Steven J Wurzelbacher1, Alysha R Meyers2, Michael P Lampl3, P Timothy Bushnell4, Stephen J Bertke5, David C Robins6, Chih-Yu Tseng7, Steven J Naber8. 1. National Institute for Occupational Safety and Health, 1090 Tusculum Ave, Cincinnati, OH 45226-1998, United States. Electronic address: Srw3@cdc.gov. 2. National Institute for Occupational Safety and Health, 1090 Tusculum Ave, Cincinnati, OH 45226-1998, United States. Electronic address: itm4@cdc.gov. 3. Ohio Bureau of Workers' Compensation, 30 W Spring St Ste L1, Columbus, OH 43215, United States. Electronic address: Michael.L.1@bwc.state.oh.us. 4. National Institute for Occupational Safety and Health, 1090 Tusculum Ave, Cincinnati, OH 45226-1998, United States. Electronic address: plb4@cdc.gov. 5. National Institute for Occupational Safety and Health, 1090 Tusculum Ave, Cincinnati, OH 45226-1998, United States. Electronic address: inh4@cdc.gov. 6. Ohio Bureau of Workers' Compensation, 30 W Spring St Ste L1, Columbus, OH 43215, United States. Electronic address: David.R.1@bwc.state.oh.us. 7. National Institute for Occupational Safety and Health, 1090 Tusculum Ave, Cincinnati, OH 45226-1998, United States. Electronic address: cft8@cdc.gov. 8. Ohio Bureau of Workers' Compensation, 30 W Spring St Ste L1, Columbus, OH 43215, United States. Electronic address: Steven.N.1@bwc.state.oh.us.
Abstract
INTRODUCTION: This study analyzed workers' compensation (WC) claims among private employers insured by the Ohio state-based WC carrier to identify high-risk industries by detailed cause of injury. METHODS: A machine learning algorithm was used to code each claim by U.S. Bureau of Labor Statistics (BLS) event/exposure. The codes assigned to lost-time (LT) claims with lower algorithm probabilities of accurate classification or those LT claims with high costs were manually reviewed. WC data were linked with the state's unemployment insurance (UI) data to identify the employer's industry and number of employees. BLS data on hours worked per employee were used to estimate full-time equivalents (FTE) and calculate rates of WC claims per 100 FTE. RESULTS: 140,780 LT claims and 633,373 medical-only claims were analyzed. Although counts and rates of LT WC claims declined from 2007 to 2017, the shares of leading LT injury event/exposures remained largely unchanged. LT claims due to Overexertion and Bodily Reaction (33.0%) were most common, followed by Falls, Slips, and Trips (31.4%), Contact with Objects and Equipment (22.5%), Transportation Incidents (7.0%), Exposure to Harmful Substances or Environments (2.8%), Violence and Other Injuries by Persons or Animals (2.5%), and Fires and Explosions (0.4%). These findings are consistent with other reported data. The proportions of injury event/exposures varied by industry, and high-risk industries were identified. CONCLUSIONS: Injuries have been reduced, but prevention challenges remain in certain industries. Available evidence on intervention effectiveness was summarized and mapped to the analysis results to demonstrate how the results can guide prevention efforts. Practical Applications: Employers, safety/health practitioners, researchers, WC insurers, and bureaus can use these data and machine learning methods to understand industry differences in the level and mix of risks, as well as industry trends, and to tailor safety, health, and disability prevention services and research. Published by Elsevier Ltd.
INTRODUCTION: This study analyzed workers' compensation (WC) claims among private employers insured by the Ohio state-based WC carrier to identify high-risk industries by detailed cause of injury. METHODS: A machine learning algorithm was used to code each claim by U.S. Bureau of Labor Statistics (BLS) event/exposure. The codes assigned to lost-time (LT) claims with lower algorithm probabilities of accurate classification or those LT claims with high costs were manually reviewed. WC data were linked with the state's unemployment insurance (UI) data to identify the employer's industry and number of employees. BLS data on hours worked per employee were used to estimate full-time equivalents (FTE) and calculate rates of WC claims per 100 FTE. RESULTS: 140,780 LT claims and 633,373 medical-only claims were analyzed. Although counts and rates of LT WC claims declined from 2007 to 2017, the shares of leading LT injury event/exposures remained largely unchanged. LT claims due to Overexertion and Bodily Reaction (33.0%) were most common, followed by Falls, Slips, and Trips (31.4%), Contact with Objects and Equipment (22.5%), Transportation Incidents (7.0%), Exposure to Harmful Substances or Environments (2.8%), Violence and Other Injuries by Persons or Animals (2.5%), and Fires and Explosions (0.4%). These findings are consistent with other reported data. The proportions of injury event/exposures varied by industry, and high-risk industries were identified. CONCLUSIONS: Injuries have been reduced, but prevention challenges remain in certain industries. Available evidence on intervention effectiveness was summarized and mapped to the analysis results to demonstrate how the results can guide prevention efforts. Practical Applications: Employers, safety/health practitioners, researchers, WC insurers, and bureaus can use these data and machine learning methods to understand industry differences in the level and mix of risks, as well as industry trends, and to tailor safety, health, and disability prevention services and research. Published by Elsevier Ltd.
Authors: K D Rosenman; J C Gardiner; J Wang; J Biddle; A Hogan; M J Reilly; K Roberts; E Welch Journal: J Occup Environ Med Date: 2000-01 Impact factor: 2.162
Authors: Kaori Fujishiro; Jean L Weaver; Catherine A Heaney; Christopher A Hamrick; William S Marras Journal: Am J Ind Med Date: 2005-11 Impact factor: 2.214
Authors: Steven J Wurzelbacher; Ibraheem S Al-Tarawneh; Alysha R Meyers; P Timothy Bushnell; Michael P Lampl; David C Robins; Chih-Yu Tseng; Chia Wei; Stephen J Bertke; Jill A Raudabaugh; Thomas M Haviland; Teresa M Schnorr Journal: Am J Ind Med Date: 2016-09-26 Impact factor: 2.214
Authors: Hope M Tiesman; Melody Gwilliam; Jeff Rojek; Scott Hendricks; Brian Montgomery; Geoff Alpert Journal: Am J Ind Med Date: 2019-08-05 Impact factor: 2.214
Authors: Santosh K Verma; Wen Ruey Chang; Theodore K Courtney; David A Lombardi; Yueng-Hsiang Huang; Melanye J Brennan; Murray A Mittleman; James H Ware; Melissa J Perry Journal: Occup Environ Med Date: 2010-10-08 Impact factor: 4.402
Authors: Steven J Wurzelbacher; Stephen J Bertke; Michael P Lampl; P Timothy Bushnell; David C Robins; Steven J Naber; Libby L Moore Journal: J Occup Environ Med Date: 2022-02-01 Impact factor: 2.306