Background:The integration of artificial intelligence and chatbot technology in healthcare has attracted significant attention due to its potential to improve patient care and streamline history-taking. As AI-driven conversational agents, chatbots offer the opportunity to revolutionise history-taking, necessitating a comprehensive examination of their impact on medical practice.Objective: This systematic review comprehensively assesses the role, efficacy, usability, and patient acceptance of chatbots for healthcare history-taking. It also explores potential challenges and future opportunities for integration into clinical practice.Methods: This systematic review includes 18 studies and focuses on chatbots for healthcare history-taking to support diagnosis and treatment decisions by capturing detailed patient information. All study designs, except conference papers, were eligible to evaluate the feasibility, acceptability, and effectiveness of chatbot-based history-taking. A systematic search included PubMed, Embase, Medline (via Ovid), CENTRAL, Scopus, and Open Science and covered studies through August 2023. The quality of observational studies was classified using the STROBE criteria, while the RoB 2 tool assessed areas of bias in randomised clinical trials (RCTs).
Results:The review included 15 observational studies and 3 randomised clinical trials (RCTs) and synthesised evidence from different medical fields and populations. Chatbots systematically collect information through targeted queries and data retrieval, improving patient engagement and satisfaction. They also demonstrated the potential to improve healthcare efficiency and accessibility through automated data collection 24/7.
Conclusions:This systematic review provides critical insights into the potential benefits and challenges of using chatbots for history-taking. Chatbots can potentially increase patient engagement, streamline data collection, and improve healthcare decisionmaking. However, the limitations of the studies stem from the different designs and methodological variations, which limits the validity of the results. Clinical Trial: PROSPERO database for systematic reviews, registration number: CRD42023410312