Analysis of workers’ compensation claims data for machine‐related injuries in metal fabrication businesses

Abstract

Despite limitations, workers' compensation data were useful in characterizing machine-related injuries. Improving the quality of data collected by insurers would enhance occupational injury surveillance and prevention efforts. Am. J. Ind. Med. 59:656-664, 2016. © 2016 Wiley Periodicals, Inc.

Applying Machine Learning to Workers’ Compensation Data to Identify Industry-Specific Ergonomic and Safety Prevention Priorities

“…35 SAS code and word probabilities used for auto-coding have been shared with other researchers and health departments with some success. 48–50 For example, Yamin et al 48 used the three intervention category auto-coding program on 4268 WC claims in the metal manufacturing sub-sector to identify OTH WC claims for manual review.…”

“…Other researchers and public health practitioners have had some success using our SAS auto-coding program and word probabilities from unstructured narrative text information from first reports of injury data. 48–50…”

Workers′ compensation reported injuries among distillery industry workers, 2010–2019

“…To our knowledge, there are no previous reports of work‐related injury among distillery workers in the literature. However, other studies have sought to examine the frequency of injury, cost of injury, lost time, task performed before injury, and percent of disability through the use of workers′ compensation data 16–20 . Such studies were conducted to identify factors associated with occupational injuries, determine the subsequent monetary and physical consequences, and put forth recommendations for prevention.…”

“…However, other studies have sought to examine the frequency of injury, cost of injury, lost time, task performed before injury, and percent of disability through the use of workers′ compensation data. [16][17][18][19][20] The variables job tenure, season of injury, month of injury, day of week injury occurred, and year of injury were created using the hire date, injury date, and last work date variables. The county of injury variable was excluded to protect worker confidentiality.…”