id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-257555-tmuvbq1k	Munsch, N.	A benchmark of online COVID-19 symptom checkers	2020-05-26		.txt	text/plain	3637	197	57	Results We find that the number of correctly assessed cases varies considerably between different symptom checkers, with Symptoma (F1=0.92, MCC=0.85) showing the overall best performance followed by Infermedica (F1=0.80, MCC=0.61). In the following, we present a study evaluating 10 different COVID-19 online symptom checkers using 50 COVID-19 cases extracted from the literature and 410 non-COVID-19 control cases of patients with other diseases. Under these constraints and when COVID-19 positive is defined by high risk only, Symptoma still significantly outperforms Apple and Cleveland Clinic, while performing statistically similar to six of the remaining symptom checkers (upper panel of Fig 2B ) . Full table of sensitivity, specificity, accuracy, F1 score and MCC for Symptoma constrained by each symptom checker (COVID-19 positive defined by "medium risk" or "high risk" for non binary symptom checkers) 	./cache/cord-257555-tmuvbq1k.txt	./txt/cord-257555-tmuvbq1k.txt