Background: Conversational agents also known as chatbots are computer programs designed to simulate human text or verbal conversations. They are increasingly used in a range of fields, including healthcare. By enabling better accessibility, personalization and efficiency, conversational agents have the potential to improve patient care.
Objectives: To review the current applications, gaps and challenges in the literature on conversational agents in healthcare and provide recommendations for their future research, design and application.
Methods: We performed a scoping review. A broad literature search was done in Medline (Ovid), EMBASE (Ovid), PubMed, Scopus and Cochrane central with the search terms “conversational agents”, “conversational AI”, “chatbots” and associated synonyms. We also searched grey literature using sources such as OCLC World Cat database and Research Gate in April 2019. Reference lists of relevant articles were checked for further articles. Screening and data extraction were performed in parallel by two review authors. The included evidence was analyzed narratively employing the principles of thematic analysis.
Results: The literature search yielded 47 study reports (45 articles and two ongoing clinical trials) which matched the inclusion criteria. The identified conversational agents were largely smartphone applications-delivered (n=23) and used free text only as the main input (n=19) and output (n=30) modality. Case-studies describing chatbot development (n=18) were most prevalent and only 11 RCTs were identified. Three most commonly reported conversational agent applications in the literature were treatment and monitoring, healthcare service support, and patient education.
Conclusions: The literature on conversational agents in healthcare is largely descriptive and aimed at treatment and monitoring and health service support. It mostly reports on text-based, AI-driven and mobile application-delivered conversational agents. There is an urgent need for robust evaluation of diverse healthcare conversational agents’ formats focusing on their acceptability, safety and effectiveness.