ISU researchers use AI to detect heart irregularities in rural Illinois
A collaboration between nursing and IT departments aims to identify atrial fibrillation risk in underserved populations using machine learning.
Researchers at Illinois State University (ISU) are utilizing artificial intelligence to enhance the detection of heart irregularities, specifically atrial fibrillation (AF). AF is a common heart rhythm disorder that significantly increases the risk of stroke and heart failure if left untreated, making early detection critical for patient outcomes.
Led by Marilyn Prasun, a professor at the Mennonite College of Nursing, and Nariman Ammar, an assistant professor of Information Technology, the initiative represents a cross-departmental collaboration. The team is developing machine learning algorithms designed to predict the risk of AF, shifting cardiac screening from a reactive to a proactive model. This research is supported by a training grant from the National Institutes of Health's AIM-AHEAD Program for Artificial Intelligence Readiness (PAIR) seed program.
Addressing Rural Healthcare Gaps
The project specifically targets underserved rural communities across Central Illinois. In these regions, access to specialized cardiology care is often limited by geography and socioeconomic factors, which frequently leads to delayed diagnoses and worse health outcomes. By leveraging AI-driven predictive tools, the researchers aim to bridge this gap, identifying high-risk patients before they experience severe cardiac events.
The Shift Toward AI Cardiology
This research aligns with a broader industry trend of integrating machine learning into cardiology. AI is increasingly deployed to analyze complex physiological data—such as ECG patterns—more rapidly and accurately than traditional manual reviews. When applied to atrial fibrillation, these tools can detect subtle irregularities that might be missed during standard clinical visits, facilitating earlier medical intervention and personalized care plans.
Future Implications
If successful, the algorithms developed by the ISU team could provide a blueprint for non-invasive, scalable diagnostic tools tailored specifically for rural health settings. The next phase of the project will focus on refining these predictive models to ensure accuracy across diverse patient demographics.
While the project is currently in its early stages, the integration of nursing expertise with information technology suggests a move toward more holistic, data-driven patient care in the Midwest. By combining clinical insight with computational power, the team hopes to create a sustainable model for rural health equity.