Resumen

KUMAR, Prabhat  y  SURESH, Selvam. Comprehensive Performance Analysis on Classical Machine Learning and Deep Learning Methods for Predicting the COVID-19 Infections. Comp. y Sist. [online]. 2022, vol.26, n.3, pp.1119-1135.  Epub 02-Dic-2022. ISSN 2007-9737.  https://doi.org/10.13053/cys-26-3-3782.

The COVID-19 (coronavirus disease) has been declared a pandemic throughout the world by the WHO (World Health Organization). The number of active COVID-19 cases is increasing day by day and clinical laboratory findings consume more time while interpreting the COVID-19 infected result. There are limited treatment facilities and proper guidelines for reducing infection rates. To overcome these limitations, the requirement of clinical decision support systems embedded with prediction algorithms is raised. In our study, we have architected the clinical prediction system using classical machine learning, deep learning algorithms, and experimental laboratory data. Our model estimated which patients were likely infected with COVID-19 disease. The prediction performances of our models are evaluated based on the accuracy score. The experimental dataset has been provided by Hospital Israelita Albert Einstein at Sao Paulo, Brazil, which included the records of 600 patients from 18 laboratory findings with 10% COVID-19 disease infected patients. Our model has been validated with a train-test split approach, 10-fold cross-validation, and AUC-ROC curve score. The experimental results show that the infected patients with COVID-19 disease are identified at an accuracy of 91.88% through the deep learning method (Convolutional Neural Network (CNN)) and 89.79 % through classical machine learning (Logistic Regression) respectively. This high accuracy is evidence that our prediction model could be readily used for predicting the COVID-19 infections and assisting the health experts in better diagnosis and clinical studies.

Palabras llave : COVID-19; coronavirus disease; WHO; machine learning; deep learning; decision support system.

        · texto en Inglés     · Inglés ( pdf )