# Breathprints for Breast Cancer: Evaluating a Non-Invasive Approach to BI-RADS 4 Risk Stratification in a Preliminary Study

## TL;DR

A breath test could help avoid unnecessary breast cancer biopsies by identifying high-risk cases non-invasively.

## Contribution

This study introduces breath analysis as a potential non-invasive tool for BI-RADS 4 risk stratification in breast cancer screening.

## Key findings

- The breath test model achieved 88% sensitivity and 75% specificity in distinguishing cancerous from benign cases.
- The high negative predictive value (97%) suggests breath analysis could reliably rule out cancer in BI-RADS 4 cases.
- Results were consistent across BI-RADS 4 subcategories, especially effective in higher-risk groups.

## Abstract

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.

Background/Objectives: Breast cancer is the most common malignancy among women, and early detection is critical for improving outcomes. The Breast Imaging Reporting and Data System (BI-RADS) standardizes reporting, but the BI-RADS 4 category presents a major challenge, with malignancy risk ranging from 2% to 95%. Consequently, most women in this category undergo biopsies that ultimately prove unnecessary. This study evaluated whether exhaled breath analysis could distinguish malignant from benign findings in BI-RADS 4 patients. Methods: Participants referred to the McGill University Health Centre Breast Center with BI-RADS 3–5 findings provided multiple breath specimens. Breathprints were captured using an electronic nose (eNose) powered breathalyzer, and diagnoses were confirmed by imaging and pathology. An autoencoder-based model fused the breath data with BI-RADS scores to predict malignancy. Model performance was assessed using repeated cross-validation with ensemble voting, prioritizing sensitivity to minimize false negatives. Results: The breath specimens of eighty-five participants, including sixty-eight patients with biopsy-confirmed benign lesions and seventeen patients with biopsy-confirmed breast cancer within the BI-RADS 4 cohort were analyzed. The model achieved a mean sensitivity of 88%, specificity of 75%, and a negative predictive value (NPV) of 97%. Results were consistent across BI-RADS 4 subcategories, with particularly strong sensitivity in higher-risk groups. Conclusions: This proof-of-concept study shows that exhaled breath analysis can reliably differentiate malignant from benign findings in BI-RADS 4 patients. With its high negative predictive value, this approach may serve as a non-invasive rule-out tool to reduce unnecessary biopsies, lessen patient burden, and improve diagnostic decision-making. Larger, multi-center studies are warranted.