{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,15]],"date-time":"2026-11-15T06:27:53Z","timestamp":1794724073754,"version":"4.9.1"},"reference-count":23,"publisher":"BMJ","issue":"11","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"unspecified","delay-in-days":27,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,11,12]]},"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop a machine learning (ML)-based predictive model to determine the key predictors of dissatisfaction after occupational injury (OI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>A retrospective cohort study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Nationwide 5-year panel data (2018\u20132022) from the Panel Study of Workers\u2019 Compensation Insurance in South Korea.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>A total of 2298 workers who completed compensation-related medical care in 2017.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Predictive modelling was conducted with extreme gradient (XG) Boost, light gradient boosting machine (GBM), CatBoost and random forest. SHapley Additive Explanations (SHAPs) analysis was conducted to interpret the feature importance. Further, logistic regression was conducted for comparison.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary outcome measures<\/jats:title>\n                    <jats:p>This study evaluated postinjury satisfaction among workers using survey items associated with satisfaction levels. We adopted a 5-year follow-up period.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of the 2298 participants, 570 were dissatisfied. The logistic regression model indicated that dissatisfaction was significantly associated with unemployment (adjusted OR (aOR) 1.701; 95% CI: 1.296 to 2.233), lack of private health insurance (aOR 1.347; 95%\u2009CI 1.042 to 1.741) and lower perceived socioeconomic status (aOR 2.097; 95%\u2009CI 1.109 to 3.965). Among the ML models, light GBM exhibited the highest area under the receiver operating characteristics curve (0.770 (95% CI 0.718 to 0.819)), followed by CatBoost (0.768 (95% CI 0.718 to 0.815)), random forest (0.766 (95% CI 0.715 to 0.814)) and XGBoost (0.765 (95% CI 0.717 to 0.811)). The SHAP analysis demonstrated the total number of household members, extent of pain interference with daily life, perceived health status before injury and financial factors as the strongest predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed and demonstrated robust predictive performance of an ML-based model for determining dissatisfaction after OI. The key features included employment status, financial stability, chronic pain and cognitive function, highlighting the multifaceted nature of worker satisfaction.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-103321","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:34Z","timestamp":1764355234000},"page":"e103321","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Machine learning-based prediction of dissatisfaction after occupational injury: a retrospective cohort study using the nationwide Korean workers\u2019 compensation insurance database"],"prefix":"10.1136","volume":"15","author":[{"given":"Youjin","family":"Lee","sequence":"first","affiliation":[{"name":"Pohang Stroke and Spine Hospital, Pohang-si, Korea (the Republic of)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taeyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Pohang Stroke and Spine Hospital, Pohang-si, Korea (the Republic of)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahyeon","family":"Koo","sequence":"additional","affiliation":[{"name":"Pohang Stroke and Spine Hospital, Pohang-si, Korea (the Republic of)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1288-470X","authenticated-orcid":false,"given":"Dougho","family":"Park","sequence":"additional","affiliation":[{"name":"Pohang Stroke and Spine Hospital, Pohang-si, Korea (the Republic of)"},{"name":"Pohang University of Science and Technology, Pohang-si, Korea (the Republic of)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,11,28]]},"reference":[{"key":"2026111421185898000_15.11.e103321.1","doi-asserted-by":"crossref","first-page":"102391","DOI":"10.1016\/j.jflm.2022.102391","article-title":"The impact of major occupational injuries on professional reintegration. A Portuguese medico-legal contribution","volume":"90","author":"Almeida","year":"2022","journal-title":"J Forensic Leg Med"},{"key":"2026111421185898000_15.11.e103321.2","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.3346\/jkms.2013.28.11.1581","article-title":"Return-to-work according to impairment type among occupationally injured workers in Korea","volume":"28","author":"Rhie","year":"2013","journal-title":"J Korean Med Sci"},{"key":"2026111421185898000_15.11.e103321.3","doi-asserted-by":"publisher","DOI":"10.1097\/01.jom.0000250491.37986.b6"},{"key":"2026111421185898000_15.11.e103321.4","doi-asserted-by":"crossref","DOI":"10.1186\/s40557-018-0260-x","article-title":"Satisfaction with life and the risk of occupational injury","volume":"30","author":"Park","year":"2018","journal-title":"Ann Occup Environ Med"},{"key":"2026111421185898000_15.11.e103321.5","doi-asserted-by":"crossref","first-page":"2164","DOI":"10.1016\/j.apmr.2022.01.159","article-title":"Factors Associated With High and Low Life Satisfaction 10 Years After Traumatic Brain Injury","volume":"103","author":"O\u2019Neil-Pirozzi","year":"2022","journal-title":"Arch Phys Med Rehabil"},{"key":"2026111421185898000_15.11.e103321.6","doi-asserted-by":"publisher","DOI":"10.2106\/JBJS.G.00492"},{"key":"2026111421185898000_15.11.e103321.7","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s10728-020-00420-y","article-title":"The Satisfaction with Life Scale: Philosophical Foundation and Practical Limitations","volume":"29","author":"Kusier","year":"2021","journal-title":"Health Care Anal"},{"key":"2026111421185898000_15.11.e103321.8","doi-asserted-by":"publisher","DOI":"10.1007\/S00167-022-06896-6\/FIGURES\/1"},{"key":"2026111421185898000_15.11.e103321.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.061"},{"key":"2026111421185898000_15.11.e103321.10","doi-asserted-by":"crossref","unstructured":"Lee J , Kim HR . Prediction of Return-to-original-work after an Industrial Accident Using Machine Learning and Comparison of Techniques. J Korean Med Sci 2018;33. doi:10.3346\/jkms.2018.33.e144","DOI":"10.3346\/jkms.2018.33.e144"},{"key":"2026111421185898000_15.11.e103321.11","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1097\/j.pain.0000000000003087","article-title":"Machine learning-based identification of determinants for rehabilitation success and future healthcare use prevention in patients with high-grade, chronic, nonspecific low back pain: an individual data 7-year follow-up analysis on 154,167 individuals","volume":"165","author":"Niederer","year":"2024","journal-title":"Pain"},{"key":"2026111421185898000_15.11.e103321.12","doi-asserted-by":"crossref","DOI":"10.4178\/epih.e2024071","article-title":"Data profile: the Korean Workers\u2019 Compensation-National Health Insurance Service (KoWorC-NHIS) cohort","volume":"46","author":"Min","year":"2024","journal-title":"Epidemiol Health"},{"key":"2026111421185898000_15.11.e103321.13","doi-asserted-by":"crossref","DOI":"10.3389\/frobt.2024.1444763","article-title":"Enhancing interpretability and accuracy of AI models in healthcare: a comprehensive review on challenges and future directions","volume":"11","author":"Ennab","year":"2024","journal-title":"Front Robot AI"},{"key":"2026111421185898000_15.11.e103321.14","doi-asserted-by":"crossref","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development","volume":"17","author":"Ponce-Bobadilla","year":"2024","journal-title":"Clin Transl Sci"},{"key":"2026111421185898000_15.11.e103321.15","doi-asserted-by":"crossref","DOI":"10.3346\/jkms.2023.38.e284","article-title":"Self-Esteem Trajectories After Occupational Injuries and Diseases and Their Relation to Changes in Subjective Health: Result From the Panel Study of Workers\u2019 Compensation Insurance (PSWCI)","volume":"38","author":"Baek","year":"2023","journal-title":"J Korean Med Sci"},{"key":"2026111421185898000_15.11.e103321.16","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1007\/s00127-016-1299-z","article-title":"The impact of psychological factors on recovery from injury: a multicentre cohort study","volume":"52","author":"Kellezi","year":"2017","journal-title":"Soc Psychiatry Psychiatr Epidemiol"},{"key":"2026111421185898000_15.11.e103321.17","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.shaw.2021.10.001","article-title":"Positive Factors for Return to Work After Accidents: Health Awareness, Consultation with Doctors, and Personal Characteristics of Workers","volume":"13","author":"Kang","year":"2022","journal-title":"Saf Health Work"},{"key":"2026111421185898000_15.11.e103321.18","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.jht.2021.06.008","article-title":"Predictive factors for return to work or study and satisfaction in traumatic brachial plexus injury individuals undergoing rehabilitation: A retrospective follow-up study of 101 cases","volume":"36","author":"Gushikem","year":"2023","journal-title":"J Hand Ther"},{"key":"2026111421185898000_15.11.e103321.19","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyg.2023.1148634","article-title":"Psychosocial risks emerged from COVID-19 pandemic and workers\u2019 mental health","volume":"14","author":"Koren","year":"2023","journal-title":"Front Psychol"},{"key":"2026111421185898000_15.11.e103321.20","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-36493-7","article-title":"Lessons on the COVID-19 pandemic: who are the most affected","volume":"13","author":"Xie","year":"2023","journal-title":"Sci Rep"},{"key":"2026111421185898000_15.11.e103321.21","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1007\/s10462-023-10561-w","article-title":"Machine and deep learning for longitudinal biomedical data: a review of methods and applications","volume":"56","author":"Cascarano","year":"2023","journal-title":"Artif Intell Rev"},{"key":"2026111421185898000_15.11.e103321.22","doi-asserted-by":"crossref","first-page":"672","DOI":"10.3390\/app15020672","article-title":"C-SHAP: A Hybrid Method for Fast and Efficient Interpretability","volume":"15","author":"Ranjbaran","year":"2025","journal-title":"Appl Sci (Basel)"},{"key":"2026111421185898000_15.11.e103321.23","doi-asserted-by":"publisher","DOI":"10.1504\/IJBHR.2011.043414"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-103321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,15]],"date-time":"2026-11-15T05:23:07Z","timestamp":1794720187000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-103321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":23,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11,28]]},"published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1136\/bmjopen-2025-103321"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-103321","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1136\/bmjopen-2025-103321.supp2","asserted-by":"subject"},{"id-type":"doi","id":"https:\/\/doi.org\/10.1136\/bmjopen-2025-103321.supp1","asserted-by":"subject"}]},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}