id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-355102-jcyq8qve	Avila, Eduardo	Hemogram data as a tool for decision-making in COVID-19 management: applications to resource scarcity scenarios	2020-06-29		.txt	text/plain	4768	242	39	PURPOSE: This work describes a machine learning model derived from hemogram exam data performed in symptomatic patients and how they can be used to predict qRT-PCR test results. METHODS: Hemogram exams data from 510 symptomatic patients (73 positives and 437 negatives) were used to model and predict qRT-PCR results through Naïve-Bayes algorithms. In order to evaluate the adequacy and generalization power of the proposed model, as well as its tolerance to handle samples containing missing data (i.e., at least one variable with no informed values), an additional set of 92 samples (10 positives for COVID-19 and 82 negatives) was obtained from the patient database. When no clinical or medical data is available, or when decisions regarding resource management involving multiple symptomatic patients are necessary, the model can be used in multiple individuals simultaneously, aiming to identify those with higher probabilities of presenting positive qRT-PCR results.	./cache/cord-355102-jcyq8qve.txt	./txt/cord-355102-jcyq8qve.txt