University of Edinburgh blood test identifies breast cancer signs

17 Dec 2024

Raman spectroscopy plus machine learning points to effective screening for multiple cancers.

A technique developed by the University of Edinburgh and partners could improve early detection and monitoring of breast cancer.

Combining Raman spectroscopy (RS) and machine learning allows the method to spot subtle changes in the bloodstream that occur during the initial phases of the disease, according to the project.

Published in Journal of Biophotonics, the new approach indicates the value of a non-invasive, personalized approach for early detection and monitoring of disease progression.

Standard tests for breast cancer can include a physical examination, x-ray or ultrasound scans or biopsy analysis of a sample of breast tissue, but at present early detection strategies rely upon screening people based on age or at-risk status, noted the Edinburgh team.

The project aimed to improve matters by using Raman analysis to detect biomarkers associated with cancer, exploiting the technique's ability to reveal subtle differences in chemical composition caused by diseases.

Existing applications of RS to this task had suggested that the technique can distinguish between breast cancer patients and healthy controls with high accuracy, but those earlier studies had not differentiated between stages of development of individual cancers.

This pooling in previous studies "could mask stage-specific spectral variations that are critical for understanding the progression and treatment of breast cancer," noted the project in its paper.

Early detection for more successful treatment

In a pilot study, the Edinburgh team took blood plasma from stage Ia breast cancer patients and used RS to classify four major breast cancer sub-types. Machine learning then played a key role in analyzing the data, identifying similar features and helping to classify samples from their Raman spectral response.

"To the best of our knowledge, this study is the first of its kind to utilize RS and machine learning to classify Luminal A, Luminal B, HER2-enriched and Triple Negative Breast Cancer (TNBC) at stage Ia," said the team in its paper.

Results showed that the technique was 98 per cent effective at identifying breast cancer at stage Ia, and could also distinguish between each of the four sub-types of breast cancer with an accuracy of more than 90 per cent. This could enable patients to receive more effective, personalized treatment.

Implementing this as a screening test would help identify more people in the earliest stages of breast cancer and improve the chances of treatment being successful. The project next aims to expand the work to involve more participants, and include tests for early forms of other cancer types.

"Most deaths from cancer occur following a late-stage diagnosis after symptoms become apparent, so a future screening test for multiple cancer types could find these at a stage where they can be far more easily treated," said Andy Downes from the University of Edinburgh.

"Early diagnosis is key to long-term survival, and we finally have the technology required. We just need to apply it to other cancer types and build up a database, before this can be used as a multi-cancer test."