Author: Alistair Martin; Jama Nateqi; Stefanie Gruarin; Nicolas Munsch; Isselmou Abdarahmane; Bernhard Knapp
Title: An artificial intelligence-based first-line defence against COVID-19: digitally screening citizens for risks via a chatbot Document date: 2020_3_26
ID: 52nw9gxq_21
Snippet: The copyright holder for this preprint (which was not peer-reviewed) is the . https://doi.org/10.1101/2020.03.25.008805 doi: bioRxiv preprint On the left, we show the performance of Symptoma, highlighted in blue, against alternatives, all of which are constrained to consider only three alternative diagnoses (the common cold, influenza, and hay fever). We also give Symptoma's accuracy on this set of case reports when unconstrained (labelled as top.....
Document: The copyright holder for this preprint (which was not peer-reviewed) is the . https://doi.org/10.1101/2020.03.25.008805 doi: bioRxiv preprint On the left, we show the performance of Symptoma, highlighted in blue, against alternatives, all of which are constrained to consider only three alternative diagnoses (the common cold, influenza, and hay fever). We also give Symptoma's accuracy on this set of case reports when unconstrained (labelled as top30). On the right, we breakdown the predictions by Symptoma on the COVID-19 cases. Missing points indicate that the corresponding disease was considered so unlikely that it was not returned by the search.
Search related documents:
Co phrase search for related documents- case set and common cold: 1
- case set and Symptoma accuracy: 1, 2
- common cold and hay fever: 1, 2, 3, 4
- common cold and hay fever influenza common cold: 1, 2, 3, 4
- common cold and Symptoma performance: 1
- hay fever and Symptoma performance: 1
- hay fever influenza common cold and Symptoma performance: 1
Co phrase search for related documents, hyperlinks ordered by date