: Research and evaluate existing large language models (LLMs) and AI tools that can simulate conversational or examination-style interactions. Assess their ability to handle complex surgical case scenarios, provide meaningful feedback, and adapt to different levels of expertise.
3. Design the AI System: Develop a system architecture for an AI tool capable of:
o Presenting realistic, accurate surgical cases (e.g., patient histories, physical exams, imaging, lab results).
o Engaging in dynamic, conversational interactions with users, posing follow-up questions based on their responses.
o Avoiding hallucinations that would train the learner with incorrect information.
o Providing constructive feedback on clinical reasoning and communication skills.
o Update based on user feedback.
o Tracking user progress over time.
***This project is conducting remote interviews. Please visit https://bit.ly/4oOOXcN to schedule a time to speak to the sponsor***