NYU Langone Health Researchers Test AI for Breast Cancer Risk Prediction

A new study by researchers at NYU Langone Health suggests that artificial intelligence (AI) could help doctors predict a woman's risk of developing breast cancer years before it occurs. The research, published in the American Journal of Roentgenology, introduces an AI model built to estimate breast cancer risk within a five-year window by analyzing mammograms over several years.

Large Dataset of Mammograms Used to Train AI Model

The AI tool was developed and tested using more than 313,000 mammograms from over 161,000 women. Unlike traditional methods, which often rely on a single scan, the model considers several years of 3D mammograms to monitor changes in breast tissue over time. This approach aims to capture subtle clues that could indicate a heightened breast cancer risk.

How the AI Tool Enhances Traditional Screening

Dr. Connie Lehman, a breast imaging specialist and professor of radiology at Harvard Medical School who was not involved in the study, explained that traditional breast cancer risk assessments typically account for family history and genetic mutations. In contrast, the AI system examines clues within the breast tissue visible on a woman’s mammograms. Lehman noted that such innovation may help spot increased risk that might otherwise go unnoticed, especially for women without a family history of the disease.

She remarked, "A mammogram can tell us more than whether cancer is visible today—it can also provide information about a woman's risk of developing cancer in the years ahead."

Potential Impact on Breast Cancer Screening and Personalized Care

By offering more detailed risk information, the technology could lead to more personalized breast cancer screening. Women identified as being at higher risk might consider additional screening options, such as MRI, in consultation with their health care providers. Meanwhile, women with lower assessed risk could continue with standard mammogram schedules. Lehman also highlighted that the system can analyze existing mammogram records, providing further risk insight without extra imaging or exposure to radiation.

Cautions and Current Status of the AI Model

Lehman cautioned that an AI risk score is not a definitive cancer diagnosis and does not guarantee whether someone will or will not develop breast cancer. She emphasized, "A higher score can prompt a conversation with your health care provider about additional screening and risk-reduction options. A lower score does not eliminate risk or replace regular mammography."

The NYU model remains in the research phase and is not yet approved by the FDA for clinical use. The study's data was sourced from NYU Langone hospitals and relied on imaging equipment from a single manufacturer. Researchers noted that more testing is needed, including evaluations using data from different medical centers and various 3D mammography systems.

Outlook for AI-Driven Mammogram Analysis

As AI tools for mammogram analysis continue to advance, experts believe they could transform breast cancer screening, offering the potential for earlier detection and more personalized patient care. However, ongoing validation and regulatory approval will be necessary before widespread clinical adoption.

Source: foxnews.com.