New Delhi. Machine learning based screening method can prove to be effective in detecting early symptoms of breast cancer. This has been revealed in a study.
This fast, noninvasive technique developed by researchers at the University of Edinburgh combines laser analysis with machine learning. This is the first technology of its kind to identify patients with breast cancer at an early stage. Researchers said this technology could open the way for screening tests for many types of cancer.
The technology can detect subtle changes in blood flow during the early stages of the disease (called stage 1A) that current tests miss.
Physical examination, Xray or ultrasound scan, or analysis of a sample of breast tissue (known as a biopsy) are the standard tests currently available for breast cancer. These test people based on their age or whether they are in atrisk groups.
The original study, published in the Journal of BioPhotonics, included 12 samples from breast cancer patients and 12 healthy control groups. In the study, the team adapted a laser analysis technique called Raman spectroscopy and combined it with machine learning. The team was able to detect breast cancer at stage 1A with 98 percent effectiveness.
It was the first to flash a laser beam into blood plasma taken from patients. Using a spectrometer device, the team analyzed the properties of blood after light interacted with it. The spectrometer detected tiny changes in the chemical composition of cells and tissues, which are early signs of disease.
Using machine learning algorithms, physicians can interpret the results. Using this new approach, the team could also distinguish between each of the four main breast cancer subtypes with an accuracy of more than 90 percent. The team said this helped patients receive more effective, personalized treatment.
—
– .
Image Credit: KhasKhabar.