AI uses virtual patients to revolutionize nutrition education

In a recent study published in nutrients, Researchers are evaluating a new generative artificial intelligence (AI) model, Authentic Teaching and Learning Application Simulation (ATLAS), aimed at improving the communication skills of nutrition and dietetics students.

Currently, the ATLAS platform is realized using human simulated patients (HSPs), which are cost- and resource-intensive and replace traditional communication methods known as virtual simulated patients (VSPs). , offering a cost-effective, highly reproducible, and personalized alternative.

study: Generative artificial intelligence as a communication guidance tool in nutrition and dietary education — new educational innovation. Image credit: metamorworks / Shutterstock.com

The role of HSP in nutrition education

Communication between nutrition and nutrition professionals and patients is essential for optimal clinical outcomes in any medical field. To date, there is still a lack of research focused on optimally teaching communication skills to students in this field. In particular, the practical application of communication theory presents obvious challenges in the absence of trained humans who can simulate nutrition and nutrition intervention sessions.

The traditional solution to this problem has been the use of HSPs. HSPs are mechanical, often computer-controlled mannequins that reproduce elements of human physiology. Unfortunately, the development, frequent operation, and maintenance of these HSPs are costly and resource-intensive.

To overcome these challenges, AI has facilitated the development of new VSPs. Compared to HSP, VSP is completely computer-based and built on a large language model that powers applications such as ChatGPT.

What is Atlas?

ATLAS is a state-of-the-art voice chat-based platform originally developed by study authors to enhance the learning experience of nutrition students at Monash University in Melbourne, Australia.

ATLAS represents the next generation of communicative experiential learning by representing the confluence between large-scale language models (LLMs), educator-designed patient personas, and generative AI algorithms. Also, while ATLAS negates the need for the expensive her HSP, this model is probably better given that the course requirements can be adapted to the specific needs of a given student.

Interaction with the VSP through voice recognition represents a more realistic student-patient interaction, requiring students to professionally articulate messages with empathy and clarity. ”

An experiential learning session consists of a series of steps initiated by student voice. The model converts it to text, processes the parameters of the given persona, and outputs the student’s response as text and audio. In particular, this model mimics real-life interactions by considering the trust relationship built between the student and her VSP and adjusting responses accordingly.

The VSP was further developed by outlining personal communication styles (talkative, direct, anxious, indifferent, etc.), replicating the diversity observed in the real world…to help students understand the importance of nonverbal communication I’ve put the body language in parentheses so you can see it. ”

Did students find ATLAS useful?

The ATLAS platform is primarily used by students in Monash University’s Master of Nutrition and Dietetics programs who need to interact with VSPs at various stages of their education. Importantly, students are introduced to the experiential learning platform only after completing didactic learning, ensuring they have the knowledge needed to successfully respond to the VSP.

Student response to the platform has been largely positive, with many students working to improve their relationship with the platform and their grades even outside of class hours. In fact, many students have expressed enthusiasm for the platform, especially its ability to provide personalized and immediate feedback that emphasizes the importance of reflection and improvement for future sessions.

conclusion

ATLAS represents a step forward in experiential learning in the medical field. Unlike traditional methods, this approach is cheap, easy to develop and deploy, and given the history of LLM, will perform better over time. ATLAS also supports the growth of users’ communication skills by considering mistakes as part of the learning process and encouraging repetition.

This platform not only bridges the gap between theory and practice in communication skills training, but also bridges the gap between generative AI, academics, and experienced practitioners. ”