id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-319436-mlitd45q	Brinati, D.	Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: a Feasibility Study	2020-04-25		.txt	text/plain	4603	237	51	Amplification of viral RNA by (real time) reverse transcription polymerase chain reaction (rRT-PCR) is the current gold standard test for confirmation of infection, although it presents known shortcomings: long turnaround times (3-4 hours to generate results), potential shortage of reagents, false-negative rates as large as 15-20%, the need for certified laboratories, expensive equipment and trained personnel. Material and methods We developed two machine learning classification models using hematochemical values from routine blood exams (namely: white blood cells counts, and the platelets, CRP, AST, ALT, GGT, ALP, LDH plasma levels) drawn from 279 patients who, after being admitted to the San Raffaele Hospital (Milan, Italy) emergency-room with COVID-19 symptoms, were screened with the rRT-PCR test performed on respiratory tract specimens. The best performing model, i.e. the Random Forest classifier, trained on dataset B, achieved the following results on the test/validation set: accuracy = 82% , sensitivity = 92%, PPV = 83%, specificity = 65%, AUC = 84%.	./cache/cord-319436-mlitd45q.txt	./txt/cord-319436-mlitd45q.txt