Machine Learning Models for the Prediction the Necessity of Resorting to ICU of COVID-19 Patients

Abstract

The world is currently facing many unrests and challenges due to the emergence of the COVID-19 Epidemic. The management of medical resources is considered one of the most important challenges posed by the emergence of this epidemic. The intensive care unit (ICU) plays an important role in saving the life of a COVID-19 patient, and therefore work has been done in this research to find models to predict the patient's need to enter ICU or not. The prediction models depend on Machine Learning (ML). Three models will be built to predict the state at which the patient needs to enter the ICU or not. The proposed predictor models based on three types of Supervised machine learning Naive Bayes, K -nearest neighbor (K-NN), and Support Vector Machine (SVM) according to the scarce datasets. Predictor model trained based on Extracted features from patients' X-ray images.

Comparison of Machine Learning Tools for the Prediction of ICU Admission in COVID-19 Hospitalized Patients

“…In addition, the critical patients at admission time were discarded from the analysis. Thus, if validated, these features could be applied for predicting the Many studies have focused on determining the key risk factors for ICU admission (8,9,11,13,24,25). The ten top clinical variables predicting ICU risk in reviewed studies encompassed age (older age), body temperature (high), oxygen saturation (decreased), neutrophil count and lymphocyte count (raised), C-reactive protein (elevated), D-dimer (increased), ALT and/or AST (augmented), LDH (elevated), loss of consciousness, and hypertension/cardiovascular diseases.…”

“…Ac-cordingly, predicting the individual disease courses and outcomes is essential for triaging patients, customized care service provision, utilizing life-saving resources in the best possible way, and directing them toward vulnerable and at-risk sub-groups deteriorating to critical COVID-19. Furthermore, many problems resulting from the shortage of hospital resources can be overcome by predicting the risk of patient deterioration, determining the length of stay, using hospital resources efficiently, and managing bed turnover (9,10).…”

“…Innovative approaches for the early identification and triaging of patients at the time of admission will be greatly beneficial and effective in estimating which patients are at the high risk of clinical deterioration and have poor outcomes requiring ICU admission (8,9). In such conditions, the design and implementation of clinical decision support systems equipped with machine learning (ML)-based prediction models will be critical for the optimal use of limited hospital resources and supporting clinical decisions.…”

“…In the previous researches, a large number of ML algorithms were trained for the prediction of COVID-19 disease progression, patient condition deterioration (9, 10), ICU hospitalization (8,9,(11)(12)(13), and death (8,11,(14)(15)(16)(17)(18)(19).…”

Predicting Student Program Completion Using Naïve Bayes Classification Algorithm

“…To have the most relevant classifier and an effective and efficient model, the researchers utilized the Naï ve Bayes Classification Algorithm, a simple technique for constructing classifiers or models based on Bayes Theorem of conditional probability and strong independence assumptions. Many researchers have previously used it and observed that among other classification approaches, Naï ve Bayes performs well [2,3,4,5,6,7].…”