An artificial intelligence-based first-line defence against COVID-19: digitally screening citizens for risks via a chatbot

Abstract

To combat the pandemic of the coronavirus disease 2019 (COVID-19), numerous governments have established phone hotlines to prescreen potential cases. These hotlines have struggled with the volume of callers, leading to wait times of hours or, even, an inability to contact health authorities. Symptoma is a symptom-to-disease digital health assistant that can differentiate more than 20,000 diseases with an accuracy of more than 90%. We tested the accuracy of Symptoma to identify COVID-19 using a set of diverse clinical cases combined with case reports of COVID-19. We showed that Symptoma can accurately distinguish COVID-19 in 96.32% of clinical cases. When considering only COVID-19 symptoms and risk factors, Symptoma identified 100% of those infected when presented with only three signs. Lastly, we showed that Symptoma’s accuracy far exceeds that of simple “yes–no” questionnaires widely available online. In summary, Symptoma provides unparalleled accuracy in systematically identifying cases of COVID-19 while also considering over 20,000 other diseases. Furthermore, Symptoma allows free text input, furthered with disease-specific follow up questions, in 36 languages. Combined, these results and accessibility give Symptoma the potential to be a key tool in the global fight against COVID-19. The Symptoma predictor is freely available online at https://www.symptoma.com.

What Can COVID-19 Teach Us about Using AI in Pandemics?

“…Often, AI designers do not stress these features, which leads to limited reach and low trust in AI-driven protocols [ 60 , 61 ]. This may be of particular concern if non-radiological data such as chatbots, phone information, and web informatics are used to train AI [ 62 , 63 ].…”

Symptoms associated with a COVID-19 infection in the general population of Vienna

“…The aim was to offer, in addition to the non-emergency medical health line “1450”, a fast to use, always available, and accurate digital channel, available via https://coronavirus.wien.gv.at/site/symptomchecker/. Fonds Soziales Wien (Vienna Social Fund) and the company Symptoma developed the chatbot based on database, artificial intelligence, and algorithms of Symptoma [3]–[5] together. During the chatbot conversation, the user is answering a series of 13 yes/no questions about symptoms.…”

“…The Vienna Social Fund (FSW), the Public Health Services of the City of Vienna (MA15) and the company Symptoma mutually developed the chatbot based on the database, artificial intelligence, and algorithms of Symptoma [3], [6], [7]. During the chatbot conversation, the user is answering a series of 13 yes/no questions about symptoms.…”

“…screening the population and rapidly identifying cases). Symptom frequencies are used in applications including triage recommendation [1] and COVID-19 diagnostics [2] [3]. However, the reported symptom frequencies vary considerably across studies [1].…”

Machine Learning in Healthcare Communication

“…Symptoma allows free text input in 36 languages. Combined with the result and accessibility give Symptoma the potential technology to fight against COVID-19 [91]. Chatbots played a crucial role in combating COVID-19 ( Figure 2).…”