Washington State University sociologist Anna Zamora-Kapoor is studying how artificial intelligence (AI) and machine learning (ML) could help improve cancer survival outcomes among the Pacific Northwest’s rural Hispanic population.
As one of 25 fellows in the National Institutes of Health (NIH) AIM-AHEAD leadership program, and in partnership with Three Rivers Hospital in Brewster, Washington, Zamora-Kapoor is using AI generated text messages and a text-based intervention to help identify, schedule, and follow up with patients eligible for a low-dose computed tomography (CT) scan, an efficient and effective way to screen for lung cancer. As with other types of cancer, early detection is key to improving the likelihood of survival.
AIM-AHEAD—the Artificial Intelligence-Machine Learning Consortium to Advance Health Equity and Research Diversity—was created by the NIH to enhance the participation and representation of researchers and communities currently underrepresented in the development of AI/ML models and to improve the capabilities of emerging technology to address health disparities and inequities.
“This is a critical first step toward developing studies that can leverage the strengths of technologies like artificial intelligence and machine learning in clinical settings to improve health outcomes,” said Zamora-Kapoor.
According to the NIH, the lack of diversity of both data and researchers in the AI/ML field runs the risk of creating and perpetuating harmful biases in how the technology is used, how algorithms are developed and trained, and how findings are interpreted.
Zamora-Kapoor, an assistant professor in both the College of Arts and Sciences and the Elson S. Floyd College of Medicine, says adding AI/ML tools to sociological research methods, medical education, and clinical studies will aid the development of future interventions and improve health equity in Washington and elsewhere.
“I am fascinated by the amount of sociological factors underlying health outcomes and their disparities. For example, many older patients in rural areas do not have SMS-enabled cell phones and rarely interact with online patient portals. In addition to the expense of artificial intelligence and machine learning tools, many rural clinics do not have the full-time IT support needed to manage new technologies, and some tech companies won’t work with rural health clinics below a certain size. All these factors perpetuate the disproportionate burden of disease in rural areas,” Zamora-Kapoor explained.
In addition to funding support for individual research projects during their nine-month fellowship, AIM-AHEAD fellows receive training in data science, ethics, using AI tools in healthcare research, and more. Within each cohort, participants also complete a multi-disciplinary team project designed to provide hands-on experience working with curated data. Zamora-Kapoor’s team is exploring racial and ethnic differences in cardiovascular and cancer mortality during the COVID-19 pandemic.
