January 18, 2026

E10 - Breathprints for Breast Cancer Risk

10 minutes

E10 | 11 min | Latest | Publication Link

Podcast based on: Masilamani, A.P.; Hooper, J.K.; Rahman, M.H.; Philip, R.; Kaushik, P.; Graham, G.; Yockell-Lelievre, H.; Khomami Abadi, M.; Meterissian, S.H. Breathprints for Breast Cancer: Evaluating a Non-Invasive Approach to BI-RADS 4 Risk Stratification in a Preliminary Study. Cancers 2026, 18, 226. https://doi.org/10.3390/cancers18020226

Type: Article | Publication date: 11 January 2026

Summary: Breast cancer screening often identifies findings that are suspicious but uncertain, especially those labeled as BI-RADS 4. While doctors usually recommend a biopsy for these cases, most turn out to be benign, meaning many women go through an invasive procedure unnecessarily. This study explored whether a simple breath test could help better identify high-risk patients. By analyzing patterns of natural chemicals in exhaled breath, we trained a computer model to distinguish between cancerous and non-cancerous findings. The model was able to correctly identify most cancers while also giving strong reassurance when no cancer was present. These results suggest that a breath test could be used alongside mammography to provide patients and doctors with clearer information. If confirmed in larger studies, this approach could spare many women from unnecessary biopsies, lower healthcare costs, and improve trust in breast cancer screening.

Keywords: breast cancer; BI-RADS 4; breath analysis; volatile organic compounds (VOCs); digital olfaction (electronic nose); chemiresistive sensor array; machine learning; multi-modal fusion; autoencoder; risk stratification; rule-out diagnostics

Disclaimer:

This podcast provides a synthetically generated voice summary and discussion of scientific publications. The views expressed do not represent the views of the original authors, journals, or publishers. This podcast uses AI-assisted summaries, so it may or may not introduce inaccuracies or omit important details. Listeners are strongly encouraged to consult the original publications or sources for full context and accuracy. This podcast is for educational and informational purposes only and does not constitute clinical advice, medical guidance, or recommendations. The creators of this podcast are not liable for any errors, omissions, or outcomes resulting from the use of the information provided.

...more