Hemogram Data as a Tool for Decision-making in COVID-19 Management: Applications to Resource Scarcity Scenarios

TL;DR

This study develops a Naive-Bayes machine learning model using hemogram data to predict COVID-19 qRT-PCR results, aiding decision-making during resource shortages and testing limitations.

Contribution

It introduces a novel, adaptable model that leverages common blood test data to predict COVID-19 status, optimizing resource allocation in scarcity scenarios.

Findings

High accuracy, sensitivity, and specificity in predictions

Effective management of testing shortages and personnel allocation

Model adaptability to different scarcity contexts

Abstract

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. Methods: A Naive-Bayes model for machine learning is proposed for handling different scarcity scenarios, including managing symptomatic essential workforce and absence of diagnostic tests. Hemogram result data was used to predict qRT-PCR results in situations where the latter was not performed, or results are not yet available. Adjusts in assumed prior 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. Data assessment can be performed in an individual or simultaneous basis, according to desired outcome. Based on hemogram data and background scarcity context, resource distribution is significantly optimized when model-based patient selection is observed, compared to random choice. The model can help manage testing deficiency and other critical circumstances. 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.