Triage of Patients with COVID-19: Using Ensemble Learning Method for Risk Factor Analysis and Death Prediction

Neda Sadat; Sharareh R. Niakan Kalhori; Shahrzad Darvishi; Jamileh Kiani; Farhad Abbasi; Batool Amiri; Erfan Javanmardi; Safiyeh Daneshi

doi:10.5812/koomesh-150060

Koomesh

Journal of Semnan University of Medical Sciences

Home

Current Issue Archive In Press Accepted Manuscripts Search

Instructions

Journal Information Editors & Boards Indexing and Listing Sources Journal Metrics Open Peer Review (OPR)Publication Ethics and Publication Malpractice Statement Support Contact Us Reviewer and AE Registration Form

APC

Authors Guide Submit Manuscript

Image Credit:Koomesh

https://doi.org/10.69107/koomesh-150060

Triage of Patients with COVID-19: Using Ensemble Learning Method for Risk Factor Analysis and Death Prediction

Author(s):

Neda Sadat¹,

Sharareh R. Niakan Kalhori^{2, 3,*},

Shahrzad Darvishi⁴,

Jamileh Kiani¹,

Farhad Abbasi⁵,

Batool Amiri¹,

Erfan Javanmardi

¹,

Safiyeh Daneshi

¹

1Clinical Research Development Unit, Persian Gulf Martyrs Hospital, Bushehr University of Medical Sciences, Bushehr, Iran

2Department of Health Information Management, Faculty of Paramedicine, Tehran University of Medical Sciences, Tehran, Iran

3PLRI Informatics Research Institute, Medical School Hannover, Technical University of Braunschweig, Braunschweig, Germany

4Imam Khomeini Hospital, Bushehr University of Medical Sciences, Bushehr, Iran

5Department of Infectious Diseases, Faculty of Medicine, Bushehr University of Medical Sciences, Bushehr, Iran

Koomesh:Vol. 26, issue 1; e150060

Published online:Oct 12, 2024

Article type:Research Article

How to Cite:Neda SadatSharareh R. Niakan KalhoriShahrzad DarvishiJamileh KianiFarhad AbbasiBatool AmiriErfan JavanmardiSafiyeh Daneshiet al.Triage of Patients with COVID-19: Using Ensemble Learning Method for Risk Factor Analysis and Death Prediction.koomesh.26(1):e150060.https://doi.org/10.69107/koomesh-150060.

Abstract

Background: Early identification of high-risk patients with COVID-19 using non-laboratory data at the time of admission may help the effective use of limited healthcare resources and improve clinical decision-making which reduces cost and time, and consequently the death of patients.

Objectives: This study aims to provide an intelligent approach to triaging COVID-19 patients by analyzing effective risk factors and predicting the risk of death due to COVID-19 using an ensemble learning method.

Methods: This is a descriptive-applied study that was conducted in 2021. Non-laboratory data were used during the admission of 4558 confirmed patients with COVID-19 referred to the Shohaday-e-Khalij-e-Fars Hospital in Bushehr registered in the medical care information system. After data preprocessing, the risk factors affecting the death were identified and ranked in importance. The ensemble learning (voting) method was used to develop the death prediction model, and the confusion matrix criteria evaluated its performance.

Results: From a total of 5433 patient records, the data of 4558 cases were included in the study, of which 2222 (45.5%) were women and 2663 (64.5%) were men. The average age of the patients was 47.6. Out of all the investigated factors, 17 characteristics were identified as effective in predicting the death of patients, and their ranking indicated that the first six factors for predicting the death of patients are state of blood oxygen, age, state of consciousness, fever, cough, and body pain, respectively. The proposed model estimated the risk of death with an accuracy of 85%, sensitivity of 85%, specificity of 0.85%, and AUROC of 0.91.

Conclusions: The results of the study provide a low-cost, fast, and innovative solution for the early identification of patients with COVID-19 at risk of death to triage them more effectively, which can be used by the managers of healthcare systems to manage resources by continuously updating new data and providing appropriate treatments for high-risk patients.

Keywords

COVID-19

Machine Learning

Risk Factors

Fulltext

The full text is available in the PDF file.

comments

Crossmark

Checking

Share on

Comments

Number of Comments:0

Cited by

CrossRef 0

Metrics

Get Permission (article level)

Purchasing Reprints

Copyright Clearance Center (CCC) handles bulk orders for article reprints for Brieflands. To place an order for reprints, please click here ( https://www.copyright.com/landing/reprintsinquiryform/ ). Clicking this link will bring you to a CCC request form where you can provide the details of your order. Once complete, please click the ‘Submit Request’ button and CCC’s Reprints Services team will generate a quote for your review.

Search Relations

Author(s):

Neda Sadat:[PubMed][Scholar]
Sharareh R. Niakan Kalhori:[PubMed][Scholar]
Shahrzad Darvishi:[PubMed][Scholar]
Jamileh Kiani:[PubMed][Scholar]
Farhad Abbasi:[PubMed][Scholar]
Batool Amiri:[PubMed][Scholar]
Erfan Javanmardi:[PubMed][Scholar]
Safiyeh Daneshi:[PubMed][Scholar]