Detection of COVID-19 Patients Using Machine Learning Techniques: A Nationwide Chilean Study

被引:5
作者
Ormeno, Pablo [1 ]
Marquez, Gaston [2 ]
Guerrero-Nancuante, Camilo [3 ]
Taramasco, Carla [4 ]
机构
[1] Univ Vina del Mar, Escuela Ingn & Negocios, Vina Del Mar 2520000, Chile
[2] Univ Tecn Federico Santa Maria, Dept Elect & Informat, Millennium Nucleus Sociomed, Concepcion 4030000, Chile
[3] Univ Valparaiso, Escuela Enfermeria, Valparaiso 2500000, Chile
[4] Univ Andres Bello, Fac Ingn, Millennium Nucleus Sociomed, Vina Del Mar 2520000, Chile
关键词
Epivigila; machine learning; symptoms; comorbidities;
D O I
10.3390/ijerph19138058
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Epivigila is a Chilean integrated epidemiological surveillance system with more than 17,000,000 Chilean patient records, making it an essential and unique source of information for the quantitative and qualitative analysis of the COVID-19 pandemic in Chile. Nevertheless, given the extensive volume of data controlled by Epivigila, it is difficult for health professionals to classify vast volumes of data to determine which symptoms and comorbidities are related to infected patients. This paper aims to compare machine learning techniques (such as support-vector machine, decision tree and random forest techniques) to determine whether a patient has COVID-19 or not based on the symptoms and comorbidities reported by Epivigila. From the group of patients with COVID-19, we selected a sample of 10% confirmed patients to execute and evaluate the techniques. We used precision, recall, accuracy, F-1-score, and AUC to compare the techniques. The results suggest that the support-vector machine performs better than decision tree and random forest regarding the recall, accuracy, F-1-score, and AUC. Machine learning techniques help process and classify large volumes of data more efficiently and effectively, speeding up healthcare decision making.
引用
收藏
页数:15
相关论文
共 26 条
  • [1] A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients
    Ahamad, Md Martuza
    Aktar, Sakifa
    Rashed-Al-Mahfuz, Md
    Uddin, Shahadat
    Lio, Pietro
    Xu, Haoming
    Summers, Matthew A.
    Quinn, Julian M. W.
    Moni, Mohammad Ali
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2020, 160
  • [2] A Novel Bayesian Optimization-Based Machine Learning Framework for COVID-19 Detection From Inpatient Facility Data
    Awal, Md. Abdul
    Masud, Mehedi
    Hossain, Md. Shahadat
    Bulbul, Abdullah Al-Mamun
    Mahmud, S. M. Hasan
    Bairagi, Anupam Kumar
    [J]. IEEE ACCESS, 2021, 9 : 10263 - 10281
  • [3] Assessing countries' performances against COVID-19 via WSIDEA and machine learning algorithms
    Aydin, Nezir
    Yurdakul, Gokhan
    [J]. APPLIED SOFT COMPUTING, 2020, 97 (97)
  • [4] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32
  • [5] Chilean Ministry of Health, EPIDEMIOLOGICAL SURV
  • [6] Epidemiological and clinical characteristics of the COVID-19 epidemic in Brazil
    de Souza, William Marciel
    Buss, Lewis Fletcher
    Candido, Darlan da Silva
    Carrera, Jean-Paul
    Li, Sabrina
    Zarebski, Alexander E.
    Pereira, Rafael Henrique Moraes
    Prete, Carlos A., Jr.
    de Souza-Santos, Andreza Aruska
    Parag, Kris V.
    Belotti, Maria Carolina T. D.
    Vincenti-Gonzalez, Maria F.
    Messina, Janey
    da Silva Sales, Flavia Cristina
    Andrade, Pamela dos Santos
    Nascimento, Vitor Heloiz
    Ghilardi, Fabio
    Abade, Leandro
    Gutierrez, Bernardo
    Kraemer, Moritz U. G.
    Braga, Carlos K. V.
    Aguiar, Renato Santana
    Alexander, Neal
    Mayaud, Philippe
    Brady, Oliver J.
    Marcilio, Izabel
    Gouveia, Nelson
    Li, Guangdi
    Tami, Adriana
    de Oliveira, Silvano Barbosa
    Porto, Victor Bertollo Gomes
    Ganem, Fabiana
    de Almeida, Walquiria Aparecida Ferreira
    Fantinato, Francieli Fontana Sutile Tardetti
    Macario, Eduardo Marques
    de Oliveira, Wanderson Kleber
    Nogueira, Mauricio L.
    Pybus, Oliver G.
    Wu, Chieh-Hsi
    Croda, Julio
    Sabino, Ester C.
    Faria, Nuno Rodrigues
    [J]. NATURE HUMAN BEHAVIOUR, 2020, 4 (08) : 856 - +
  • [7] Parameter Selection for Linear Support Vector Regression
    Hsia, Jui-Yang
    Lin, Chih-Jen
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (12) : 5639 - 5644
  • [8] Modeling Predictive Age-Dependent and Age-Independent Symptoms and Comorbidities of Patients Seeking Treatment for COVID-19: Model Development and Validation Study
    Huang, Yingxiang
    Radenkovic, Dina
    Perez, Kevin
    Nadeau, Kari
    Verdin, Eric
    Furman, David
    [J]. JOURNAL OF MEDICAL INTERNET RESEARCH, 2021, 23 (03)
  • [9] Predictive symptoms and comorbidities for severe COVID-19 and intensive care unit admission: a systematic review and meta-analysis
    Jain, Vageesh
    Yuan, Jin-Min
    [J]. INTERNATIONAL JOURNAL OF PUBLIC HEALTH, 2020, 65 (05) : 533 - 546
  • [10] Kolbe L., 1990, HEALTH EDUC, P44, DOI 10.1080/00970050.1990.10614591