Study published in The Journal of Thoracic and Cardiovascular Surgery indicates OneBreath™ technology can help diagnose and predict pneumonia from a single exhale.
"Exhaled breath is an extraordinary diagnostic medium," said Ivan Lo, CEO of Breath Diagnostics. "This study suggests our OneBreath™ technology can help identify disease before symptoms appear."
LOUISVILLE, Ky., Aug. 27, 2025 -- Breath Diagnostics, Inc. (the "Company"), developer of the patented OneBreath™ technology, which transforms a single exhale into powerful diagnostic data, is pleased to announce the results of a peer-reviewed clinical study (the "Study") published in The Journal of Thoracic and Cardiovascular Surgery. The Study indicates the Company's proprietary breath analysis technology, coupled with (AI) machine learning, can both diagnose and predict the onset of pneumonia in patients undergoing elective cardiac surgery.
The Study represents one of the first demonstrations that volatile organic compounds (VOCs) measured in exhaled breath can reliably serve as biomarkers for future disease, paving the way for earlier intervention, reduced complications, cost savings for healthcare systems, and a new era of predictive, non-invasive medicine.
Study Design and Methods
The prospective study enrolled 75 patients undergoing elective cardiac surgery. Breath samples were collected using a Tedlar bag system with microchip capture of carbonyl compounds, followed by ultra-high-performance liquid chromatography mass spectrometry for compound identification.
- Samples were taken preoperatively, within 24 hours postoperatively, and every three days during hospitalization.
- Carbonyl VOC profiles were analyzed using advanced machine learning workflows, including feature selection, random forest, and boosted generalized linear models.
- The diagnostic model was trained on perioperative VOC samples, while a separate predictive model was trained using only preoperative breath samples to assess risk before pneumonia onset.
Results
Out of the 75 patients, 10 developed postoperative pneumonia — one of the most serious and costly complications after cardiac surgery.
- Diagnosis model performance: The model achieved an AUROC of 0.833 and PRAUC of 0.818 on the test set.
- Prediction model performance: Using only baseline preoperative breath samples, key VOCs predicted pneumonia onset with the same AUROC of 0.833 and PRAUC of 0.818.
- Importantly, the predictive model identified high-risk patients days before clinical symptoms emerged, enabling the potential early interventions.
"These findings are highly significant," said Dr. Victor van Berkel, Chief Medical Officer and Co-Founder of Breath Diagnostics and co-author of the Study. "Our study demonstrated not only that pneumonia can be diagnosed earlier than with current clinical methods, but also that its onset can be predicted before symptoms appear. This capability could transform postoperative care and outcomes for cardiac surgery patients, and potentially for those undergoing other major surgeries as well."
The study was conducted at the University of Louisville and published in The Journal of Thoracic and Cardiovascular Surgery. Among the authors, Dr. Victor van Berkel, Chief Medical Officer and Co-Founder of Breath Diagnostics, and Dr. Xiao An Fu, Co-Founder of the Company, contributed to the work.
Implications for Predictive Medicine and The Healthcare Industry
Pneumonia develops in 6–20% of patients following elective cardiac surgery, making it one of the most frequent and serious postoperative complications. It is strongly associated with longer ICU stays, extended hospitalizations, higher costs, and increased mortality. Despite decades of research, preventive strategies such as prophylactic antibiotics have produced inconsistent results, largely because clinicians lack a reliable way to identify which patients are truly at risk.
Until now, there has been no reliable, non-invasive way to predict who will develop the condition. This study marks the first time that VOC breath analysis, paired with machine learning, has demonstrated the ability not only to diagnose but also to predict disease onset days in advance.
Breath Diagnostics' OneBreath™ platform offers:
- Non-invasive testing independent of patient history or comorbidities
- Rapid, repeatable sampling suitable for perioperative and ICU monitoring
- Scalable integration with machine learning to continuously refine predictive accuracy
By detecting VOC signatures associated with inflammation, oxidative stress, and bacterial metabolism, this approach could be extended to a range of diseases — from lung infections to cancer and inflammatory disorders.
"Exhaled breath is an extraordinary diagnostic medium that has only begun to be tapped," said Ivan Lo, CEO of Breath Diagnostics. "This study demonstrates that with our OneBreath™ technology, combined with advanced data science, breath can serve as a reliable biomarker for predicting disease before symptoms appear. The implications go far beyond pneumonia. Our platform is among the most clinically validated breath technologies for lung cancer detection, with 94% sensitivity and 85% specificity across multiple independent sites and stages of disease. We believe OneBreath™ has the potential to become a first line of defense in identifying disease at its earliest stages, helping physicians make more informed decisions sooner."
Next Steps
Breath Diagnostics will build on these results by expanding clinical validation into larger, multi-center patient cohorts to further confirm the predictive value of exhaled breath biomarkers. The Company is also working with leading academic and clinical partners to refine study protocols, with the goal of pursuing regulatory clearances in the United States and select international markets. These efforts will represent an important step toward the Company's long-term goal of integrating predictive breath tests into hospital and surgical settings, where early detection may reduce complications and healthcare costs, and improve clinical decision-making.
About Breath Diagnostics
Breath Diagnostics, Inc. is a medical technology company pioneering non-invasive diagnostics through exhaled breath analysis. By combining proprietary microchips, advanced machine learning algorithms, and high-performance liquid chromatography mass spectrometry, the Company is developing a new platform for early disease prediction and diagnosis.
This News is brought to you by Qube Mark, your trusted source for the latest updates and insights in marketing technology. Stay tuned for more groundbreaking innovations in the world of technology.
