{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T11:29:29Z","timestamp":1767180569510,"version":"build-2238731810"},"reference-count":24,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T00:00:00Z","timestamp":1722384000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013414","name":"Conseil R\u00e9gional des Pays de la Loire","doi-asserted-by":"publisher","award":["TEC-TOP"],"award-info":[{"award-number":["TEC-TOP"]}],"id":[{"id":"10.13039\/501100013414","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-11-INBS-0002"],"award-info":[{"award-number":["ANR-11-INBS-0002"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CONSTANCES","award":["Merck Sharp & Dohme (MSD), AstraZeneca, Lundbeck and L\u2019Or\u00e9al through Inserm-Transfert"],"award-info":[{"award-number":["Merck Sharp & Dohme (MSD), AstraZeneca, Lundbeck and L\u2019Or\u00e9al through Inserm-Transfert"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Though the rise of big data in the field of occupational health offers new opportunities especially for cross-cutting research, they raise the issue of privacy and security of data, especially when linking sensitive data from the field of insurance, occupational health or compensation claims. We aimed to validate a large, blinded synthesized database developed from the CONSTANCES cohort by comparing associations between three independently selected outcomes, and various exposures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>From the CONSTANCES cohort, a large synthetic dataset was constructed using the avatar method (Octopize) that is agnostic to the data primary or secondary data uses. Three main analyses of interest were chosen to compare associations between the raw and avatar dataset: risk of stroke (any stroke, and subtypes of stroke), risk of knee pain and limitations associated with knee pain. Logistic models were computed, and a qualitative comparison of paired odds ratio (OR) was made.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Both raw and avatar datasets included 162,434 observations and 19 relevant variables. On the 172 paired raw\/avatar OR that were computed, including stratified analyses on sex, more than 77% of the comparisons had a OR difference \u22640.5 and less than 7% had a discrepancy in the statistical significance of the associations, with a Cohen\u2019s Kappa coefficient of 0.80.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study shows the flexibility and the multiple usage of a synthetic database created with the avatar method in the particular field of occupational health, which can be shared in open access without risking re-identification and privacy issues and help bring new insights for complex phenomenon like return to work.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0308063","type":"journal-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T13:32:15Z","timestamp":1722432735000},"page":"e0308063","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["Flexibility of a large blindly synthetized avatar database for occupational research: Example from the CONSTANCES cohort for stroke and knee pain"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1554-0021","authenticated-orcid":true,"given":"Marc","family":"Fadel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Petot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierre-Antoine","family":"Gourraud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6028-3186","authenticated-orcid":true,"given":"Alexis","family":"Descatha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"key":"pone.0308063.ref001","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1097\/EDE.0000000000000711","article-title":"Big Data and Population Health: Focusing on the Health Impacts of the Social, Physical, and Economic Environment","volume":"28","author":"H Hu","year":"2017","journal-title":"Epidemiology"},{"key":"pone.0308063.ref002","first-page":"1049","article-title":"Toward the development of a big data analytics capabilityInformation &","volume":"53","author":"M Gupta","year":"2016","journal-title":"Management"},{"key":"pone.0308063.ref003","doi-asserted-by":"crossref","first-page":"1750","DOI":"10.1001\/jama.2016.4226","article-title":"The Association Between Income and Life Expectancy in the United States, 2001\u20132014","volume":"315","author":"R Chetty","year":"2016","journal-title":"JAMA"},{"key":"pone.0308063.ref004","doi-asserted-by":"crossref","first-page":"267","DOI":"10.2147\/CLEP.S105613","article-title":"Use of the Medicare database in epidemiologic and health services research: a valuable source of real-world evidence on the older and disabled populations in the US","volume":"9","author":"KE Mues","year":"2017","journal-title":"Clinical Epidemiology"},{"key":"pone.0308063.ref005","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s10926-019-09863-0","article-title":"An Interpretable Algorithm on Post-injury Health Service Utilization Patterns to Predict Injury Outcomes","volume":"30","author":"H Akbarzadeh Khorshidi","year":"2020","journal-title":"J Occup Rehabil"},{"key":"pone.0308063.ref006","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s10926-020-09910-1","article-title":"Machine Learning for Work Disability Prevention: Introduction to the Special Series","volume":"30","author":"DP Gross","year":"2020","journal-title":"J Occup Rehabil"},{"key":"pone.0308063.ref007","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1007\/s10926-020-09886-y","article-title":"Smart Work Injury Management (SWIM) System: Artificial Intelligence in Work Disability Management","volume":"30","author":"ASK Cheng","year":"2020","journal-title":"J Occup Rehabil"},{"key":"pone.0308063.ref008","article-title":"Comparison of Machine Learning Methods in the Study of Cancer Survivors\u2019 Return to Work: An Example of Breast Cancer Survivors with Work-Related Factors in the CONSTANCES Cohort","author":"M Badreau","journal-title":"J Occup Rehabil. In press"},{"key":"pone.0308063.ref009","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","volume":"14","author":"T van der Ploeg","year":"2014","journal-title":"BMC Med Res Methodol"},{"key":"pone.0308063.ref010","first-page":"10","article-title":"Big data and black-box medical algorithms","author":"WN Price","year":"2018","journal-title":"Science Translational Medicine"},{"key":"pone.0308063.ref011","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1038\/s41467-019-10933-3","article-title":"Estimating the success of re-identifications in incomplete datasets using generative models","volume":"10","author":"L Rocher","year":"2019","journal-title":"Nat Commun"},{"key":"pone.0308063.ref012","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1080\/15265161.2010.494215","article-title":"Is deidentification sufficient to protect health privacy in research?","volume":"10","author":"MA Rothstein","year":"2010","journal-title":"Am J Bioeth"},{"key":"pone.0308063.ref013","unstructured":"Haute Autorit\u00e9 de Sant\u00e9. Le dossier m\u00e9dical en sant\u00e9 au travail. In: Haute Autorit\u00e9 de Sant\u00e9 [Internet]. Jan 2009 [cited 18 Apr 2024]. Available: https:\/\/www.has-sante.fr\/jcms\/c_757826\/fr\/le-dossier-medical-en-sante-au-travail."},{"key":"pone.0308063.ref014","unstructured":"Haute Autorit\u00e9 de Sant\u00e9. Cat\u00e9gories d\u2019informations susceptibles d\u2019\u00eatre int\u00e9gr\u00e9es dans le volet sant\u00e9 au travail du dossier m\u00e9dical partag\u00e9. In: Haute Autorit\u00e9 de Sant\u00e9 [Internet]. Mar 2023 [cited 18 Apr 2024]. Available: https:\/\/www.has-sante.fr\/jcms\/p_3382712\/fr\/categories-d-informations-susceptibles-d-etre-integrees-dans-le-volet-sante-au-travail-du-dossier-medical-partage."},{"key":"pone.0308063.ref015","unstructured":"EUR-Lex. Directive 95\/46\/EC of the European Parliament and of the Council of 24 October 1995 on the protection of individuals with regard to the processing of personal data and on the free movement of such data. OJ L Oct 24, 1995. Available: http:\/\/data.europa.eu\/eli\/dir\/1995\/46\/oj\/eng."},{"key":"pone.0308063.ref016","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/MSEC.2020.2992821","article-title":"Seven Ways to Evaluate the Utility of Synthetic Data","volume":"18","author":"K. El Emam","year":"2020","journal-title":"IEEE Security & Privacy"},{"key":"pone.0308063.ref017","doi-asserted-by":"crossref","first-page":"e23139","DOI":"10.2196\/23139","article-title":"Evaluating Identity Disclosure Risk in Fully Synthetic Health Data: Model Development and Validation","volume":"22","author":"K El Emam","year":"2020","journal-title":"J Med Internet Res"},{"key":"pone.0308063.ref018","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1111\/rssa.12358","article-title":"General and specific utility measures for synthetic data","volume":"181","author":"J Snoke","year":"2018","journal-title":"Journal of the Royal Statistical Society: Series A (Statistics in Society)"},{"key":"pone.0308063.ref019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-023-00771-5","article-title":"Patient-centric synthetic data generation, no reason to risk re-identification in biomedical data analysis","volume":"6","author":"M Guillaudeux","year":"2023","journal-title":"npj Digit Med"},{"key":"pone.0308063.ref020","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1136\/oemed-2016-103678","article-title":"CONSTANCES: a general prospective population-based cohort for occupational and environmental epidemiology: cohort profile","volume":"74","author":"M Goldberg","year":"2017","journal-title":"Occup Environ Med"},{"key":"pone.0308063.ref021","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1093\/annweh\/wxaa015","article-title":"Comparison Between a Job-Exposure Matrix (JEM) Score and Self-Reported Exposures for Carrying Heavy Loads Over the Working Lifetime in the CONSTANCES Cohort","volume":"64","author":"L Ngabirano","year":"2020","journal-title":"Ann Work Expo Health"},{"key":"pone.0308063.ref022","doi-asserted-by":"crossref","first-page":"1879","DOI":"10.1161\/STROKEAHA.119.025454","article-title":"Association Between Reported Long Working Hours and History of Stroke in the CONSTANCES Cohort","volume":"50","author":"M Fadel","year":"2019","journal-title":"Stroke"},{"key":"pone.0308063.ref023","article-title":"Ransomware in Healthcare Facilities: A Harbinger of the Future?","author":"N Spence","year":"2018","journal-title":"Management Faculty Research"},{"key":"pone.0308063.ref024","doi-asserted-by":"crossref","first-page":"e043497","DOI":"10.1136\/bmjopen-2020-043497","article-title":"Can synthetic data be a proxy for real clinical trial data? A validation study","volume":"11","author":"Z Azizi","year":"2021","journal-title":"BMJ Open"}],"updated-by":[{"DOI":"10.1371\/journal.pone.0324790","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000}}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0308063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T13:32:37Z","timestamp":1722432757000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0308063"}},"subtitle":[],"editor":[{"given":"Mir","family":"Ali","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,7,31]]},"references-count":24,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0308063","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,31]]}}}