A doctor in a white coat and with a red stethescope speaks to a patient.

UTMB-TSU Team Awarded $1M to Analyze Cancer Disparities Using Human-Centered Artificial Intelligence

Researchers from the University of Texas Medical Branch and Texas Southern University have been awarded a $1 million grant from the National Institutes of Health to use human-centered artificial intelligence to tackle the social and cultural barriers that hinder timely cancer diagnoses and effective treatments in the United States.

The grant, part of the Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD), will be led by Dr. Suresh Bhavnani, a professor of biomedical informatics at UTMB, and Dr. Rodney Hunter, a clinical associate professor of pharmacy practice from TSU.

Many Americans have social and cultural hurdles that prevent them from getting timely cancer diagnoses and effective treatments. For example, lack of transportation can prevent women from being regularly screened for breast cancer, increasing the risk of a late cancer diagnosis that can be difficult to treat.

“Such social factors, also called social determinants of health, are well-known but have been difficult to analyze and interpret despite the use of powerful machine learning methods,” Bhavnani said.

With this project, Bhavnani and Hunter aim to address some of the main hurdles to understanding and dealing with social determinants of health. Those include the number and complexity of patients' social determinants of health, the “black box” AI problem where the use of complex machine learning methods transform the data in ways that are difficult to interpret by clinicians, and the underrepresentation of Black and Hispanic researchers in AI and machine learning research, which further exacerbates the risk of biased data, analyses, and interpretations.

To overcome these hurdles, the researchers will employ a Human-Centered AI approach, utilizing graphical networks to automatically identify complex patterns in large datasets. This approach will also provide visualizations at each step, allowing ethicists, biostatisticians, and clinicians to inspect and interpret the results. The research will use data from the All of Us program which aims to collect data from one million Americans with a focus on underrepresented populations, and involve researchers from TSU, a minority-serving institution.

"This partnership between Texas Southern University and the University of Texas Medical Branch in Galveston on this National Institutes of Health grant will begin a new era of leveraging Artificial Intelligence and Social Determinants of Health to help predict and address factors that negatively impact morbidity and mortality associated with cancers that minority patients have consistently had, resulting in poorer outcomes compared to their majority counterparts,” Hunter said.

Categories