Hassan Hijry, Richard Olawoyin, William Edwards, Gary C. McDonald, D. Debnath, Y. Al-Hejri
{"title":"Predicting Average Wait-Time of COVID-19 Test Results and Efficacy Using Machine Learning Algorithms","authors":"Hassan Hijry, Richard Olawoyin, William Edwards, Gary C. McDonald, D. Debnath, Y. Al-Hejri","doi":"10.46254/j.ieom.20210202","DOIUrl":null,"url":null,"abstract":"Due to the rising number of confirmed positive tests, the global impact of COVID-19 continues to grow. This can be attributed to the long wait times patients face to receive COVID-19 test results. During these lengthy waiting periods, people become anxious, especially those who are not experiencing early COVID-19 symptoms. This study aimed to develop models that predict waiting times for COVID-19 test results based on different factors such as testing facility, result interpretation, and date of test. Several machine learning algorithms were used to predict average waiting times for COVID-19 test results and to find the most accurate model. These algorithms include neural network, support vector regression, K-nearest neighbor regression, and more. COVID-19 test result waiting times were predicted for 54,730 patients recorded during the pandemic across 171 hospitals and 14 labs. To examine and evaluate the model’s accuracy, different measurements were applied such as root mean squared and R-Squared. Among the eight proposed models, the results showed that decision tree regression performed the best for predicting COVID-19 test results waiting times. The proposed models could be used to prioritize testing for COVID-19 and provide decision makers with the proper prediction tools to prepare against possible threats and consequences of future COVID-19 waves.","PeriodicalId":268888,"journal":{"name":"International Journal of Industrial Engineering and Operations Management","volume":"70 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Industrial Engineering and Operations Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.46254/j.ieom.20210202","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Due to the rising number of confirmed positive tests, the global impact of COVID-19 continues to grow. This can be attributed to the long wait times patients face to receive COVID-19 test results. During these lengthy waiting periods, people become anxious, especially those who are not experiencing early COVID-19 symptoms. This study aimed to develop models that predict waiting times for COVID-19 test results based on different factors such as testing facility, result interpretation, and date of test. Several machine learning algorithms were used to predict average waiting times for COVID-19 test results and to find the most accurate model. These algorithms include neural network, support vector regression, K-nearest neighbor regression, and more. COVID-19 test result waiting times were predicted for 54,730 patients recorded during the pandemic across 171 hospitals and 14 labs. To examine and evaluate the model’s accuracy, different measurements were applied such as root mean squared and R-Squared. Among the eight proposed models, the results showed that decision tree regression performed the best for predicting COVID-19 test results waiting times. The proposed models could be used to prioritize testing for COVID-19 and provide decision makers with the proper prediction tools to prepare against possible threats and consequences of future COVID-19 waves.