AI technology developed at the Massachusetts Institute of Technology has been found to help predict breast cancer in patients.
The software called “Mirai” has shown to be three times more likely to find early signs of breast cancer in patients, compared to previous statistical techniques.
It is being developed to help improve early detection and to reduce the stress and cost of false positives. Developed by a team of scientists and PhD students at MIT, the tool is said to ‘detect and flag patients who might develop breast cancer within a 5 year window’.
The tool was developed using data from the Massachusetts General Hospital, trained using 210,819 datasets, and validated against 25,855 examinations.
Adam Yala, CSAIL PhD student and lead author on a paper about Mirai that was published last week in Science Translational Medicine, said: “Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection, and less screening harm than existing guidelines.
“Our goal is to make these advances part of the standard of care. We are partnering with clinicians from Novant Health in North Carolina, Emory in Georgia, Maccabi in Israel, TecSalud in Mexico, Apollo in India, and Barretos in Brazil to further validate the model on diverse populations and study how to best clinically implement it.
“We know MRI can catch cancers earlier than mammography, and that earlier detection improves patient outcomes.
“But for patients at low risk of cancer, the risk of false-positives can outweigh the benefits. With improved risk models, we can design more nuanced risk-screening guidelines that offer more sensitive screening, like MRI, to patients who will develop cancer, to get better outcomes while reducing unnecessary screening and over-treatment for the rest.”
The software was trialled in Taiwan and Sweden to explore if any variations can be found and if the software found any differences between ethnicities; the model outperformed older versions in every case, boosting hopes that it could be used in multiple healthcare settings across the world.
The paper highlights ‘deep learning’ is a vital part of the innerworkings of Mirai and mimics how the human brain works but is often faster and often more reliable.
Details of the programme have been published in Science Translation Medicine.
Watch an overview video of the work here: