• AI
  • Molecular Imaging
  • CT
  • X-Ray
  • Ultrasound
  • MRI
  • Facility Management
  • Mammography

Personalizing Breast Cancer Risk Assessment


Artificial intelligence can help seek out and identify high-risk patients who might benefit from more extensive screening.

If only we were as good at prevention and early detection as we are at treating complex disease in U.S. healthcare. Generally, people know what they should do, and in some cases, they do it. For example, many patients religiously go to the dentist for a cleaning every six months to prevent cavities. 

But screening women with consistent mammograms beginning at age 40 to detect breast cancer?1 Not so much. Just imagine how many lives we could save if we looked for breast cancer with the rigor and diligence with which we prevent tooth decay.

An Ounce of Prevention: Weighing Evidence and Personal Risk Factors

Unfortunately, when it comes to breast cancer screening recommendations,2 there are multiple sets of guidelines, many of them different. Conflicting recommendations can breed confusion and, far worse, can potentially threaten lives. One study estimated that if women followed less stringent recommendations and started screening at age 50 (instead of 40), and women aged 50-74 only screened every other year (instead of annually), it could result in about 6,500 more deaths from breast cancer every year in the United States.3

To further complicate matters, even the best evidence-based guidelines may not be the best approach for every patient. All patients need to make sure their complete history is part of their healthcare decision making, and that is particularly important for breast cancer patients. Each woman has a unique personal and family history which may impact her risk of getting breast cancer. There are many factors that women and their physicians should consider when determining the best approach to breast cancer screening, such as personal health history, family history, genetic profile and hormonal considerations, among many others.

Doctors don’t know their patients as well as patients know themselves. For example, who in the family has had cancer, especially breast, ovarian or cancer of the gastrointestinal tract? Has the patient ever had a breast biopsy that showed abnormal cells, or prior cancer? At what age did she have her first period? Go through menopause? How many pregnancies? How dense is the patient’s breast tissue? Women and their doctors must work through these issues together to pursue more effective prevention.

Where Artificial Intelligence (AI) Can Help With Breast Cancer Prevention Efforts

As a breast radiologist, I believe one of the keys to better outcomes will be a more personalized level of risk assessment for every patient. AI can help deliver this personalization. For example, women with the densest breast tissue have a higher risk of breast cancer.4 These women may benefit from more extensive screenings, such as ultrasound or breast MRI. AI can help conduct density assessments to identify higher-risk patients.

In addition to density assessment, AI can enhance breast cancer detection by helping clinicians identify abnormalities on a mammogram, including a 3D (tomosynthesis) mammogram, that might be overlooked by even the most experienced radiologist. 

There is some promising research around applying data and AI to identifying breast cancer. An IBM research team analyzed de-identified mammography images, linked to comprehensive clinical data and biomarkers, to create a new algorithm designed to predict breast cancer.5 The combined machine- and deep-learning model correctly predicted the development of breast cancer in 87 percent of the cases it analyzed – an accuracy comparable to radiologists.

There are many exciting possibilities that could result from this type of research. For example, this may be the first study to incorporate both mammograms and electronic health record data for the prediction of breast cancer, which shows the potential of one day harnessing multiple data sets and AI algorithms to tailor risk assessment to each patient. The research team plans to continue analyzing clinical risk elements to better understand their relationship to an individual’s personalized risk.

To be clear, AI will never replace the radiologist. Another large-scale IBM Research study found that no single AI algorithm could outperform radiologists, but the combination of AI with radiologist assessment improved overall accuracy.7

And no matter how good the technology gets, there will never be a replacement for good, patient-centered care. I encourage women to know their risk and talk to their doctors about breast cancer screenings. I’d like to see all patients do for the rest of our bodies what we so willingly do to prevent dental disease. The benefits to our lives can be dramatic.


  1. This article does not provide medical advice. For information on the benefits of breast cancer screening starting at age 40, visit the Society of Breast Imaging
  2. For a more detailed discussion of differences between recommendations, see “Clearing up confusion over breast cancer screening recommendations” Mayo Clinic News Network. Oct. 9, 2020.
  3. Hendrick and Helvie, “United States Preventive Services Task Force Screening Mammography Recommendations: Science Ignored.” American Journal of Roentgenology. 2011;196: W112-W116. 10.2214/AJR.10.5609
  4. Source: NIH National Cancer Institute. https://www.cancer.gov/types/breast/breast-changes/dense-breasts
  5. Akselrod-Ballin A, Chorev M, Shoshan Y, et al. Predicting breast cancer by applying deep learning to linked health records and mammograms. Radiology. 2019;292(2):331-342.
  6. Schaffter T, Buist DSM, Lee CI, et al. Evaluation of combined artificial intelligence and radiologist assessment to interpret screening mammograms. JAMA Netw Open. 2020;3(3):e200265.
Related Videos
Where the USPSTF Breast Cancer Screening Recommendations Fall Short: An Interview with Stacy Smith-Foley, MD
A Closer Look at MRI-Guided Transurethral Ultrasound Ablation for Intermediate Risk Prostate Cancer
Improving the Quality of Breast MRI Acquisition and Processing
Can Fiber Optic RealShape (FORS) Technology Provide a Viable Alternative to X-Rays for Aortic Procedures?
Does Initial CCTA Provide the Best Assessment of Stable Chest Pain?
Making the Case for Intravascular Ultrasound Use in Peripheral Vascular Interventions
Can Diffusion Microstructural Imaging Provide Insights into Long Covid Beyond Conventional MRI?
Emerging MRI and PET Research Reveals Link Between Visceral Abdominal Fat and Early Signs of Alzheimer’s Disease
Nina Kottler, MD, MS
Practical Insights on CT and MRI Neuroimaging and Reporting for Stroke Patients
Related Content
© 2024 MJH Life Sciences

All rights reserved.