Early silicosis detection — via a 5 min breath test?

Physicians and scientists from UNSW Sydney are developing a new diagnostic tool that by analysing a person’s breath for signs of silicosis has the potential to catch the disease before irreversible lung damage appears.

Silicosis, an incurable and totally preventable lung disease caused by inhaling tiny crystalline particles of silicon dioxide, is recognised as a major WHS concern in Australia. And it’s a growing concern, too. Recently, cases that extend beyond engineered stone workers — where the Australian Government responded with a ban — to tunnelling and construction workers, have been grabbing headlines.

And there are several other diseases that can arise from silica exposure — including chronic obstructive pulmonary disease, lung fibrosis, lung cancer and autoimmune diseases like rheumatoid arthritis and scleroderma — in addition to silicosis.

“Currently in NSW, workers are increasingly being diagnosed with silicosis at younger ages, reflecting excess dust exposures,” Professor Deborah Yates, Respiratory Physician in the Department of Thoracic Medicine at St Vincent’s Hospital in Sydney and a Conjoint Professor at UNSW Sydney, said.

Yates — together with UNSW Sydney Professor William Alexander Donald — are authors of a timely study published in March 2025 in Journal of Breath Research. It describes a rapid, AI-powered breath test that could transform the way silicosis is diagnosed, potentially catching the disease earlier, rather than waiting for irreversible lung damage to appear.

CT scans of a tunneller diagnosed with silicosis. The light grey areas at the top part of the lungs represent severe scar-tissue. Credit: UNSW Sydney/Deborah Yates

Why early detection matters — problems with existing methods

“There are three stages of silicosis,” Yates said, and it “can be difficult to diagnose such patients, especially in the early stages of disease. Sometimes a biopsy is needed, which is invasive and expensive.” It is therefore crucial to detect affected workers early and remove them from further silica exposure, in order to stop the progression of their disease.

Traditional methods of silicosis detection include CT scans and X-rays, which show the disease at later stages. The high risk of silicosis to the safety of workers, especially in light of new cases emerging from other high-risk industries, have demonstrated an urgent need for better diagnostic tools.

AI-powered breath test — the potential of this diagnostic solution

Using a scientific technique that analyses molecules, known as ‘mass spectrometry’, the test combines this technique with AI to rapidly detect silicosis from breath samples, providing a fast and non-invasive diagnostic tool for at-risk workers. And with the UNSW-developed test, results are provided in minutes.

“Our study shows that the AI-driven model accurately distinguished silicosis patients from healthy individuals based on their breath profiles, providing a reliable tool for early detection,” William Alexander Donald from UNSW’s School of Chemistry said, who is the lead researcher on the recent study.

“This suggests that breath testing could be a practical tool for large-scale worker screening and early intervention.” For the study, breath samples from 31 silicosis patients and 60 healthy controls were analysed, confirming the test’s ability to differentiate between affected and unaffected individuals with high accuracy.

Currently, breath samples are collected in clinics and transported to the lab for analysis, while the researchers noted that future implementation could enable direct, on-site testing. Plus, as a compact benchtop system — occupying less than a cubic metre — the instrument could feasibly be installed in clinical settings for point-of-care testing.

“We’ve now installed this testing at a second site to test its effectiveness with hundreds of at-risk workers, including coal miners to further validate its effectiveness,” Donald said.

Postgraduate student Laura Capasso, Professor William Alexander Donald and study lead author Merryn Baker look at results of breath samples analysed by AI for early detection of silicosis in a UNSW Chemistry laboratory. Credit: UNSW Sydney/Richard Freeman

In less than five minutes — how the test works

“In human breath, there are thousands of organic molecules that you breathe out,” Donald said. And so, when participants breathe into a bag using, this technology means that all the different molecules present are detected when the breath content gets pushed to a mass spectrometer.

The instrument can make a profile of “someone’s breath, and then we feed that into an artificial intelligence algorithm that’s really good at finding patterns,” Donald said. “In this case, it’s looking for patterns in the organic compounds that are present in the breath of people in the early stages of silicosis. And we’re getting very high accuracies, like over 90% accuracy, for just such a simple, non-invasive breath test.”

Donald added: “By combining advanced chemical analysis techniques with AI, it means we can now detect silicosis in minutes rather than waiting for irreversible lung damage to appear on scans.” In less than five minutes for the entire breath sampling and analysis process, this means the tool is potentially suitable for routine screening of at-risk workers.

Further validations needed — where to from here?

Silicosis has no cure and is fatal in its worst stages. Lung transplantation is a rare option for silicosis, but is a scarce resource and not every patient is suitable, which makes early detection of vital importance. But, while this breath test shows considerable promise, as the researchers stress, it needs further validation in larger cohorts before it can be implemented as a routine screening tool.

Future studies will refine the technique, integrate it into screening programs for silica-exposed workers and explore its ability to differentiate silicosis from other lung diseases. “Breath testing is a new and simple technique for patients and doctors but has been valuable in other lung diseases such as asthma,” Yates said.

“It could provide the non-invasive method needed to monitor such workers for development of silicosis. Although this research is yet in its early stages and will need further development, it provides a ‘breath of hope’ for the future.”

Top image caption: Merryn Baker and Laura Capasso at a clinic in Sydney where engineered stone worker Angus Read provides a breath sample to be analysed for signs of silicosis. Credit: UNSW Sydney/Richard Freeman