The task of creating a personalised health assistant, a chatbot, for coeliacs is believed to be beneficial both for individuals in pursuit of accurate data and for those diagnosed with coeliac disease (CD). This condition is a chronic autoimmune disorder triggered by gluten consumption, a protein found in wheat, barley, and rye [1]. It affects 1 in 100 people worldwide, with the only treatment available to date being the recommendation to follow a gluten-free diet [2].
This work researched, and subsequently applied, recent advances in chatbots to the health sector, specifically with the aim of assisting coeliacs. Following an in-depth analysis of numerous state-of-the-art models and techniques, a system was implemented towards achieving the goal of successfully creating a chatbot that would process and simulate human conversation by answering various questions about CD [3]. Moreover, it could connect individuals to relevant support groups and resources, which could be beneficial to them on a daily basis.
Data collection, cleaning and handling proved to be the main challenge of this project, in view of the substantial amount of data needed and the various unknowns of CD. Furthermore, it was established that more applications utilising artificial intelligence (AI) would be needed for persons suffering from this disorder, towards facilitating their daily life.
The research at the basis of the project and the implementation of the proposed system were evaluated through surveys and interviews. The assessment focused on the system’s performance, including the chatbot’s usability, effectiveness, and user satisfaction.
The majority of the participants evaluating the proposed chatbot confirmed the AI element as a valuable tool. This is mostly due to its ability to provide timely and accessible information and support to help them manage their condition and make informed choices about their diet and lifestyle.
Figure 1. A dictionary definition of coeliac disease (credit: iStock.com/Chiociolla)
Figure 2. A chatbot screenshot (credit: iStock.com/Tero Vesalainen)
Student: Ruby Ai Young
Supervisor: Prof. Matthew Montebello