Identification of high-risk COVID-19 patients using machine learning

Abstract

The current COVID-19 public health crisis, caused by SARSCoV- 2 (severe acute respiratory syndrome coronavirus 2), has produced a devastating toll both in terms of human life loss and economic disruption. In this paper we present a machine-learning algorithm capable of identifying whether a given patient (actually infected or suspected to be infected) is more likely to survive than to die, or vice-versa. We train this algorithm with historical data, including medical history, demographic data, as well as COVID-19-related information. This is extracted from a database of confirmed and suspected COVID-19 infections in Mexico, constituting the official COVID-19 data compiled and made publicly available by the Mexican Federal Government. We demonstrate that the proposed method can detect high-risk patients with high accuracy, in each of four identified treatment stages, thus improving hospital capacity planning and timely treatment. Furthermore, we show that our method can be extended to provide optimal estimators for hypothesis-testing techniques commonly-used in biological and medical statistics. We believe that our work could be of use in the context of the current pandemic in assisting medical professionals with real-time assessments so as to determine health care priorities.

Determination of COVID-19 Patients Using Machine Learning Algorithms

“…The dataset is obtained from the Israeli government website and is accessible worldwide, https://data.gov.il/dataset/covid-19/resource/ d337959a-020a-4ed3-84f7-fca182292308. Such type of datasets are also used by several other research publications [6]. Although the website is constantly updated with the latest data, we used a dataset from 15/12/2020 till 21/01/2021.…”

“…Since the vaccines are not yet mature, other techniques like early detection of the disease can be effective to decrease the spread. Artificial intelligence (AI) approaches, including machine learning approaches [2] and deep learning algorithms [3], play an essential role in prediction for this disease like outbreak prediction [4,5], high-risk patients' identification [6], COVID-19 analysis with clinical features [7], spread probability analysis [8], ways to combat this disease [9], and death risk in patients. The recent advancement in AI and data mining approaches to solve medical problems emphasize that they can improve the epidemic situation [10].…”

COVID-19 impact on socio-economic and health interventions : A gaps and peaks analysis using clustering approach

“…The impact of Artificial Intelligence (AI) and Machine Learning (ML) in developing predictive models is seen across all the fields of scientific discoveries and COVID-19 research is no different. A large number of predictive models have used ML to study the propagation, prevalence as well as control against COVID-19 pandemic [37][38][39][40][41][42][43][44][45] which shows that these approaches can extensively contribute in identifying the risk of infections, screening and diagnostics, speed up drug discovery/development, predicting risk of new pandemics etc. An effective method to understand the deeper insights of what is going to happen next with this pandemic is to pursue the past data in details.…”

COVID-19 impact on Socio-economic and Health Interventions: A Gaps and Peaks analysis using Clustering Approach

“…The impact of Artificial Intelligence (AI) and Machine Learning (ML) in developing predictive models is seen across all the fields of scientific discoveries and COVID-19 research is no different. A large number of predictive models have used ML to study the propagation, prevalence as well as control against COVID-19 pandemic [37][38][39][40][41][42][43][44][45] which shows that these approaches can extensively contribute in identifying the risk of infections, screening and diagnostics, speed up drug discovery/development, predicting risk of new pandemics etc. An effective method to understand the deeper insights of what is going to happen next with this pandemic is to pursue the past data in details.…”