Hemogram data as a tool for decision-making in COVID-19 management: applications to resource scarcity scenarios

COVID-19 pandemics has challenged emergency response systems worldwide, with widespread reports of essential services breakdown and collapse of health care structure. A critical element involves essential workforce management since current protocols recommend release from duty for symptomatic indivi...

Full description

Saved in:
Bibliographic Details
Published in:PeerJ (San Francisco, CA) Vol. 8; p. e9482
Main Authors: Avila, Eduardo, Kahmann, Alessandro, Alho, Clarice, Dorn, Marcio
Format: Journal Article
Language:English
Published: United States PeerJ, Inc 29.06.2020
PeerJ Inc
Subjects:
Algorithms
Automation
Bayesian analysis
Choice learning
Classification
Coronaviruses
COVID-19
Data Mining and Machine Learning
Datasets
Decision making
Diagnosis
Disease
Health care
Hematology
Hemoglobin
Hemogram
Infectious Diseases
Learning algorithms
Machine learning
Medical personnel
Medical supplies
Methods
Naïve-Bayes
Pandemics
Patients
Public Health
Scarcity
Statistics
Workforce
COVID-19
Hemogram
Scarcity
Naïve-Bayes
Machine learning
ISSN:2167-8359, 2167-8359
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:COVID-19 pandemics has challenged emergency response systems worldwide, with widespread reports of essential services breakdown and collapse of health care structure. A critical element involves essential workforce management since current protocols recommend release from duty for symptomatic individuals, including essential personnel. Testing capacity is also problematic in several countries, where diagnosis demand outnumbers available local testing capacity. 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. 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. Different scarcity scenarios were simulated, including symptomatic essential workforce management and absence of diagnostic tests. Adjusts in assumed probabilities allow fine-tuning of the model, according to actual prediction context. Proposed models can predict COVID-19 qRT-PCR results in symptomatic individuals with high accuracy, sensitivity and specificity, yielding a 100% sensitivity and 22.6% specificity with a of 0.9999; 76.7% for both sensitivity and specificity with a of 0.2933; and 0% sensitivity and 100% specificity with a of 0.001. Regarding background scarcity context, resources allocation can be significantly improved when model-based patient selection is observed, compared to random choice. Machine learning models can be derived from widely available, quick, and inexpensive exam data in order to predict qRT-PCR results used in COVID-19 diagnosis. These models can be used to assist strategic decision-making in resource scarcity scenarios, including personnel shortage, lack of medical resources, and testing insufficiency.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2167-8359
2167-8359
DOI:10.7717/peerj.9482