id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-123970-qikmhoo4	Bao, Forrest Sheng	Triaging moderate COVID-19 and other viral pneumonias from routine blood tests	2020-05-13		.txt	text/plain	7144	389	62	Trained on blood data from 208 moderate COVID-19 subjects and 86 subjects with non-COVID-19 moderate viral pneumonia, the best result is obtained in an SVM-based classifier with an accuracy of 84%, a sensitivity of 88%, a specificity of 80%, and a precision of 92%. The 3 groups of subjects thus form 3 binary classification tasks: 1 Medical workers need help the most from the primary task of differentiating moderate COVID-19 cases from 1 The numbers are not 118 vs 208 because 5 samples have too many missing values in additional features in Table 2 . We pick two empirically effective and robust families of classifiers, random forests (RFs) and support vector machines (SVMs), as representatives to study the general feasibility and effectiveness of using ML to make use of routine blood tests for COVID-19 triage.	./cache/cord-123970-qikmhoo4.txt	./txt/cord-123970-qikmhoo4.txt