Elia Gabarron1, Dillys Larbi1, Kerstin Denecke2, Eirik Årsand1. 1. Norwegian Centre for E-health Research, University Hospital of North Norway, Tromsø, Norway. 2. Bern University of Applied Sciences, Bern, Switzerland.
Abstract
BACKGROUND AND OBJECTIVE: The number of publications on the use of chatbots for health is recently increasing, however to our knowledge, there are no publications summarizing what is known about using chatbots for public health yet. The objective of this work is to provide an overview of the existing scientific literature on the use of chatbots for public health, for which purpose have chatbots been used, and whether health-related outcomes have been reported. METHODS: We carried out a literature review on this topic across 5 databases: Pubmed, EMBASE, PsychINFO, SCOPUS, and IEEE Xplore. Identified papers were classified according to their underlying technology, application area, and study design. RESULTS: A total of 15 relevant papers were identified: eight of these papers were developmental studies that tested the feasibility or usability of a chatbot, and seven were interventional studies. All the interventional studies reported positive health- related outcomes associated with the chatbot use. DISCUSSION: The first studies testing chatbots for public health seem very promising; however, there are various aspects that should be improved, including the chatbots' designs, studies' methods, and analysis and reporting of results. More high-quality studies and improved reporting of chatbots' use are needed.
BACKGROUND AND OBJECTIVE: The number of publications on the use of chatbots for health is recently increasing, however to our knowledge, there are no publications summarizing what is known about using chatbots for public health yet. The objective of this work is to provide an overview of the existing scientific literature on the use of chatbots for public health, for which purpose have chatbots been used, and whether health-related outcomes have been reported. METHODS: We carried out a literature review on this topic across 5 databases: Pubmed, EMBASE, PsychINFO, SCOPUS, and IEEE Xplore. Identified papers were classified according to their underlying technology, application area, and study design. RESULTS: A total of 15 relevant papers were identified: eight of these papers were developmental studies that tested the feasibility or usability of a chatbot, and seven were interventional studies. All the interventional studies reported positive health- related outcomes associated with the chatbot use. DISCUSSION: The first studies testing chatbots for public health seem very promising; however, there are various aspects that should be improved, including the chatbots' designs, studies' methods, and analysis and reporting of results. More high-quality studies and improved reporting of chatbots' use are needed.
Keywords:
Chatbot; mHealth; public health; public health informatics