West Virginia Researchers Innovate AI for Heart Disease in Rural Areas

West Virginia University (WVU) researchers are developing advanced artificial intelligence (AI) models designed to improve the diagnosis and prediction of heart disease specifically for rural patients. This initiative addresses a critical gap in healthcare, where existing AI tools often favor urban populations, leaving rural areas underserved.

Prashnna Gyawali, an assistant professor in the Benjamin M. Statler College of Engineering and Mineral Resources, emphasized that while AI systems are being implemented globally to assist in patient diagnosis, the majority of data driving these models originates from urban settings. These areas generally feature more affluent patients whose biological characteristics may differ significantly from those in rural communities. This discrepancy can hinder the effectiveness of AI applications in rural healthcare environments.

To combat this issue, Gyawali and his team have begun creating a new AI model that utilizes exclusively rural patient data collected from various regions in West Virginia. “You have to ensure your algorithms have seen the populations where you want them applied,” he stated. He further noted that for AI to effectively assist in diagnosing heart disease, it must be trained on data that reflects the unique characteristics of rural populations.

The team has gathered anonymous patient datasets to evaluate the performance of different AI models in diagnosing heart disease based on test results. Gyawali believes that if implemented correctly, AI can substantially benefit rural healthcare systems. It can alleviate the workload of healthcare professionals who often face manpower shortages while also facilitating early detection of critical conditions like heart disease.

“Healthcare problems are growing, and we have manpower shortages,” Gyawali explained. “In our state, we don’t have easily accessible healthcare infrastructures. A person who wants to get tested properly may have to travel several hours just for an initial diagnosis.” He envisions a future where clinics equipped with affordable scanning devices and integrated AI systems could flag high-risk patients for early intervention.

While Gyawali’s team is optimistic about their progress, they are cautious; the models have only been tested with historical datasets and have not yet been applied in real-world clinical settings. Continuous refinement of the AI model is essential to ensure its safety and reliability before it can be used on actual patients. “Whenever we talk about safety-critical applications like healthcare, we need to make sure they’re reliable,” Gyawali asserted. “We don’t want to give medications to patients who are wrongly diagnosed.”

The research team plans to keep enhancing the AI model to ensure its dependability prior to its entry into clinical trials. Although no specific timeline for these trials exists, Gyawali confirmed that the development process is ongoing. “We’re adding more layers to ensure the model is reliable,” he said. “How can we further enhance performance? These are AI questions my lab is trying to answer.”

In the long term, Gyawali aims to validate the AI algorithms in clinics outside of their study. He expressed interest in exploring how the model could perform in different states, emphasizing the importance of policy-level interventions to facilitate real-world clinical trials. “That’s the roadmap toward adopting these tools in clinics,” he concluded.

With its focus on rural health, this innovative research at West Virginia University holds promise for reshaping how heart disease is diagnosed and treated in underserved areas, potentially improving health outcomes for many individuals facing barriers to healthcare access.