WVU Researchers Harness AI to Transform Heart Disease Diagnosis in Rural Areas

Researchers at West Virginia University (WVU) are pioneering the development of artificial intelligence (AI) models aimed at enhancing the diagnosis and prediction of heart disease among rural patients. Given that many existing AI healthcare models are predominantly designed using data from urban populations, this initiative is vital for addressing the unique health challenges faced by rural communities.

Prashnna Gyawali, an assistant professor at the Benjamin M. Statler College of Engineering and Mineral Resources, emphasized the need for AI systems to be trained on data that accurately reflects the populations they serve. “Most AI models are built on datasets from urban areas where biological differences can skew results for rural patients,” Gyawali noted. This discrepancy can limit AI’s effectiveness in rural health care settings, a concern that has prompted Gyawali and his team to focus solely on rural patient data from West Virginia.

The research team has collected anonymous patient datasets from various regions in West Virginia, using this data to evaluate the performance of different AI models in diagnosing heart disease. Gyawali stated that if implemented effectively, AI could significantly alleviate pressures on healthcare systems already strained by workforce shortages. He pointed out that in West Virginia, accessing healthcare often requires long travel times, which can delay diagnosis and treatment.

To counter this, Gyawali envisions a future where rural clinics equipped with affordable scanning devices integrated with AI technology can provide early detection of heart disease. “If we have more clinics with inexpensive scanning devices with an AI system attached, we can have an early detection system flagging certain patients,” he explained. Achieving this goal hinges on developing AI models that are both reliable and unbiased, tailored specifically to rural populations.

While the team remains optimistic about their AI model’s potential, Gyawali highlighted the importance of continued refinement. The current models have only been tested with historical datasets and have not yet been applied in real-world patient diagnostics. “Whenever we talk about safety-critical applications like healthcare, we need to make sure they’re reliable,” he cautioned. Gyawali reiterated the need for thorough validation to ensure that AI can accurately identify patients requiring urgent care.

Looking ahead, Gyawali and his team are committed to enhancing the model’s reliability before it enters clinical trials. Although no specific timeline has been established for these trials, they are actively exploring additional avenues for research. “We’re adding more layers to ensure the model is reliable,” he said. The team is also considering the possibility of validating their algorithms in clinics outside their study, potentially expanding their research to other states.

In addition to technical advancements, Gyawali stressed the necessity of policy-level interventions to facilitate the integration of AI technologies in clinical settings. “That’s the roadmap toward adopting these tools in clinics,” he asserted. As the project progresses, the team aims to ensure that AI can serve as a robust support system within rural healthcare, ultimately improving health outcomes for communities that need it most.