Black women face an 80% higher mortality rate from endometrial cancer compared to other groups, and new research suggests the disparity may stem from more than just unequal access to care. A team at Emory University used artificial intelligence to uncover biological differences in tumor behavior that may help explain the poorer outcomes.
“Racism and equitable access to health care certainly play a big role,” said Anant Madabhushi, executive director of Emory’s Empathetic AI For Health Institute. “But with endometrial cancer, it may not completely explain the difference in mortality.”
Using machine learning, researchers analyzed tissue slides from African American and European American women. They found distinct patterns in how immune cells interacted with tumor structures. In Black women, tumor-infiltrating lymphocytes were more likely to engage with stroma—supportive tissue—while in white women, they interacted with epithelial tissue, which typically signals better outcomes.
The AI-generated risk models showed that combining data from both groups failed to accurately predict outcomes for Black women. Only models built specifically from Black women’s data provided reliable prognoses.
“There really are differences with regard to the immune architecture,” Madabhushi said. “When we leveraged that pattern, we were able to create a predictive model that worked much more accurately in Black women.”
These findings could reshape how immunotherapies are designed, moving away from a one-size-fits-all approach. “If you want to pick an example of a disease that disproportionately affects women of color, it has to be endometrial cancer,” Madabhushi added.
See: “Research uses AI to find pathologic and genetic basis for worse outcome of endometrial cancer in Black women” (July 24, 2025)
