{"id":20620,"date":"2024-10-04T16:45:35","date_gmt":"2024-10-04T20:45:35","guid":{"rendered":"https:\/\/www.ices.on.ca\/?post_type=journal_article&p=20620"},"modified":"2024-11-01T16:53:54","modified_gmt":"2024-11-01T20:53:54","slug":"comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction","status":"publish","type":"journal_article","link":"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/","title":{"rendered":"Comparing AI\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction"},"content":{"rendered":"

Background<\/strong> \u2014\u00a0Research comparing artificial intelligence and machine learning (AI\/ML) methods with classical statistical methods applied to large population health databases is limited.<\/p>\n

Objectives<\/strong> \u2014\u00a0This retrospective cohort study aimed to compare the predictive performance of AI\/ML algorithms against conventional multivariate logistic regression models using linked health administrative data.<\/p>\n

Methods<\/strong> \u2014\u00a0Using Ontario’s population health databases, we created a cohort of residents of the city of Ottawa, Ontario, who underwent a PCR test for COVID-19 between March 10, 2020, and May 13, 2021. Using demographic, socio-economic and health data (including COVID-19 PCR test results and available, symptom data), we developed predictive models for the purpose of COVID-19 case identification using the following approaches: classical multivariate logistic regression (LR); deep neural network (DNN); random forest (RF); and gradient boosting trees (GBT). Model performance comparisons were made using the area under the curve (AUC) swarm plot for 10-fold cross-validation.<\/p>\n

Results<\/strong> \u2014 The cohort consisted of n = 351,248 Ottawa residents tested for COVID-19 during the study period. Among whom, a total of n = 883,879 unique COVID-19 tests were performed (2.6 % positive test results). Inclusion of COVID-19 symptoms data in the analysis improved model performance and variable predictive value across all tested models (p < 0.0001), with the 10-fold cross-validation AUC increasing to near or over 0.7 in all models when symptoms data were included. In various pairwise comparisons, the GBT method had the highest predictive ability (AUC = 0.796 \u00b1 0.017), significantly outperforming multivariate logistic regression and the other AI\/ML approaches.<\/p>\n

Conclusions<\/strong> \u2014 Conventional multivariate regression-based models are better than some and worse than other machine learning algorithms to provide good predictive accuracy in a moderate dataset with a reasonable number of features. However, whenever possible, the AI\/ML GBT approach should be considered.<\/p>\n","protected":false},"excerpt":{"rendered":"

Background \u2014\u00a0Research comparing artificial intelligence and machine learning (AI\/ML) methods with classical statistical methods applied to large population health databases is limited. Objectives \u2014\u00a0This retrospective cohort study aimed to compare the predictive performance of AI\/ML algorithms against conventional multivariate logistic regression models using linked health administrative data. Methods \u2014\u00a0Using Ontario’s population health databases, we created […]<\/p>\n","protected":false},"template":"","migration-helper-automated":[],"migration-manual":[],"topic":[59,39],"migration-helper-qa-sample-set":[],"class_list":["post-20620","journal_article","type-journal_article","status-publish","hentry","topic-data-science","topic-infectious-diseases"],"acf":{"citation":"Bjerre LM, Peixoto C, Alkurd R, Talarico R, Abielmona R. Glob Epidemiol<\/em>. 2024; 8:100168.","source_url":"https:\/\/doi.org\/10.1016\/j.gloepi.2024.100168","ices_scientist":[1163,21984],"site":[6733],"research_program":[6746],"news_release":"","journal_article":"","atlas":"","research_report":"","infographic":"","video":"","downloads":null,"links":null,"sitecore_item_id":"","sitecore_item_name":"","sitecore_field_values":"","previous_url":""},"yoast_head":"\nICES | Comparing AI\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction<\/title>\n<meta name=\"description\" content=\"Background \u2014\u00a0Research comparing artificial intelligence and machine learning (AI\/ML) methods with classical statistical methods applied to large\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ICES | Comparing AI\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction\" \/>\n<meta property=\"og:description\" content=\"Background \u2014\u00a0Research comparing artificial intelligence and machine learning (AI\/ML) methods with classical statistical methods applied to large\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/\" \/>\n<meta property=\"og:site_name\" content=\"ICES\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/ICESOntario\/\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-01T20:53:54+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.ices.on.ca\/wp-content\/uploads\/2024\/11\/ic-es-data-discovery-better-health-logo.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"675\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/publications\\\/journal-articles\\\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\\\/\",\"url\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/publications\\\/journal-articles\\\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\\\/\",\"name\":\"ICES | Comparing AI\\\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/#website\"},\"datePublished\":\"2024-10-04T20:45:35+00:00\",\"dateModified\":\"2024-11-01T20:53:54+00:00\",\"description\":\"Background \u2014\u00a0Research comparing artificial intelligence and machine learning (AI\\\/ML) methods with classical statistical methods applied to large\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/publications\\\/journal-articles\\\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/publications\\\/journal-articles\\\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/publications\\\/journal-articles\\\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Journal Articles\",\"item\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/publications\\\/journal-articles\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Comparing AI\\\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/#website\",\"url\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/\",\"name\":\"ICES\",\"description\":\"POPULATION-BASED HEALTH RESEARCH THAT MAKES A DIFFERENCE\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/#organization\"},\"alternateName\":\"Institute for Clinical Evaluative Sciences\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/#organization\",\"name\":\"ICES\",\"alternateName\":\"Institute for Clinical Evaluative Sciences\",\"url\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/www.ices.on.ca\\\/wp-content\\\/uploads\\\/2023\\\/04\\\/ices-logo.png\",\"contentUrl\":\"https:\\\/\\\/www.ices.on.ca\\\/wp-content\\\/uploads\\\/2023\\\/04\\\/ices-logo.png\",\"width\":\"676\",\"height\":\"618\",\"caption\":\"ICES\"},\"image\":{\"@id\":\"https:\\\/\\\/www.ices.on.ca\\\/fr\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/ICESOntario\\\/\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/ices-research-institute\\\/\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"ICES | Comparing AI\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction","description":"Background \u2014\u00a0Research comparing artificial intelligence and machine learning (AI\/ML) methods with classical statistical methods applied to large","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/","og_locale":"fr_FR","og_type":"article","og_title":"ICES | Comparing AI\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction","og_description":"Background \u2014\u00a0Research comparing artificial intelligence and machine learning (AI\/ML) methods with classical statistical methods applied to large","og_url":"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/","og_site_name":"ICES","article_publisher":"https:\/\/www.facebook.com\/ICESOntario\/","article_modified_time":"2024-11-01T20:53:54+00:00","og_image":[{"width":1200,"height":675,"url":"https:\/\/www.ices.on.ca\/wp-content\/uploads\/2024\/11\/ic-es-data-discovery-better-health-logo.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/","url":"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/","name":"ICES | Comparing AI\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction","isPartOf":{"@id":"https:\/\/www.ices.on.ca\/fr\/#website"},"datePublished":"2024-10-04T20:45:35+00:00","dateModified":"2024-11-01T20:53:54+00:00","description":"Background \u2014\u00a0Research comparing artificial intelligence and machine learning (AI\/ML) methods with classical statistical methods applied to large","breadcrumb":{"@id":"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/comparing-ai-ml-approaches-and-classical-regression-for-predictive-modeling-using-large-population-health-databases-applications-to-covid-19-case-prediction\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ices.on.ca\/fr\/"},{"@type":"ListItem","position":2,"name":"Journal Articles","item":"https:\/\/www.ices.on.ca\/fr\/publications\/journal-articles\/"},{"@type":"ListItem","position":3,"name":"Comparing AI\/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction"}]},{"@type":"WebSite","@id":"https:\/\/www.ices.on.ca\/fr\/#website","url":"https:\/\/www.ices.on.ca\/fr\/","name":"ICES","description":"POPULATION-BASED HEALTH RESEARCH THAT MAKES A DIFFERENCE","publisher":{"@id":"https:\/\/www.ices.on.ca\/fr\/#organization"},"alternateName":"Institute for Clinical Evaluative Sciences","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.ices.on.ca\/fr\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/www.ices.on.ca\/fr\/#organization","name":"ICES","alternateName":"Institute for Clinical Evaluative Sciences","url":"https:\/\/www.ices.on.ca\/fr\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/www.ices.on.ca\/fr\/#\/schema\/logo\/image\/","url":"https:\/\/www.ices.on.ca\/wp-content\/uploads\/2023\/04\/ices-logo.png","contentUrl":"https:\/\/www.ices.on.ca\/wp-content\/uploads\/2023\/04\/ices-logo.png","width":"676","height":"618","caption":"ICES"},"image":{"@id":"https:\/\/www.ices.on.ca\/fr\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/ICESOntario\/","https:\/\/www.linkedin.com\/company\/ices-research-institute\/"]}]}},"_links":{"self":[{"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/journal_article\/20620","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/journal_article"}],"about":[{"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/types\/journal_article"}],"acf:post":[{"embeddable":true,"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/research_program\/6746"},{"embeddable":true,"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/site\/6733"},{"embeddable":true,"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/ices_scientist\/21984"},{"embeddable":true,"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/ices_scientist\/1163"}],"wp:attachment":[{"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/media?parent=20620"}],"wp:term":[{"taxonomy":"migration-helper-automated","embeddable":true,"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/migration-helper-automated?post=20620"},{"taxonomy":"migration-manual","embeddable":true,"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/migration-manual?post=20620"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/topic?post=20620"},{"taxonomy":"migration-helper-qa-sample-set","embeddable":true,"href":"https:\/\/www.ices.on.ca\/fr\/wp-json\/wp\/v2\/migration-helper-qa-sample-set?post=20620"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}