Exactly, this is another way in which artificial intelligence is entering the field of medicine and potentially enhancing existing practices for predicting breast cancer risks.
A study published this week in the peer-reviewed journal Radiology revealed that artificial intelligence algorithms outperform the standard clinical risk model for predicting five-year breast cancer risk.
Risk models, such as the Breast Cancer Surveillance Consortium (BCSC) risk assessment, which use self-reported and other patient information including age, family history, and several other factors, are typically used to calculate breast cancer risk in women.
Artificial intelligence can identify missed cancers “Clinical risk models rely on gathering information from various sources, which may not always be available. Recent advances in studying artificial intelligence afford us the ability to extract hundreds to thousands of additional mammographic features,” said lead researcher Dr. Vignesh A. Arasu, a scientist and radiologist at Kaiser Permanente Northern California.
In a retrospective study, thousands of mammograms were analyzed, and five AI algorithms were used to generate breast cancer risk results over a five-year period. These results were then compared to each other and to the BCSC clinical risk result. “All five artificial intelligence algorithms performed better than the BCSC risk model for predicting breast cancer risk from 0 to 5 years,” said Arasu, adding, “This strong predictive performance over a five-year period suggests that artificial intelligence identifies missed cancers and breast tissue features that aid in predicting future cancer development.”
An important tool in providing personalized medical care While some institutions already use artificial intelligence in mammography to aid in cancer detection, these findings suggest that AI can be a vital tool in predicting future risks in patients, which can be generated by artificial intelligence within seconds, according to the statement.
AI for cancer risk prediction offers the potential for individualizing care for each woman, which is not systematically available. Therefore, it becomes an important tool in providing personalized, precise medical assistance at a national level.
