{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:18:47Z","timestamp":1767982727612,"version":"3.49.0"},"reference-count":76,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Peers Health through a research agreement with the University of Michigan"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Occupational injuries (OIs) cause an immense burden on the US population. Prediction models help focus resources on those at greatest risk of a delayed return to work (RTW). RTW depends on factors that develop over time; however, existing methods only utilize information collected at the time of injury. We investigate the performance benefits of dynamically estimating RTW, using longitudinal observations of diagnoses and treatments collected beyond the time of initial injury.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We characterize the difference in predictive performance between an approach that uses information collected at the time of initial injury (baseline model) and a proposed approach that uses longitudinal information collected over the course of the patient\u2019s recovery period (proposed model). To control the comparison, both models use the same deep learning architecture and differ only in the information used. We utilize a large longitudinal observation dataset of OI claims and compare the performance of the\u00a0two approaches in terms of daily prediction of future work state (working vs not working). The performance of these\u00a0two approaches was assessed in terms of the area under the receiver operator characteristic curve (AUROC) and expected calibration error (ECE).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>After subsampling and applying inclusion criteria, our final dataset covered 294\u200a103 OIs, which were split evenly between train, development, and test datasets (1\/3, 1\/3, 1\/3). In terms of discriminative performance on the test dataset, the proposed model had an AUROC of 0.728 (90% confidence interval: 0.723, 0.734) versus the baseline\u2019s 0.591 (0.585, 0.598). The proposed model had an ECE of 0.004 (0.003, 0.005) versus the baseline\u2019s 0.016 (0.009, 0.018).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The longitudinal approach outperforms current practice and shows potential for leveraging observational data to dynamically update predictions of RTW in the setting of OI. This approach may enable physicians and workers\u2019 compensation programs to manage large populations of injured workers more effectively.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocac130","type":"journal-article","created":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T10:22:28Z","timestamp":1661768548000},"page":"1931-1940","source":"Crossref","is-referenced-by-count":3,"title":["Dynamic prediction of work status for workers with occupational injuries: assessing the value of longitudinal observations"],"prefix":"10.1093","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3169-6832","authenticated-orcid":false,"given":"Erkin","family":"\u00d6tle\u015f","sequence":"first","affiliation":[{"name":"Department of Industrial & Operations Engineering, University of Michigan , Ann Arbor, Michigan, USA"},{"name":"Medical Scientist Training Program, University of Michigan Medical School , Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jon","family":"Seymour","sequence":"additional","affiliation":[{"name":"Peers Health , Chicago, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9679-0144","authenticated-orcid":false,"given":"Haozhu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering & Computer Science, University of Michigan , Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian T","family":"Denton","sequence":"additional","affiliation":[{"name":"Department of Industrial & Operations Engineering, University of Michigan , Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,8,29]]},"reference":[{"issue":"4","key":"2022101107575630000_ocac130-B1","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1111\/j.1468-0009.2011.00648.x","article-title":"Economic burden of occupational injury and illness in the United States","volume":"89","author":"Leigh","year":"2011","journal-title":"Milbank Q"},{"key":"2022101107575630000_ocac130-B2"},{"key":"2022101107575630000_ocac130-B3","volume-title":"Injuries, Illnesses, and Fatalities","author":"U.S. Bureau of Labor Statistics","year":"2019"},{"issue":"12","key":"2022101107575630000_ocac130-B4","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1002\/ajim.22632","article-title":"The impact of non-fatal workplace injuries and illnesses on mortality","volume":"59","author":"Boden","year":"2016","journal-title":"Am J Ind Med"},{"issue":"5","key":"2022101107575630000_ocac130-B5","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1002\/(SICI)1097-0274(199911)36:5<487::AID-AJIM1>3.0.CO;2-2","article-title":"Economic consequences of workplace injuries and illnesses: lost earnings and benefit adequacy","volume":"36","author":"Boden","year":"1999","journal-title":"Am J Ind Med"},{"issue":"3","key":"2022101107575630000_ocac130-B6","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1136\/oemed-2015-103067","article-title":"Marginal structural modelling of associations of occupational injuries with voluntary and involuntary job loss among nursing home workers","volume":"73","author":"Okechukwu","year":"2016","journal-title":"Occup Environ Med"},{"issue":"2","key":"2022101107575630000_ocac130-B7","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1002\/ajim.22559","article-title":"Economic consequences of workplace injuries in the United States: findings from the National Longitudinal Survey of Youth (NLSY79)","volume":"59","author":"Dong","year":"2016","journal-title":"Am J Ind Med"},{"issue":"2","key":"2022101107575630000_ocac130-B8","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1377\/hlthaff.2016.1185","article-title":"Racial and ethnic differences in the frequency of workplace injuries and prevalence of work-related disability","volume":"36","author":"Seabury","year":"2017","journal-title":"Health Aff (Millwood)"},{"key":"2022101107575630000_ocac130-B9","volume-title":"Stay-at-Work\/Return-to-Work: Key Facts, Critical Information Gaps, and Current Practices and Proposals","author":"Ben-Shalom","year":"2017"},{"key":"2022101107575630000_ocac130-B10","first-page":"40","year":"2012"},{"key":"2022101107575630000_ocac130-B11","author":"Wiesner","year":"2016"},{"issue":"7","key":"2022101107575630000_ocac130-B12","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1016\/j.spinee.2014.01.030","article-title":"A primer for workers\u2019 compensation","volume":"14","author":"Bible","year":"2014","journal-title":"Spine J"},{"issue":"11","key":"2022101107575630000_ocac130-B13","doi-asserted-by":"crossref","first-page":"298","DOI":"10.15585\/mmwr.mm6911a5","article-title":"Variation in adult outpatient opioid prescription dispensing by age and sex\u2014United States, 2008\u20132018","volume":"69","author":"Schieber","year":"2020","journal-title":"MMWR Morb Mortal Wkly Rep"},{"key":"2022101107575630000_ocac130-B14"},{"key":"2022101107575630000_ocac130-B15"},{"key":"2022101107575630000_ocac130-B16","author":"Gaspar","year":"2017"},{"issue":"4","key":"2022101107575630000_ocac130-B17","doi-asserted-by":"crossref","first-page":"e57","DOI":"10.1097\/JOM.0000000000001014","article-title":"Advancing value-based medicine: why integrating functional outcomes with clinical measures is critical to our health care future","volume":"59","author":"Mueller","year":"2017","journal-title":"J Occup Environ Med"},{"issue":"6","key":"2022101107575630000_ocac130-B18","doi-asserted-by":"crossref","first-page":"440","DOI":"10.2340\/16501977-0194","article-title":"Worker\u2019s compensation and return-to-work following orthopaedic injury to extremities","volume":"40","author":"Hou","year":"2008","journal-title":"J Rehabil Med"},{"issue":"4","key":"2022101107575630000_ocac130-B19","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1136\/oem.60.4.235","article-title":"The right treatment to the right patient at the right time","volume":"60","author":"Haldorsen","year":"2003","journal-title":"Occup Environ Med"},{"issue":"4","key":"2022101107575630000_ocac130-B20","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1136\/oem.60.4.244","article-title":"Early prognostic factors for duration on temporary total benefits in the first year among workers with compensated occupational soft tissue injuries","volume":"60","author":"Hogg-Johnson","year":"2003","journal-title":"Occup Environ Med"},{"issue":"2","key":"2022101107575630000_ocac130-B21","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s10926-014-9534-5","article-title":"Predicting time on prolonged benefits for injured workers with acute back pain","volume":"25","author":"Steenstra","year":"2015","journal-title":"J Occup Rehabil"},{"issue":"1","key":"2022101107575630000_ocac130-B22","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1038\/s41598-018-36745-x","article-title":"Learning from longitudinal data in electronic health record and genetic data to improve cardiovascular event prediction","volume":"9","author":"Zhao","year":"2019","journal-title":"Sci Rep"},{"key":"2022101107575630000_ocac130-B23","article-title":"A critical review of recurrent neural networks for sequence learning","author":"Zachary","year":"2015","journal-title":"ArXiv"},{"key":"2022101107575630000_ocac130-B24","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2022101107575630000_ocac130-B25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-642-24797-2_1","article-title":"Supervised sequence labelling with recurrent neural networks","volume":"385","author":"Graves","year":"2012","journal-title":"Stud Comput Intell"},{"key":"2022101107575630000_ocac130-B26","article-title":"Neural turing machines","author":"Graves","year":"2014","journal-title":"arXiv"},{"issue":"1","key":"2022101107575630000_ocac130-B27","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1007\/s10926-007-9116-x","article-title":"A systematic review of disability management interventions with economic evaluations","volume":"18","author":"Tompa","year":"2008","journal-title":"J Occup Rehabil"},{"key":"2022101107575630000_ocac130-B28","first-page":"S27","article-title":"Impact of a musculoskeletal disability management program on medical costs and productivity in a large manufacturing company","volume":"12","author":"Bunn","year":"2006","journal-title":"Am J Manag Care"},{"issue":"10","key":"2022101107575630000_ocac130-B29","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1097\/00043764-200010000-00007","article-title":"Disability management: corporate medical department management of employee health and productivity","volume":"42","author":"Burton","year":"2000","journal-title":"J Occup Environ Med"},{"key":"2022101107575630000_ocac130-B30","doi-asserted-by":"crossref","DOI":"10.1037\/10662-013","volume-title":"Returning to Work after Occupational Injury","author":"Krause","year":"2004"},{"key":"2022101107575630000_ocac130-B31","author":"American College of Occupational and Environmental Medicine","year":"2017"},{"issue":"9","key":"2022101107575630000_ocac130-B32","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1097\/01.jom.0000235915.61746.0d","article-title":"Preventing needless work disability by helping people stay employed","volume":"48","author":"Guideline","year":"2006","journal-title":"J Occup Environ Med"},{"issue":"2","key":"2022101107575630000_ocac130-B33","first-page":"102","article-title":"Overview of occupational medicine training among US family medicine residency programs","volume":"40","author":"Michas","year":"2008","journal-title":"Fam Med"},{"key":"2022101107575630000_ocac130-B34","volume-title":"Evaluating Medical Treatment Guideline Sets for Injured Workers in California","author":"Nuckols","year":"2005"},{"key":"2022101107575630000_ocac130-B35","author":"ODG by MCG"},{"key":"2022101107575630000_ocac130-B36","author":"MDGuidelines"},{"issue":"8","key":"2022101107575630000_ocac130-B37","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.injury.2010.04.005","article-title":"A systematic review of early prognostic factors for return to work following acute orthopaedic trauma","volume":"41","author":"Clay","year":"2010","journal-title":"Injury"},{"key":"2022101107575630000_ocac130-B38","first-page":"181","article-title":"Return to work after lumbar microdiscectomy\u2014personalizing approach through predictive modeling","volume":"224","author":"Papic","year":"2016","journal-title":"Stud Health Technol Inform"},{"issue":"2","key":"2022101107575630000_ocac130-B39","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s10926-017-9714-1","article-title":"Common psychosocial factors predicting return to work after common mental disorders, cardiovascular diseases, and cancers: a review of reviews supporting a cross-disease approach","volume":"28","author":"Gragnano","year":"2018","journal-title":"J Occup Rehabil"},{"key":"2022101107575630000_ocac130-B40","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.jpsychires.2017.07.024","article-title":"Prognostic factors for return to work after depression-related work disability: a systematic review and meta-analysis","volume":"95","author":"Ervasti","year":"2017","journal-title":"J Psychiatr Res"},{"issue":"01","key":"2022101107575630000_ocac130-B41","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1142\/S0218001401000836","article-title":"An introduction to hidden Markov models and Bayesian networks","volume":"15","author":"Ghahramani","year":"2001","journal-title":"Int J Patt Recogn Artif Intell"},{"key":"2022101107575630000_ocac130-B42","first-page":"241","author":"Bolano","year":"2016"},{"key":"2022101107575630000_ocac130-B43","doi-asserted-by":"crossref","DOI":"10.5772\/601","volume-title":"Hidden Markov Models: Theory and Applications","author":"Dymarski","year":"2011"},{"key":"2022101107575630000_ocac130-B44","doi-asserted-by":"crossref","DOI":"10.1201\/b13246","volume-title":"Latent Markov Models for Longitudinal Data","author":"Bartolucci","year":"2012"},{"key":"2022101107575630000_ocac130-B45","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1186\/s12911-018-0672-0","article-title":"EHR phenotyping via jointly embedding medical concepts and words into a unified vector space","volume":"18","author":"Bai","year":"2018","journal-title":"BMC Med Inform Decis"},{"key":"2022101107575630000_ocac130-B46","article-title":"Clinical concept embeddings learned from massive sources of medical data","author":"Beam","year":"2018","journal-title":"arXiv"},{"key":"2022101107575630000_ocac130-B47","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv"},{"key":"2022101107575630000_ocac130-B48","author":"Google"},{"key":"2022101107575630000_ocac130-B49","author":"Google"},{"key":"2022101107575630000_ocac130-B50","author":"Szymendera","year":"2018"},{"key":"2022101107575630000_ocac130-B51","author":"Li","year":"2018"},{"issue":"8","key":"2022101107575630000_ocac130-B52","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1001\/jamainternmed.2021.2626","article-title":"External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients","volume":"181","author":"Wong","year":"2021","journal-title":"JAMA Intern Med"},{"issue":"3","key":"2022101107575630000_ocac130-B53","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1175\/WAF993.1","article-title":"Increasing the reliability of reliability diagrams","volume":"22","author":"Br\u00f6cker","year":"2007","journal-title":"Weather Forecast"},{"key":"2022101107575630000_ocac130-B54","author":"Seedat","year":"2019"},{"key":"2022101107575630000_ocac130-B55","volume-title":"Python Reference Manual","author":"Rossum","year":"1995"},{"key":"2022101107575630000_ocac130-B56","article-title":"Tensorflow: large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016","journal-title":"arXiv"},{"key":"2022101107575630000_ocac130-B57","volume-title":"Hands-on Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems","author":"G\u00e9ron","year":"2017"},{"key":"2022101107575630000_ocac130-B58","volume-title":"Keras","author":"Chollet","year":"2015"},{"key":"2022101107575630000_ocac130-B59","volume-title":"The Definitive Guide to SQLite","author":"Owens","year":"2010"},{"key":"2022101107575630000_ocac130-B60","volume-title":"A Guide to NumPy.","author":"Oliphant","year":"2006"},{"issue":"2","key":"2022101107575630000_ocac130-B61","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/MCSE.2011.37","article-title":"The NumPy array: a structure for efficient numerical computation","volume":"13","author":"Van Der Walt","year":"2011","journal-title":"Comput Sci Eng"},{"key":"2022101107575630000_ocac130-B62","first-page":"51","author":"McKinney","year":"2010"},{"issue":"1","key":"2022101107575630000_ocac130-B63","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1093\/jamiaopen\/ooy012","article-title":"tableone: an open source Python package for producing summary statistics for research papers","volume":"1","author":"Pollard","year":"2018","journal-title":"JAMIA Open"},{"issue":"Oct","key":"2022101107575630000_ocac130-B64","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2022101107575630000_ocac130-B65","author":"\u00d6tle\u015f","year":"2021"},{"issue":"24","key":"2022101107575630000_ocac130-B66","doi-asserted-by":"crossref","first-page":"2377","DOI":"10.1001\/jama.2019.18058","article-title":"Addressing bias in artificial intelligence in health care","volume":"322","author":"Parikh","year":"2019","journal-title":"JAMA"},{"issue":"2","key":"2022101107575630000_ocac130-B67","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1111\/awr.12148","article-title":"When they\u2019re done with you: legal violence and structural vulnerability among injured immigrant poultry workers","volume":"39","author":"Stuesse","year":"2018","journal-title":"Anthropol Work Rev"},{"issue":"3","key":"2022101107575630000_ocac130-B68","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1007\/s10926-010-9232-x","article-title":"Determinants of return to work after occupational injury","volume":"20","author":"He","year":"2010","journal-title":"J Occup Rehabil"},{"issue":"2","key":"2022101107575630000_ocac130-B69","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1177\/1073110518782948","article-title":"The impact of prescription drug monitoring programs on U.S. opioid prescriptions","volume":"46","author":"Ayres","year":"2018","journal-title":"J Law Med Ethics"},{"key":"2022101107575630000_ocac130-B70","volume-title":"Interpretability of Deep Learning Models: A Survey of Results","author":"Chakraborty","year":"2017"},{"key":"2022101107575630000_ocac130-B71","author":"Thompson","year":"2020"},{"key":"2022101107575630000_ocac130-B72","author":"Marcus","year":"2018"},{"issue":"5","key":"2022101107575630000_ocac130-B73","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1002\/sam.11236","article-title":"Survival analysis with electronic health record data: experiments with chronic kidney disease","volume":"7","author":"Hagar","year":"2014","journal-title":"Stat Anal Data Min"},{"key":"2022101107575630000_ocac130-B74","author":"Daum\u00e9","year":"2009"},{"issue":"4","key":"2022101107575630000_ocac130-B75","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1017\/ice.2018.16","article-title":"A generalizable, data-driven approach to predict daily risk of clostridium difficile infection at two large academic health centers","volume":"39","author":"Oh","year":"2018","journal-title":"Infect Control Hosp Epidemiol"},{"issue":"2","key":"2022101107575630000_ocac130-B76","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1093\/jamia\/ocx035","article-title":"Representation of occupational information across resources and validation of the occupational data for health model","volume":"25","author":"Rajamani","year":"2018","journal-title":"J Am Med Inform Assoc"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/29\/11\/1931\/46378826\/ocac130.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/29\/11\/1931\/46378826\/ocac130.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,11]],"date-time":"2022-10-11T08:00:30Z","timestamp":1665475230000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/29\/11\/1931\/6678249"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":76,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022,8,29]]},"published-print":{"date-parts":[[2022,10,7]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocac130","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,11,1]]},"published":{"date-parts":[[2022,8,29]]}}}