Pilot validation of a frontline chatbot to face COVID-19 using telehealth assistance
Abstract
The novel coronavirus pandemic has overloaded healthcare systems to the limit. Our aim was to assess the effectiveness of a chatbot to identify symptoms of COVID-19. The chatbot was developed to screen patients before teleconsultation. The symptoms informed in the dialogue were compared with those reported to the doctors in an emergency service. Among 96 patients assessed, dyspnea was the most frequent symptom (16,6%), and the only one that showed moderate agreement with the medical history recorded in electronic medical records (Kappa=0.605). In conclusion, the technology was useful in detecting one of the major symptoms of COVID-19. However, it was not possible to evidence its effectiveness to assess minor symptoms.
References
JUDSON, Timothy J. et al. Implementation of a digital chatbot to screen health system employees during the COVID-19 pandemic. Journal of the American Medical Informatics Association, v. 27, n. 9, p. 1450-1455, 2020.
Monitoring and evaluating digital health interventions: a practical guide to conducting research and assessment. Geneva: World Health Organization; 2016. Licence: CC BY- NC-SA 3.0 IGO.
Storm-Versloot MN, Ubbink DT, Kappelhof J, et al. Comparison of an informally structured triage system, the emergency severity index, and the Manchester triage system to distinguish patient priority in the emergency department. Acad. Emerg. Med. 2011; 18(8):822-829.
WILLIAMS, Noelle L. et al. Clinical Integration of Digital Solutions in Health Care: An Overview of the Current Landscape of Digital Technologies in Cancer Care. American Society of Clinical Oncology, 2018.
MARTIN,Alistrair et al. An artificial intelligencebased firstline defence against COVID19: digitally screening citizens for risks via a chatbot, 2020.
GABARRON, Elia et al. What do we know about the use of chatbots for public health? European Federation for Medical Informatics, 2020.
MILNES-IVES et al. The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review .Journal of Medical Internet Research,vol. 22, e20346,p.1, 2020.
