Mining Contract: Integration of RCMD and RCS Physicochemistry and Toxicity Outcomes in an Occupational Risk Assessment Model

Contract # 75D30121C12182
Start Date 9/1/2021
Research Concept

Predicting which miners will eventually develop lung diseases over time and delineating risk factors in the industry is a formidable challenge. Despite several studies on respirable coal mine dust and respirable silica dust exposure and health risks, the data are still too limited to allow for conclusions on lung disease causes in the mine worker population. Furthermore, there is currently no established risk model for occupational dust exposure and subsequent lung disease risk. Establishment of a valid model could help to identify high-risk miners for early intervention.

Contract Status & Impact

This contract is ongoing. For more information on this contract, send a request to

Under this contract, researchers will use an interdisciplinary approach, including mining engineering, environmental chemistry, environmental toxicology, molecular epidemiology, and machine learning expertise, to investigate respirable coal mine dust (RCMD) and respirable silica dust (RCS) dust toxicity based on particle characteristics and exposure dose. Ultimately, this work will establish a model with risk factors contributing to the long-term health outcomes in coal miners.

Investigators will develop a risk assessment model using an innovative machine learning (ML) approach to assess the susceptibility of coal miners to development of coal workers' pneumoconiosis (CWP). To achieve the overarching goal, researchers will pursue the following tasks:

  1. Conduct characterization studies (i.e., size, shape, surface area, mineralogy, elemental components) on RCMD and RCS samples.
  2. Investigate RCMD and RCS toxicity using simulated lung fluid and in vitro toxicity comparisons of respirable dust.
  3. Establish a comprehensive mine- , dust- , and health-specific database and identify potential risk factors contributing or leading to CWP development.
  4. Integrate risk factors associated with CWP in a risk assessment model using innovative machine learning techniques.
Page last reviewed: February 24, 2023
Page last updated: February 24, 2023