{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T05:48:30Z","timestamp":1770270510626,"version":"3.49.0"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T00:00:00Z","timestamp":1568678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Objective<\/jats:title><jats:p>Emergency departments (EDs) are increasingly overcrowded. Forecasting patient visit volume is challenging. Reliable and accurate forecasting strategies may help improve resource allocation and mitigate the effects of overcrowding. Patterns related to weather, day of the week, season, and holidays have been previously used to forecast ED visits. Internet search activity has proven useful for predicting disease trends and offers a new opportunity to improve ED visit forecasting. This study tests whether Google search data and relevant statistical methods can improve the accuracy of ED volume forecasting compared with traditional data sources.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and Methods<\/jats:title><jats:p>Seven years of historical daily ED arrivals were collected from Boston Children\u2019s Hospital. We used data from the public school calendar, National Oceanic and Atmospheric Administration, and Google Trends. Multiple linear models using LASSO (least absolute shrinkage and selection operator) for variable selection were created. The models were trained on 5 years of data and out-of-sample accuracy was judged using multiple error metrics on the final 2 years.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>All data sources added complementary predictive power. Our baseline day-of-the-week model recorded average percent errors of 10.99%. Autoregressive terms, calendar and weather data reduced errors to 7.71%. Search volume data reduced errors to 7.58% theoretically preventing 4 improperly staffed days.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The predictive power provided by the search volume data may stem from the ability to capture population-level interaction with events, such as winter storms and infectious diseases, that traditional data sources alone miss.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This study demonstrates that search volume data can meaningfully improve forecasting of ED visit volume and could help improve quality and reduce cost.<\/jats:p><\/jats:sec>","DOI":"10.1093\/jamia\/ocz154","type":"journal-article","created":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T19:15:44Z","timestamp":1565118944000},"page":"1574-1583","source":"Crossref","is-referenced-by-count":23,"title":["Internet search query data improve forecasts of daily emergency department volume"],"prefix":"10.1093","volume":"26","author":[{"given":"Sam","family":"Tideman","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Harvard School of Public Health, Boston, Massachusetts, USA"}]},{"given":"Mauricio","family":"Santillana","sequence":"additional","affiliation":[{"name":"Computational Health Informatics Program, Boston Children\u2019s Hospital, Boston, Massachusetts, USA"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA"}]},{"given":"Jonathan","family":"Bickel","sequence":"additional","affiliation":[{"name":"Computational Health Informatics Program, Boston Children\u2019s Hospital, Boston, Massachusetts, USA"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA"}]},{"given":"Ben","family":"Reis","sequence":"additional","affiliation":[{"name":"Computational Health Informatics Program, Boston Children\u2019s Hospital, Boston, Massachusetts, USA"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA"},{"name":"Predictive Medicine Group, Boston Children\u2019s Hospital and Harvard Medical School, Boston, Massachusetts, USA"}]}],"member":"286","published-online":{"date-parts":[[2019,9,17]]},"reference":[{"issue":"1","key":"2021012411201653700_ocz154-B1","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.jpeds.2012.12.013","article-title":"Variation in resource utilization across a national sample of pediatric emergency departments","volume":"163","author":"Kharbanda","year":"2013","journal-title":"J Pediatr"},{"key":"2021012411201653700_ocz154-B2","volume-title":"The Evolving Role of Emergency Departments in the United States","author":"Gonzalez","year":"2013"},{"issue":"2","key":"2021012411201653700_ocz154-B3","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1111\/j.1553-2712.2007.00032.x","article-title":"Forecasting daily patient volumes in the emergency department","volume":"15","author":"Jones","year":"2008","journal-title":"Acad Emerg Med"},{"issue":"9","key":"2021012411201653700_ocz154-B4","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1111\/j.1553-2712.2010.00847.x","article-title":"From model to forecasting: a multicenter study in emergency departments","volume":"17","author":"Wargon","year":"2010","journal-title":"Acad Emerg Med"},{"issue":"5","key":"2021012411201653700_ocz154-B5","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1136\/emj.2010.103531","article-title":"Predicting emergency department admissions","volume":"29","author":"Boyle","year":"2012","journal-title":"Emerg Med J"},{"issue":"1","key":"2021012411201653700_ocz154-B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-227X-9-1","article-title":"Forecasting daily attendance at an emergency department to aid resource planning","volume":"9","author":"Sun","year":"2009","journal-title":"BMC Emerg Med"},{"issue":"8","key":"2021012411201653700_ocz154-B7","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1111\/acem.12182","article-title":"Forecasting daily emergency department visits using calendar variables and ambient temperature readings","volume":"20","author":"Marcilio","year":"2013","journal-title":"Acad Emerg Med"},{"issue":"3","key":"2021012411201653700_ocz154-B8","doi-asserted-by":"crossref","first-page":"158","DOI":"10.4258\/hir.2010.16.3.158","article-title":"Prediction of daily patient numbers for a regional emergency medical center using time series analysis","volume":"16","author":"Kam","year":"2010","journal-title":"Healthc Inform Res"},{"issue":"5","key":"2021012411201653700_ocz154-B9","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1016\/j.annemergmed.2008.09.019","article-title":"Emergency department crowding, part 1\u2014concept, causes, and moral consequences","volume":"53","author":"Moskop","year":"2009","journal-title":"Ann Emerg Med"},{"key":"2021012411201653700_ocz154-B10","volume-title":"Hospital-Based Emergency Care: At the Breaking Point","author":"Institute of Medicine","year":"2007"},{"key":"2021012411201653700_ocz154-B11","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1097\/00063110-199906000-00003","article-title":"Decreased health care quality associated with emergency department overcrowding","volume":"6","author":"Mir\u00f3","year":"1999","journal-title":"Eur J Emerg Med"},{"issue":"1","key":"2021012411201653700_ocz154-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.annemergmed.2007.07.008","article-title":"Emergency department crowding is associated with poor care for patients with severe pain","volume":"51","author":"Pines","year":"2008","journal-title":"Ann Emerg Med"},{"issue":"6","key":"2021012411201653700_ocz154-B13","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1016\/j.annemergmed.2012.10.026","article-title":"Effect of emergency department crowding on outcomes of admitted patients","volume":"61","author":"Sun","year":"2013","journal-title":"Ann Emerg Med"},{"issue":"5","key":"2021012411201653700_ocz154-B14","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1136\/emj.20.5.402","article-title":"Emergency department overcrowding in the United States: an emerging threat to patient safety and public health","volume":"20","author":"Trzeciak","year":"2003","journal-title":"Emerg Med J"},{"issue":"4","key":"2021012411201653700_ocz154-B15","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1016\/j.annemergmed.2009.03.006","article-title":"Crowding delays treatment and lengthens emergency department length of stay, even among high-acuity patients","volume":"54","author":"McCarthy","year":"2009","journal-title":"Ann Emerg Med"},{"issue":"6","key":"2021012411201653700_ocz154-B16","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/j.annemergmed.2004.05.004","article-title":"Emergency department crowding and thrombolysis delays in acute myocardial infarction","volume":"44","author":"Schull","year":"2004","journal-title":"Ann Emerg Med"},{"issue":"9","key":"2021012411201653700_ocz154-B17","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1111\/j.1553-2712.2008.00200.x","article-title":"The effect of emergency department crowding on patient satisfaction for admitted patients","volume":"15","author":"Pines","year":"2008","journal-title":"Acad Emerg Med"},{"issue":"5","key":"2021012411201653700_ocz154-B18","first-page":"327\u201340.","article-title":"Emergency department overcrowding: the impact of resource scarcity on physician job satisfaction","volume":"50","author":"Rondeau","year":"2005","journal-title":"J Healthc Manag"},{"issue":"2","key":"2021012411201653700_ocz154-B19","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1097\/01.pec.0000199561.34475.29","article-title":"Local weather effects on emergency department visits: a time series and regression analysis","volume":"22","author":"Zibners","year":"2006","journal-title":"Pediatr Emerg Care"},{"issue":"11","key":"2021012411201653700_ocz154-B20","first-page":"47","article-title":"Predicting trauma admissions: the effect of weather, weekday, and other variables","volume":"92","author":"Friede","year":"2009","journal-title":"Minn Med"},{"issue":"9","key":"2021012411201653700_ocz154-B21","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1136\/emj.2006.045310","article-title":"Effects of ambient temperature on volume, specialty composition and triage levels of emergency department visits","volume":"24","author":"Tai","year":"2007","journal-title":"Emerg Med J"},{"issue":"1","key":"2021012411201653700_ocz154-B22","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1111\/j.1553-2712.2001.tb00550.x","article-title":"Predicting patient visits to an urgent care clinic using calendar variables","volume":"8","author":"Batal","year":"2001","journal-title":"Acad Emerg Med"},{"issue":"4","key":"2021012411201653700_ocz154-B23","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1016\/S0735-6757(98)90131-0","article-title":"Effect of weather on the number and the nature of visits to a pediatric ED","volume":"16","author":"Attia","year":"1998","journal-title":"Am J Emerg Med"},{"issue":"8","key":"2021012411201653700_ocz154-B24","doi-asserted-by":"crossref","first-page":"e247","DOI":"10.1371\/journal.pmed.0040247","article-title":"Monitoring the impact of influenza by age: emergency department fever and respiratory complaint surveillance in New York City","volume":"4","author":"Olson","year":"2007","journal-title":"PLoS Med"},{"issue":"9","key":"2021012411201653700_ocz154-B25","doi-asserted-by":"crossref","first-page":"e0184364","DOI":"10.1371\/journal.pone.0184364","article-title":"Real-time surveillance of heat-related morbidity: Relation to excess mortality associated with extreme heat","volume":"12","author":"Mathes","year":"2017","journal-title":"PLoS One"},{"issue":"3","key":"2021012411201653700_ocz154-B26","doi-asserted-by":"crossref","first-page":"547","DOI":"10.2105\/AJPH.2004.061358","article-title":"Diarrheal illness detected through syndromic surveillance after a massive power outage: New York City, August 2003","volume":"96","author":"Marx","year":"2006","journal-title":"Am J Public Health"},{"issue":"4","key":"2021012411201653700_ocz154-B27","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.annemergmed.2005.04.031","article-title":"Running outside the baseline: Impact of the 2004 major league baseball postseason on emergency department use","volume":"46","author":"Reis","year":"2005","journal-title":"Ann Emerg Med"},{"issue":"2","key":"2021012411201653700_ocz154-B28","doi-asserted-by":"crossref","first-page":"e14677.","DOI":"10.1371\/journal.pone.0014677","article-title":"Assessing syndromic surveillance of cardiovascular outcomes from emergency department chief complaint data in New York City","volume":"6","author":"Mathes","year":"2011","journal-title":"PLoS One"},{"issue":"3","key":"2021012411201653700_ocz154-B29","doi-asserted-by":"crossref","first-page":"1488","DOI":"10.1016\/j.dss.2012.12.019","article-title":"Modeling daily patient arrivals at Emergency Department and quantifying the relative importance of contributing variables using artificial neural network","volume":"54","author":"Xu","year":"2013","journal-title":"Decis Support Syst"},{"issue":"1","key":"2021012411201653700_ocz154-B30","doi-asserted-by":"crossref","first-page":"1.","DOI":"10.1186\/1472-6947-3-2","article-title":"Time series modeling for syndromic surveillance","volume":"3","author":"Reis","year":"2003","journal-title":"BMC Med Inform Decis Mak"},{"issue":"4","key":"2021012411201653700_ocz154-B31","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1016\/j.annemergmed.2014.10.008","article-title":"Forecasting emergency department visits using internet data","volume":"65","author":"Ekstr\u00f6m","year":"2015","journal-title":"Ann Emerg Med"},{"issue":"11","key":"2021012411201653700_ocz154-B32","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1086\/593098","article-title":"Using internet searches for influenza surveillance","volume":"47","author":"Polgreen","year":"2008","journal-title":"Clin Infect Dis"},{"issue":"10","key":"2021012411201653700_ocz154-B33","doi-asserted-by":"crossref","first-page":"1557","DOI":"10.1086\/630200","article-title":"Google trends: a web-based tool for real-time surveillance of disease outbreaks","volume":"49","author":"Carneiro","year":"2009","journal-title":"Clin Infect Dis"},{"issue":"7232","key":"2021012411201653700_ocz154-B34","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1038\/nature07634","article-title":"Detecting influenza epidemics using search engine query data","volume":"457","author":"Ginsberg","year":"2009","journal-title":"Nature"},{"issue":"6176","key":"2021012411201653700_ocz154-B35","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1126\/science.1248506","article-title":"The parable of Google flu: traps in big data analysis","volume":"343","author":"Lazer","year":"2014","journal-title":"Science"},{"issue":"8","key":"2021012411201653700_ocz154-B36","doi-asserted-by":"crossref","first-page":"e23610.","DOI":"10.1371\/journal.pone.0023610","article-title":"Assessing google flu trends performance in the United States during the 2009 influenza virus A (H1N1) pandemic","volume":"6","author":"Cook","year":"2011","journal-title":"PLoS One"},{"issue":"10","key":"2021012411201653700_ocz154-B37","doi-asserted-by":"crossref","first-page":"e1003256.","DOI":"10.1371\/journal.pcbi.1003256","article-title":"Reassessing google flu trends data for detection of seasonal and pandemic influenza: a comparative epidemiological study at three geographic scales","volume":"9","author":"Olson","year":"2013","journal-title":"PLoS Comput Biol"},{"issue":"3","key":"2021012411201653700_ocz154-B38","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.amepre.2014.05.020","article-title":"What can digital disease detection learn from (an external revision to) google flu trends?","volume":"47","author":"Santillana","year":"2014","journal-title":"Am J Prev Med"},{"key":"2021012411201653700_ocz154-B39","doi-asserted-by":"crossref","first-page":"8154.","DOI":"10.1038\/srep08154","article-title":"Using networks to combine \u201cbig data\u201d and traditional surveillance to improve influenza predictions","volume":"5","author":"Davidson","year":"2015","journal-title":"Sci Rep"},{"key":"2021012411201653700_ocz154-B40","author":"Stefansen","year":"2014"},{"issue":"47","key":"2021012411201653700_ocz154-B41","doi-asserted-by":"crossref","first-page":"14473","DOI":"10.1073\/pnas.1515373112","article-title":"Accurate estimation of influenza epidemics using Google search data via ARGO","volume":"112","author":"Yang","year":"2015","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"2021012411201653700_ocz154-B42","doi-asserted-by":"crossref","first-page":"e0005295.","DOI":"10.1371\/journal.pntd.0005295","article-title":"Forecasting Zika incidence in the 2016 Latin America outbreak combining traditional disease surveillance with search, social media, and news report data","volume":"11","author":"McGough","year":"2017","journal-title":"PLoS Negl Trop Dis"},{"issue":"7","key":"2021012411201653700_ocz154-B43","doi-asserted-by":"crossref","first-page":"e1005607.","DOI":"10.1371\/journal.pcbi.1005607","article-title":"Advances in using Internet searches to track dengue","volume":"13","author":"Yang","year":"2017","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"2021012411201653700_ocz154-B44","doi-asserted-by":"crossref","first-page":"e4.","DOI":"10.2196\/publichealth.8950","article-title":"Accurate influenza monitoring and forecasting using novel internet data streams: a case study in the Boston Metropolis","volume":"4","author":"Lu","year":"2018","journal-title":"JMIR Public Health Surveill"},{"issue":"1","key":"2021012411201653700_ocz154-B45","doi-asserted-by":"crossref","DOI":"10.1038\/srep12760","article-title":"Advances in nowcasting influenza-like illness rates using search query logs","volume":"5","author":"Lampos","year":"2015","journal-title":"Sci Rep"},{"issue":"1","key":"2021012411201653700_ocz154-B46","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1186\/s12879-017-2424-7","article-title":"Using electronic health records and Internet search information for accurate influenza forecasting","volume":"17","author":"Yang","year":"2017","journal-title":"BMC Infect Dis"},{"issue":"10","key":"2021012411201653700_ocz154-B47","doi-asserted-by":"crossref","first-page":"e1004513","DOI":"10.1371\/journal.pcbi.1004513","article-title":"Combining search, social media, and traditional data sources to improve influenza surveillance","volume":"11","author":"Santillana","year":"2015","journal-title":"PLoS Comput Biol"},{"key":"2021012411201653700_ocz154-B48"},{"issue":"1","key":"2021012411201653700_ocz154-B49","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2021012411201653700_ocz154-B50","author":"Tideman S","year":"2016"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/12\/1574\/36088134\/ocz154.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/12\/1574\/36088134\/ocz154.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T19:10:07Z","timestamp":1721589007000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/26\/12\/1574\/5570969"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,17]]},"references-count":50,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2019,9,17]]},"published-print":{"date-parts":[[2019,12,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocz154","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,12]]},"published":{"date-parts":[[2019,9,17]]}}}