Artificial intelligence can do a better job than the standard clinical risk model when it comes to predicting breast cancer.
A new study in the journal Radiology reported that researchers from Kaiser Permanente applied five different AI algorithms to thousands of mammograms and found each one was better at predicting the five-year risk for breast cancer than the standard risk model known as breast cancer surveillance consortium or BCSC.
The BCSC model uses information including age, family history of the disease, whether the patient has previously given birth and whether she has dense breasts to help calculate a risk score.
AI just uses the mammogram itself.
For example, among women with the highest risk, AI was able to predict up to 28% of cancers compared to 21% predicted by the standard model.
Researchers added that combining the two risk models improved cancer prediction even more.
