Chatbot Artificial Intelligence for Genetic Cancer Risk Assessment and Counseling: A Systematic Review and Meta-Analysis
Emily Webster, Muhammad Danyal Ahsan, Luiza Perez, Sarah R. Levi, Charlene Thomas, Paul J. Christos, Andy Hickner, Jada G. Hamilton, Kemi Babagbemi, Evelyn Cantillo, Kevin Holcomb, Eloise Chapman‐Davis, Ravi Sharaf, Melissa K. Frey
Abstract
PURPOSE: Most individuals with a hereditary cancer syndrome are unaware of their genetic status to underutilization of hereditary cancer risk assessment. Chatbots, or programs that use artificial intelligence to simulate conversation, have emerged as a promising tool in health care and, more recently, as a potential tool for genetic cancer risk assessment and counseling. Here, we evaluated the existing literature on the use of chatbots in genetic cancer risk assessment and counseling. METHODS: A systematic review was conducted using key electronic databases to identify studies which use chatbots for genetic cancer risk assessment and counseling. Eligible studies were further subjected to meta-analysis. RESULTS: Seven studies met inclusion criteria, evaluating five distinct chatbots. Three studies evaluated a chatbot that could perform genetic cancer risk assessment, one study evaluated a chatbot that offered patient counseling, and three studies included both functions. The pooled estimated completion rate for the genetic cancer risk assessment was 36.7% (95% CI, 14.8 to 65.9). Two studies included comprehensive patient characteristics, and none involved a comparison group. Chatbots varied as to the involvement of a health care provider in the process of risk assessment and counseling. CONCLUSION: Chatbots have been used to streamline genetic cancer risk assessment and counseling and hold promise for reducing barriers to genetic services. Data regarding user and nonuser characteristics are lacking, as are data regarding comparative effectiveness to usual care. Future research may consider the impact of chatbots on equitable access to genetic services.