Illinois Medicine

According to the most recent Community Assessment of Needs: Towards Health Equity report compiled by UI Health's Office of Population Health Sciences and released in 2019, 21% of our patients live at or below the poverty level, less than half have completed high school or vocational training, 25% have no reliable means of transportation, and 21% rely on food stamps to feed their families. "Strategies to improve health should include accessible and high- quality healthcare, as well as multilevel interventions that address an individual's social determinants of health—the economic and social conditions that influence health outcomes," says Jerry A. Krishnan, MD, PhD, professor of medicine and public health, associate vice chancellor for population health sciences and executive director of the Institute for Healthcare Delivery Design. As one of the core members of the executive team that developed the concept for the Center for Health Equity using Machine Learning and Artificial Intelligence (CHEMA), Krishnan brings methodological expertise in designing, implementing, evaluating and disseminating population- specific care models. This expertise informs every aspect of his team's research—with the goal of bringing more effective and efficient healthcare to patients in UI Health's communities and beyond. AI-Enhanced Community Health and Well-Being "We do not do research for research's sake," he says. "Our research ultimately aims to improve the health and well-being of people living in Chicago, the state of Illinois and across the U.S." Because of the broad scope and implications of Krishnan's work, his interdisciplinary group brings both data and a multi-stakeholder perspective to inform the development of CHEMA's AI/ML reach. "I think the potential of machine learning can expand our ability to serve patients," he adds. "AI and ML are tools that help refine information and, in terms of what our group does, help diagnose the problem. The issues related to why people are unable to access and enjoy good health are complex." Krishnan's research group at the Office of Population Health Sciences focuses on ways to serve UIC's patient population, which has substantial healthcare needs, as well as needs that are beyond the scope of healthcare. "Many times, for this population, poor health is the downstream consequence of a range of challenges, including a lack of jobs that pay a living wage, insufficient formal education, food and housing insecurity, tobacco use, inadequate transportation, and violence," says Krishnan. "AI and machine learning enable us to recognize patterns that may otherwise be difficult to identify, along with contributing factors that lead to negative effects on health." Krishnan's group partners with experts at UIC and collaborates with patients and patient groups; professional organizations; behavioral scientists; epidemiologists; statisticians; data scientists; clinical trialists; experts in health policy; human-centered designers; and clinicians such as physicians, nurses and psychologists. "We conduct research using a range of methods—including qualitative and quantitative approaches to understanding a problem, rapid-cycle prototyping, and clinical trials to test different strategies to improve healthcare. Our researchers gather data from a variety of sources such as surveys and interviews from people in the communities that we serve, electronic health records, healthcare claims, and data sets made available by the City of Chicago, the State of Illinois and the federal government—so our sources are an aggregation." Removing Barriers to Care Over the past few years, Krishnan's group has worked with the hospital to better understand some of the transportation challenges that patients face when it's time to return home after treatment. Some were UI Health's primary service area includes some of the poorest communities in Chicagoland. But poverty is only one of the social determinants of health affecting this patient population. B Y C A R L A B E E C H E R 20 | Summer 2023

• Cover