Predictive Analytics Tool Accurately Determines Breast Cancer Risk

A team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has developed a predictive analytics model that can jointly model a patient’s breast cancer risk across multiple future time points.

The model can also optionally benefit from clinical risk factors such as age or family history if they are available, and can produce predictions that are consistent across minor variances in clinical environments.

Current clinical guidelines use risk models to determine which patients should be recommended for supplemental imaging and MRI. While some guidelines use risk models with just age to determine if, and how often, a woman should get screened, others combine multiple factors related to age, hormones, genetics, and breast density to determine further testing.

However, despite decades of research and effort, the accuracy of risk models used in clinical practice remains modest.

While predictive analytics and other AI tools have shown promise in forecasting cancer risk, these technologies often show poor performance in new patient populations and neglect to racial minorities – limitations that have hindered their adoption in healthcare.

To bring these tools into clinical care, the team identified three innovations they believe are critical for risk modeling, including jointly modeling time, the optional use of non-image risk factors, and methods to ensure consistent performance across clinical settings.

The team trained the predictive analytics model, called Mirai, on the same dataset of over 200,000 exams from Massachusetts General Hospital (MGH) and validated it on test sets from MGH, the Karolinska Institute in Sweden, and Chang Gung Memorial Hospital in Taiwan.

The results showed that Mirai was significantly more accurate than prior methods in predicting cancer risk and identifying high risk groups across all three datasets. When comparing high-risk cohorts on the MGH test set, the team found that their model identified nearly two times more future cancer diagnoses compared to the current clinical standard.

“Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection, and less screening harm than existing guidelines,” said Adam Yala, CSAIL PhD student and lead author on a paper about Mirai which will be published in Science Translational Medicine.

“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.” 

Mirai was also accurate across patients of different races, age groups, and breast density categories in the MGH test set, and across different cancer subtypes in the Karolinska test set.

“African American women continue to present with breast cancer at younger ages, and often at later stages,” said Salewa Oseni, a breast surgeon at Massachusetts General Hospital who was not involved with the work.

“This, coupled with the higher instance of triple negative breast cancer in this group, has resulted in increased breast cancer mortality. This study demonstrates the development of a risk model whose prediction has notable accuracy across race. The opportunity for its use clinically is high.”

While the current model doesn’t look at any of the patient’s previous imaging results, changes in imaging over time contain a lot of information. In the future, the team will aim to create methods that can effectively use a patient’s full imaging history.

Similarly, the researchers noted that the model could be further improved by utilizing tomosynthesis, an X-ray technique for screening asymptomatic cancer patients. Additional research is required to determine how to adapt image-based risk models to different mammography devices with limited data.

“We know MRI can catch cancers earlier than mammography, and that earlier detection improves patient outcomes,” said Yala.

“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 research team is optimistic that their model can reduce disparities in cancer screening and detection for minority populations.

“We’re both excited and humbled to ask the question if this AI system will work for African American populations,” said Judy Gichoya, MD MS, and assistant professor of Interventional Radiology and Informatics at Emory University who was not involved with the work. “We’re extensively studying this question, and how to detect failure.”