June 2021
Volume 73    Issue 6

Identifying risk factors from MSHA accidents and injury data using logistic regression

Amoako, Richard; Buaba, Judith; Brickey, Andrea


This study applies a machine-learning technique known as multiclass logistic regression on a 10-year injury dataset from the U.S. Mine Safety and Health Administration (MSHA) to determine miners’ susceptibility to injury and to help identify significant risk factors associated with different classes of injury. The analysis identifies specific risk factors that influence a mineworker’s susceptibility to a given class of injury: nonfatal with no days lost or restricted activity; nonfatal with days lost and/or days of restricted work activity; and fatal and total permanent or partial permanent disability. These factors include miner’s age, mine type (coal versus noncoal), experience on the current job (years), shift start time, employment type (operator versus contractor), mining district and type of accident. The results of the analysis indicate that a miner’s experience on the job (the number of years worked in a current job) is a significant risk to injury occurrence, even for those with decades of total mining experience.

Full-text paper:
Mining, Metallurgy & Exploration (2021) 38:509–527, https://doi.org/10.1007/s42461-020-00347-x


Follow these easy steps if you are an SME member:
  • Go to www.smenet.org/login . Sign in with your email address and password.
  • Hover your mouse over “Publications and Resources” in the top banner. Click on “Mining, Metallurgy & Exploration (MME) Journal” in the pull-down menu.
  • Scroll down and click on the “Read the MME Journal Online” button, which will take you to the Springer site as an SME member who is eligible for free access. (To see published papers on the Springer site, click on “Browse Volumes & Issues” in the blue banner.)
If you are not an SME member, go to https://www.springer.com/engineering/journal/42461 for paid access. Or join SME at www.smenet.org/join