First AI-Powered Blood Test Identifies Patients in Earliest Stage of Breast Cancer

Current early detection strategies often rely on screening based on age or risk factors. Now, a new method promises to enhance early detection and monitoring of breast cancer, potentially leading to a screening test for multiple types of cancer.

Developed by researchers at The University of Edinburgh (Scotland, UK), the new screening method combines laser analysis with artificial intelligence (AI). This innovative approach is the first to detect breast cancer at its earliest stage, known as stage 1a, which is undetectable with current tests. The method uses Raman spectroscopy, a laser analysis technique, paired with machine learning, a form of AI. While similar techniques have been trialed for other cancers, they could only detect disease starting at stage two. The process involves shining a laser into blood plasma from patients, and then analyzing how the light interacts with the blood using a spectrometer. This reveals minute changes in the chemical composition of cells and tissues, which serve as early disease indicators. A machine learning algorithm then interprets the data, identifying patterns and classifying the samples.

In a pilot study with 12 breast cancer patient samples and 12 healthy control samples, the technique identified breast cancer at stage 1a with 98% accuracy. The study, published in Journal of Biophotonics, also demonstrated the method’s ability to distinguish between the four main subtypes of breast cancer with over 90% accuracy. This could enable more personalized and effective treatments. The researchers believe that implementing this as a screening tool could identify more patients at the earliest stages of breast cancer, improving treatment success. They plan to expand the study to include more participants and test early detection for other types of cancer.

“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 Dr. Andy Downes, of the University of Edinburgh’s School of Engineering, who led the study. “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.”