# Engaging Artificial Intelligence (AI)-based chatbots in digital health: A systematic review

## TL;DR

This paper reviews research on AI-based chatbots in healthcare, identifying key areas like text quality and user engagement, and highlights gaps in rigorous evaluation methods.

## Contribution

The paper provides a systematic review of AI-based chatbots in healthcare, emphasizing gaps in clinical evaluation and theoretical frameworks.

## Key findings

- Four main research areas identified: text quality, clinical efficacy, user engagement, and safety.
- Current literature lacks randomized controlled trials and theoretical frameworks for evaluation.
- Research gaps highlight the need for more rigorous and systematic studies on chatbot performance.

## Abstract

The healthcare sector is rapidly evolving with the integration of Artificial Intelligence (AI). As AI technologies shift from rule-based expert systems to deep learning architectures, AI-based chatbots have emerged as innovative solutions to persistent challenges in the health domain. Given the growing concerns about their effectiveness and ethical implications, as well as the demand to optimise their potential in facilitating health outcomes, this study conducts a systematic review of existing research on AI-based chatbots, focusing on their applications and evaluation. A total of 348 articles, collected from eight databases—PubMed/MEDLINE, EMBASE, PsycINFO, CINAHL, IEEE, the ACM Digital Library, Scopus, and Web of Science - 20 of which were analysed. This review identifies four main research areas concerning AI-based chatbots: text quality, clinical efficacy, user engagement, and safety. It also highlights the lack of randomised controlled trials (RCTs) and the limited use of theoretical frameworks in evaluating their performance. Future research directions and practical solutions are discussed.

AI-based chatbots have emerged as promising tools for addressing longstanding challenges within the healthcare sector, particularly in improving access to information, patient support, and care delivery. In response to the rapid and ongoing integration of artificial intelligence into healthcare systems, we, as communication scholars, conducted a comprehensive review of existing academic literature to identify key research gaps related to user engagement with AI-based chatbots. Specifically, our review focuses on their effectiveness, ethical implications, and the growing demand to optimize their potential in facilitating positive health outcomes. The findings of our review reveal four primary research areas concerning AI-based chatbots: text quality, clinical efficacy, user engagement, and safety. In addition, we identify significant methodological limitations in the current literature, including a lack of randomized controlled trials (RCTs) and the limited use of theoretical frameworks to systematically evaluate chatbot performance and user interactions. These gaps highlight important directions for future research in this rapidly evolving field.