AI Helps in Identifying Chemical "Fingerprints" for Breast Cancer
Thu, April 22, 2021

AI Helps in Identifying Chemical "Fingerprints" for Breast Cancer

AI can predict breast cancers for each subtype with 70% to 100% accuracy / Photo Credit: Shutterstock

 

Artificial intelligence has moved at the forefront in the continuous improvement of the healthcare industry. Recently, researchers from Lancaster University and Airedale NHS Foundation Trust developed a new way to rapidly and accurately diagnose breast cancer. Professor Ihtesham Rehman, chairman in bioengineering at Lancaster University and a senior author of the study, stated that their research is important in creating methods to identify the chemical structures of different types of breast cancers. 

According to Technology Networks, an internationally recognized publisher that provides access to the latest scientific news, products, research, videos, and posters, the researchers used Raman Spectroscopy, a specialized chemical analytical technique that provides real-time information on cells. It can also be used to check how the cells are spreading, behaving, and emerging in our bodies. The technique was utilized to identify the molecular structure of different types of breast cancers and the variations within each cancer cell group.

But first, the researchers needed to identify the unique chemical “fingerprints” for different types of breast cancers and observed how they change. The data gathered could be used to train complex machine learning algorithms to identify four subtypes of cancer. The researchers were able to predict diagnostic patterns for each subtype with 70% to 100% accuracy. 

The team is also working to create a new AI tool to make a quicker diagnosis for breast cancer. To succeed, they need to train more AI algorithms using databases. These databases consist of chemical structures from many more different types of breast cancer cells and the forms they can take. Rehman added that data mining and machine learning can potentially offer a real-time analysis in biological samples using vibrational spectroscopy.

“Vibrational spectroscopy combined with data mining and machine learning has the potential to offer a real-time analysis in biological samples, including cancer, with excellent accuracy—creating a powerful new tool to sit alongside existing techniques and helping medical specialists deliver accurate and timely diagnosis for their patients and for monitoring the progression of the disease,” Rehman said.