Romanian Journal of Information Science and Technology (ROMJIST)

An open – access publication

  |  HOME  |   GENERAL INFORMATION  |   ROMJIST ON-LINE  |  KEY INFORMATION FOR AUTHORS  |   COMMITTEES  |  

ROMJIST is a publication of Romanian Academy,
Section for Information Science and Technology

Editor – in – Chief:
Radu-Emil Precup

Honorary Co-Editors-in-Chief:
Horia-Nicolai Teodorescu
Gheorghe Stefan

Secretariate (office):
Adriana Apostol
Adress for correspondence: romjist@nano-link.net (after 1st of January, 2019)

Editing of the printed version: Mihaela Marian (Publishing House of the Romanian Academy, Bucharest)

Technical editor
of the on-line version:
Lucian Milea (University POLITEHNICA of Bucharest)

Sponsor:
• National Institute for R & D
in Microtechnologies
(IMT Bucharest), www.imt.ro

ROMJIST Volume 25, No. 3-4, 2022, pp. 290-302
 

Selçuk Öğütcü, Melih İnal, Cantekin Çelikhası, Uğur Yıldız, Nurettin Özgür Doğan, Murat Pekdemir
Early Detection of Mortality in COVID-19 Patients Through Laboratory Findings with Factor Analysis and Artificial Neural Networks

ABSTRACT: In this study, some biochemical findings of patients who applied to Kocaeli University Faculty of Medicine Emergency Service with suspicion of COVID-19 were examined. The common characteristics of the cases regarding mortality status were analyzed via factor analysis (FA). Following the FA, blood parameters related to the severity of the cases were determined. Finally, a multi-layered artificial neural network (ANN) was trained with these parameters. The study was introduced as a new method that helps early detection of severe cases and determination of non-risk group vaccination priority. Thus, the main contribution has been seen in creating a decision-support system to start advanced medical support as soon as possible. The data set consists of 105 patients with 19 different input parameters. After FA, 7 parameters were found relevant to one-month mortality. These are HB, AST, BUN, LDH, pH, HCO3 and LAC. The chi-square value was 1252.9552, the p value for the significance level of 0.05 was close to zero (7.3696x10-156). An ANN was accurately trained based on this subset of the data. The most successful model of ANN’s training and testing errors as a root sum squared estimate of error (RSSE) are 0.1958 and 0.2402, respectively. This ANN model can be queried for patient data with determined parameters.

KEYWORDS: Artificial neural networks; COVID-19; factor analysis; triage

Read full text (pdf)






  |  HOME  |   GENERAL INFORMATION  |   ROMJIST ON-LINE  |  KEY INFORMATION FOR AUTHORS  |   COMMITTEES  |