Detroit-based Karmanos Cancer Institute, a network of 16 treatment sites in Michigan and Ohio that is part of McLaren Health Care, uses artificial intelligence to improve risk assessment and highlights high-risk breast cancer patients who could benefit from additional images .
Because women have a one-in-eight chance of developing breast cancer during their lifetime, finding breast cancer at an earlier stage significantly impacts survival rates and can also improve patients’ treatment pathways and outcomes, according to the American Cancer Society.
“It’s not a cliché, it’s reality,” Brown said.
Breast cancer often remains hidden in the annual mammograms of women with high breast tissue density, prompting healthcare systems to send letters to patients explaining the challenges of standard screening. However, targeting additional screening efforts to women with an immediate family history has not been sufficient to increase early-stage breast cancer diagnosis rates.
As Brown notes in this podcast interview, many women at high risk due to many factors other than a family history of breast cancer often have no idea.
“Screening once a year may not be enough to identify them early,” he said. “Identifying breast cancer early not only means better long-term survival, but often also less treatment to cure that cancer.”
Karmanos is one of the first cancer hospitals to deploy Volpara’s artificial intelligence-based risk assessment software for mammogram screenings. Brown said that while it only added an extra two to three minutes to patient appointments, the AI’s ability to combine multiple risk assessment tools provides women and their GPs with five-year and lifetime risk scores.
At the time of the interview, Brown said the institute has rolled out the AI risk assessment tool at two centers to test integration with the network’s electronic health records and “work out the kinks” in communicating the results to primary care physicians.
Using the AI tool, Karmanos screened 7,000 patients and identified 700 as high-risk through the software. Karmanos will continue to roll this out to all screening locations. The women who come in for their annual mammogram and have a risk score of more than 20% are directed to Karmanos’ women’s wellness program, where they have a better chance of being diagnosed and treated early – or have the chance to prevent breast cancer – and the pinnacle of survival.
Do you like what you hear? Subscribe to the podcast at Apple podcasts, Spotify or Google Play!
Discussion points:
- Partnerships with the Detroit Tigers and others increase screening
- Combining risk assessments in one AI-driven tool
- How capturing additional health history factors improves risk models
- Why scoring women can help reach other high-risk family members, including men
- How data-driven assessment enables prior consent for additional imaging
AI shows it can improve predictions for invasive breast cancer
New York approves AI-driven breast cancer diagnosis
Breast cancer technologies that improve patient outcomes
UPMC uses an AI model for sentinel lymph node biopsies in breast cancer
AI helps radiologists improve accuracy in breast cancer detection with fewer recalls