Designing, developing, evaluating, and Implementing a Smartphone-delivered, rule-based COnVERsational agent (DISCOVER): a conceptual framework

Abstract

Background: Conversational agents (CAs), also known as chatbots are computer programs that simulate human conversations using predetermined rule-based responses or employing artificial intelligent algorithms. They are increasingly used in healthcare, particularly via smartphones. There is, at present no conceptual framework guiding the development of smartphone rule-based CAs in healthcare. To fill this gap we propose structured and tailored guidance for their design, development, evaluation, and implementation. Objective: To develop a conceptual framework for the design, evaluation, and implementation of smartphone-delivered, rule-based, goal-oriented, and text-based CAs for healthcare. Methods: We followed Jabareen’s approach to develop this conceptual framework. We performed two literature reviews focusing on healthcare CAs and conceptual frameworks for the development of mHealth interventions. We identified, named, categorized, integrated, and synthesized the information retrieved from the literature reviews to develop the conceptual framework. We then applied this framework by developing a CA and testing it in a feasibility study. Results: The DISCOVER conceptual framework includes eight iterative steps, grouped into three stages: (1) Design, comprising defining the goal, creating an identity, assembling the team, and selecting the delivery interface, (2) Development, including developing the content and building the conversation flow, and (3) Evaluation and implementation of the CA. They were complemented by two cross-cutting considerations, user-centered design, and privacy & security, that were relevant at all stages. The conceptual framework was successfully applied in the development of a CA to support lifestyle changes and prevent type 2 diabetes. Conclusions: Drawing on published evidence, the DISCOVER conceptual framework provides a step-by-step guide to developing rule-based, smartphone-delivered CAs. Further evaluation of this framework in diverse healthcare areas, settings, and for a variety of users is needed to demonstrate its validity. Future research should aim to explore the use of CAs to deliver healthcare interventions, including behavior change and potential privacy and safety concerns. Clinical Trial: NA