West Virginia University (WVU) researchers are developing innovative artificial intelligence (AI) models aimed at improving the diagnosis and prediction of heart disease among rural patients. This initiative addresses a significant gap in healthcare, where most existing AI models are predominantly based on data from urban populations, often overlooking the unique needs of rural communities.
According to Prashnna Gyawali, an assistant professor at the Benjamin M. Statler College of Engineering and Mineral Resources, AI applications in healthcare have been widely adopted globally. However, he emphasizes that the majority of these models rely on data from urban settings, which can lead to biased outcomes when applied to rural populations. “You have to ensure your algorithms have seen the populations where you want them applied,” Gyawali stated. The aim is to create an AI model specifically tailored to reflect the characteristics of rural health data.
The research team is utilizing anonymous patient datasets from various regions across West Virginia. They are testing different AI models to assess their effectiveness in diagnosing heart disease based on patient test results. Gyawali believes that well-functioning AI could significantly alleviate the burden on healthcare providers, especially in areas facing manpower shortages. He highlighted that rural patients often travel long distances—sometimes several hours—just to receive an initial diagnosis.
Improving access to healthcare is a critical aspect of this initiative. Gyawali envisions a future where clinics equipped with cost-effective scanning devices, integrated with AI systems, can facilitate early detection of heart disease. This proactive approach could lead to timely interventions that prevent more severe health complications. “Health care problems are growing, and we need reliable systems,” Gyawali noted.
As the project progresses, the team remains optimistic about their findings. However, it is crucial to acknowledge that the AI models have only been tested on historical rural datasets and have not yet been applied in real-world clinical settings. Gyawali stressed the importance of continuous refinement of the AI model to ensure safety and reliability before any clinical trials commence.
“Whenever we talk about safety-critical applications like health care, we need to make sure they’re reliable,” Gyawali said. He emphasized the necessity of ensuring that AI models can accurately identify patients who require immediate attention. The goal is to integrate AI as a valuable layer within the healthcare system, enhancing the overall diagnostic process.
The team is committed to further developing the AI model, focusing on performance enhancement and validation. Gyawali mentioned the potential for collaboration with clinics not involved in the current study, which could broaden the scope of testing and validate the model’s effectiveness beyond West Virginia. “We want to look at other states and see if the algorithm performs equally well,” he stated.
Additionally, Gyawali highlighted the need for policy-level interventions to facilitate the adoption of these AI tools in clinical settings. By establishing a roadmap for real-world trials, the team aims to pave the way for future integration of advanced technologies in rural healthcare.
As the research continues, WVU’s efforts stand as a significant step toward addressing the healthcare disparities faced by rural populations, with the hope of revolutionizing heart disease diagnosis and treatment in these communities.
