{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T06:31:08Z","timestamp":1778221868288,"version":"3.51.4"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1012717","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000}}],"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000030","name":"Centers for Disease Control and Prevention","doi-asserted-by":"publisher","award":["75D30123C15907"],"award-info":[{"award-number":["75D30123C15907"]}],"id":[{"id":"10.13039\/100000030","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>We propose, implement, and evaluate a method for nowcasting the daily number of new COVID-19 hospitalizations, at the level of individual US states, based on de-identified, aggregated medical insurance claims data. Our analysis proceeds under a hypothetical scenario in which, during the Delta wave, states only report data on the first day of each month, and on this day, report COVID-19 hospitalization counts for each day in the previous month. In this hypothetical scenario (just as in reality), medical insurance claims data continues to be available daily. At the beginning of each month, we train a regression model, using all data available thus far, to predict hospitalization counts from medical insurance claims. We then use this model to nowcast the (unseen) values of COVID-19 hospitalization counts from medical insurance claims, at each day in the following month. Our analysis uses properly-versioned data, which would have been available in real-time at the time predictions are produced (instead of using data that would have only been available in hindsight). In spite of the difficulties inherent to real-time estimation (e.g., latency and backfill) and the complex dynamics behind COVID-19 hospitalizations themselves, we find altogether that medical insurance claims can be an accurate predictor of hospitalization reports, with mean absolute errors typically around 0.4 hospitalizations per 100,000 people, i.e., proportion of variance explained around 75%. Perhaps more importantly, we find that nowcasts made using medical insurance claims are able to qualitatively capture the dynamics (upswings and downswings) of hospitalization waves, which are key features that inform public health decision-making.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1012717","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T13:43:38Z","timestamp":1739886218000},"page":"e1012717","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Nowcasting reported covid-19 hospitalizations using de-identified, aggregated medical insurance claims data"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1218-5068","authenticated-orcid":true,"given":"Xueda","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Rumack","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Wilder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan J","family":"Tibshirani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,2,18]]},"reference":[{"key":"pcbi.1012717.ref001"},{"key":"pcbi.1012717.ref002"},{"key":"pcbi.1012717.ref003"},{"key":"pcbi.1012717.ref004"},{"issue":"1","key":"pcbi.1012717.ref005","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1186\/s12199-019-0819-3","article-title":"Validation of claims data to identify death among aged persons utilizing enrollment data from health insurance unions","volume":"24","author":"M Sakai","year":"2019","journal-title":"Environ Health Prev Med"},{"key":"pcbi.1012717.ref006"},{"issue":"10","key":"pcbi.1012717.ref007","doi-asserted-by":"crossref","first-page":"2187","DOI":"10.1002\/hec.4568","article-title":"Toward mandatory health insurance in low-income countries? An analysis of claims data in Tanzania","volume":"31","author":"K Durizzo","year":"2022","journal-title":"Health Econ"},{"issue":"1","key":"pcbi.1012717.ref008","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/s11657-022-01096-8","article-title":"Medical expenditures for fragility hip fracture in Japan: a study using the nationwide health insurance claims database","volume":"17","author":"T Mori","year":"2022","journal-title":"Arch Osteoporos."},{"issue":"1","key":"pcbi.1012717.ref009","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/s12199-017-0644-5","article-title":"Analysis of the evidence-practice gap to facilitate proper medical care for the elderly: investigation, using databases, of utilization measures for National Database of Health Insurance Claims and Specific Health Checkups of Japan (NDB)","volume":"22","author":"T Nakayama","year":"2017","journal-title":"Environ Health Prev Med"},{"key":"pcbi.1012717.ref010"},{"issue":"1","key":"pcbi.1012717.ref011","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1186\/s12889-021-11947-7","article-title":"Assessment of the satisfaction with public health insurance programs by patients with chronic diseases in China: a structural equation modeling approach","volume":"21","author":"J Geng","year":"2021","journal-title":"BMC Public Health."},{"key":"pcbi.1012717.ref012"},{"key":"pcbi.1012717.ref013"},{"issue":"51","key":"pcbi.1012717.ref014","doi-asserted-by":"crossref","first-page":"e2111452118","DOI":"10.1073\/pnas.2111452118","article-title":"An open repository of real-time COVID-19 indicators","volume":"118","author":"A Reinhart","year":"2021","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"51","key":"pcbi.1012717.ref015","doi-asserted-by":"crossref","first-page":"e2111453118","DOI":"10.1073\/pnas.2111453118","article-title":"Can auxiliary indicators improve COVID-19 forecasting and hotspot prediction?","volume":"118","author":"DJ McDonald","year":"2021","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"51","key":"pcbi.1012717.ref016","doi-asserted-by":"crossref","first-page":"e2111456118","DOI":"10.1073\/pnas.2111456118","article-title":"Epidemic tracking and forecasting: Lessons learned from a tumultuous year","volume":"118","author":"R Rosenfeld","year":"2021","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"7","key":"pcbi.1012717.ref017","doi-asserted-by":"crossref","first-page":"e102429","DOI":"10.1371\/journal.pone.0102429","article-title":"Demonstrating the use of high-volume electronic medical claims data to monitor local and regional influenza activity in the US","volume":"9","author":"C Viboud","year":"2014","journal-title":"PLoS One"},{"issue":"10","key":"pcbi.1012717.ref018","doi-asserted-by":"crossref","first-page":"2124","DOI":"10.2105\/AJPH.2015.302696","article-title":"Flu near you: crowdsourced symptom reporting spanning 2 influenza seasons","volume":"105","author":"MS Smolinski","year":"2015","journal-title":"Am J Public Health"},{"issue":"47","key":"pcbi.1012717.ref019","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":"S Yang","year":"2015","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pcbi.1012717.ref020","article-title":"Modeling the past, present, and future of influenza [dissertation]. Pittsburgh, PA: Carnegie Mellon University","author":"DC Farrow","year":"2016"},{"issue":"1","key":"pcbi.1012717.ref021","first-page":"1","article-title":"Cloud-based electronic health records for real-time","volume":"6","author":"M Santillana","year":"2016","journal-title":"region-specific influenza surveillance. Sci Rep."},{"issue":"22","key":"pcbi.1012717.ref022","doi-asserted-by":"crossref","first-page":"4363","DOI":"10.1002\/sim.8303","article-title":"A modelling approach for correcting reporting delays in disease surveillance data","volume":"38","author":"LS Bastos","year":"2019","journal-title":"Stat Med"},{"key":"pcbi.1012717.ref023"},{"issue":"2","key":"pcbi.1012717.ref024","doi-asserted-by":"crossref","first-page":"e12341","DOI":"10.2196\/12341","article-title":"An integrated influenza surveillance framework based on national influenza-like illness incidence and multiple hospital electronic medical records for early prediction of influenza epidemics: design and evaluation","volume":"21","author":"C-Y Yang","year":"2019","journal-title":"J Med Internet Res"},{"issue":"3","key":"pcbi.1012717.ref025","doi-asserted-by":"crossref","first-page":"2148","DOI":"10.1177\/1460458219897152","article-title":"Assessing the utility of a smart thermometer and mobile application as a surveillance tool for influenza and influenza-like illness","volume":"26","author":"SF Ackley","year":"2020","journal-title":"Health Informatics J"},{"key":"pcbi.1012717.ref026","article-title":"Pancasting: forecasting epidemics from provisional data [dissertation]. Pittsburgh, PA: Carnegie Mellon University","author":"LC Brooks","year":"2020"},{"issue":"11","key":"pcbi.1012717.ref027","doi-asserted-by":"crossref","first-page":"e1008180","DOI":"10.1371\/journal.pcbi.1008180","article-title":"Tracking and predicting U.S. influenza activity with a real-time surveillance network","volume":"16","author":"SI Leuba","year":"2020","journal-title":"PLoS Comput Biol"},{"issue":"2","key":"pcbi.1012717.ref028","doi-asserted-by":"crossref","first-page":"e85","DOI":"10.1016\/S2589-7500(19)30222-5","article-title":"Harnessing wearable device data to improve state-level real-time surveillance of influenza-like illness in the USA: a population-based study","volume":"2","author":"JM Radin","year":"2020","journal-title":"Lancet Digit Health"},{"issue":"2","key":"pcbi.1012717.ref029","first-page":"207","article-title":"Real-time estimation of COVID-19 infections: deconvolution and sensor fusion","volume":"37","author":"M Jahja","year":"2021","journal-title":"Statist Sci."},{"issue":"7","key":"pcbi.1012717.ref030","doi-asserted-by":"crossref","first-page":"e1009210","DOI":"10.1371\/journal.pcbi.1009210","article-title":"Bayesian back-calculation and nowcasting for line list data during the COVID-19 pandemic","volume":"17","author":"T Li","year":"2021","journal-title":"PLoS Comput Biol"},{"issue":"11","key":"pcbi.1012717.ref031","doi-asserted-by":"crossref","first-page":"e1009570","DOI":"10.1371\/journal.pcbi.1009570","article-title":"A nowcasting framework for correcting for reporting delays in malaria surveillance","volume":"17","author":"TF Menkir","year":"2021","journal-title":"PLoS Comput Biol"},{"issue":"12","key":"pcbi.1012717.ref032","doi-asserted-by":"crossref","first-page":"e1010767","DOI":"10.1371\/journal.pcbi.1010767","article-title":"Bayesian nowcasting with leading indicators applied to COVID-19 fatalities in Sweden","volume":"18","author":"F Bergstr\u00f6m","year":"2022","journal-title":"PLoS Comput Biol"},{"issue":"4","key":"pcbi.1012717.ref033","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1097\/EDE.0000000000001495","article-title":"Statistical deconvolution for inference of infection time series","volume":"33","author":"AC Miller","year":"2022","journal-title":"Epidemiology"},{"issue":"5","key":"pcbi.1012717.ref034","doi-asserted-by":"crossref","first-page":"1266","DOI":"10.1111\/rssc.12576","article-title":"Nowcasting COVID-19 deaths in England by age and region","volume":"71","author":"SR Seaman","year":"2022","journal-title":"J R Stat Soc C."},{"issue":"3","key":"pcbi.1012717.ref035","doi-asserted-by":"crossref","first-page":"e1009964","DOI":"10.1371\/journal.pcbi.1009964","article-title":"Near real-time surveillance of the SARS-CoV-2 epidemic with incomplete data","volume":"18","author":"PM De Salazar","year":"2022","journal-title":"PLoS Comput Biol"},{"issue":"8","key":"pcbi.1012717.ref036","doi-asserted-by":"crossref","first-page":"e1011394","DOI":"10.1371\/journal.pcbi.1011394","article-title":"Collaborative nowcasting of COVID-19 hospitalization incidences in Germany","volume":"19","author":"D Wolffram","year":"2023","journal-title":"PLoS Comput Biol"},{"issue":"4","key":"pcbi.1012717.ref037","doi-asserted-by":"crossref","first-page":"e1012021","DOI":"10.1371\/journal.pcbi.1012021","article-title":"Generative Bayesian modeling to nowcast the effective reproduction number from line list data with missing symptom onset dates","volume":"20","author":"A Lison","year":"2024","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1012717.ref038"},{"key":"pcbi.1012717.ref039"},{"key":"pcbi.1012717.ref040","article-title":"Conformal PID control for time series prediction. In: Oh A, Naumann T","author":"A Angelopoulos","year":"2023"},{"key":"pcbi.1012717.ref041"},{"issue":"1","key":"pcbi.1012717.ref042","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1186\/s12889-021-12469-y","article-title":"Association between county-level risk groups and COVID-19 outcomes in the United States: a socioecological study","volume":"22","author":"SS Khan","year":"2022","journal-title":"BMC Public Health"},{"issue":"15","key":"pcbi.1012717.ref043","doi-asserted-by":"crossref","first-page":"e2113561119","DOI":"10.1073\/pnas.2113561119","article-title":"Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States","volume":"119","author":"EY Cramer","year":"2022","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"3","key":"pcbi.1012717.ref044","doi-asserted-by":"crossref","first-page":"1366","DOI":"10.1016\/j.ijforecast.2022.06.005","article-title":"Comparing trained and untrained probabilistic ensemble forecasts of COVID-19 cases and deaths in the United States","volume":"39","author":"EL Ray","year":"2023","journal-title":"Int J Forecast"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1012717","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T13:41:41Z","timestamp":1740058901000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012717"}},"subtitle":[],"editor":[{"given":"Benjamin","family":"Althouse","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,2,18]]},"references-count":44,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012717","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.12.22.23300471","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,18]]}}}