AI innovation supports screening for 2.2 million US workers exposed to toxic dust
From coal miners and construction crews to engineered stone countertop fabricators and foundry workers, more than 2.2 million U.S. workers inhale fine particles of rock, sand or coal every day on the job. After years of exposure, trapped dust can cause thick scar tissue to build up inside the lungs, leading to long-term lung damage commonly known as black lung or silicosis.
Every day, over 2.2 million U.S. workers, including coal miners, construction crews, fabricators of engineered stone countertops, and foundry workers, inhale fine particles of rock, sand or coal at their job sites. Prolonged exposure to these particles can cause thick scar tissue to form in the lungs, leading to a condition known as black lung or silicosis.
Early diagnosis of this lung disease is crucial, as it allows organizations to provide proper care for affected employees, enabling them to transition to safer roles before the disease worsens and impacts their health severely.
Currently, there are only 200 B readers in the U.S. - specialized physicians responsible for reviewing the X-rays - making it challenging for workers to receive timely care. To address this shortage and provide faster protection, researchers at Michigan State University (MSU) developed a specialized dataset of U.S. worker scans to train an AI program.
This tool, the first of its kind, uses images from U.S. workers, providing an objective second opinion to help doctors catch early signs of lung disease and preventing further damage.
Kenneth Rosenman, chief of the Division of Occupational and Environmental Medicine at MSU, emphasized the importance of early screening, stating that if a worker's lung disease goes undetected due to screening delays, they may remain in a high-dust environment, and their lungs will continue to scar. By catching the disease at an early stage, employers can remove workers from dangerous dust environments and reduce the likelihood of their lung disease progressing.
Early screening is essential to ensure workplace dust controls are effective and protect workers' health before lung damage becomes life-threatening.
The AI program demonstrated high accuracy in identifying and clearing half of all normal X-rays, removing healthy scans from the queue so human experts can focus on workers showing early signs of illness. Additionally, the software achieved 91% accuracy in spotting the earliest signs of lung scarring, outperforming human readers who averaged 77% accuracy.
The program also overlays a simple color map on the X-ray image, helping doctors see where early lung damage was detected, providing fast reviews as second opinions for B readers and ensuring workers receive earlier results and documentation.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
