Innovative Machine Learning Tool Achieves 98% Accuracy in Early Breast Cancer Detection: Research
Click to start listening
New Delhi, Dec 15 (NationPress) A revolutionary machine learning-driven screening approach has shown a remarkable 98% success rate in identifying the earliest signs of breast cancer, according to a recent study.
Created by experts at the University of Edinburgh, this rapid, non-invasive method merges laser analysis with machine learning. It stands as the first technology capable of detecting patients in the very early stages of breast cancer, potentially leading to a screening test applicable for various cancer types.
This technique identifies subtle changes in the bloodstream that occur during the initial stages of the disease, referred to as stage 1a, which conventional tests often miss.
Current standard procedures for breast cancer detection include physical exams, X-ray or ultrasound scans, and tissue sample analysis known as biopsy. These methods typically screen individuals based on age or high-risk classifications.
The pilot study, featured in the Journal of Biophotonics, involved 12 samples from breast cancer patients and 12 from healthy individuals. The team refined a laser analysis method called Raman spectroscopy and integrated it with machine learning.
With this approach, they successfully detected breast cancer at stage 1a with an impressive accuracy of 98%.
The process begins by directing a laser beam into blood plasma samples from patients. A spectrometer analyzes the light properties after it interacts with the blood, revealing slight alterations in the chemical composition of cells and tissues—early signs of disease.
Through the use of the machine learning algorithm, healthcare providers can interpret the findings. This innovative method also allows the differentiation of the four primary subtypes of breast cancer with over 90% accuracy, enabling more effective and personalized treatment for patients.
