WVU Scientists Develop 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 improving the diagnosis and prediction of heart disease among rural populations. This initiative addresses a significant gap in healthcare, as many existing AI models are primarily trained on data from urban, affluent populations, leaving rural patients underserved.

Prashnna Gyawali, an assistant professor in the Benjamin M. Statler College of Engineering and Mineral Resources at WVU, emphasizes that most AI systems in healthcare fail to consider the unique biological and socio-economic characteristics of rural communities. “You have to ensure your algorithms have seen the populations where you want them applied,” Gyawali stated. His team is committed to creating a model that is informed by data exclusively from rural patients in West Virginia.

The researchers have gathered anonymous patient datasets from various regions within the state to evaluate different AI models’ capabilities in diagnosing heart disease based on clinical test results. Gyawali believes that properly functioning AI can significantly alleviate pressures on rural healthcare providers, who often face staff shortages and limited resources. “Health care problems are growing, and we have manpower shortages,” he noted.

In rural areas, access to healthcare can be a major issue. Patients may need to travel several hours to receive basic diagnostic services. Gyawali envisions a future where more clinics equipped with affordable scanning devices and AI systems can facilitate early detection of heart disease, potentially leading to timely treatments before conditions worsen. “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.

Despite the optimism surrounding the project, Gyawali acknowledges that the AI models have only been tested with historical rural datasets and have yet to assist in real-world patient diagnostics. Continuous refinement of the model is essential to ensure safety and reliability before it can be deployed in clinical settings. “Whenever we talk about safety-critical applications like healthcare, we need to make sure they’re reliable,” he said.

The research team is focusing on enhancing the AI model’s performance and validating it through various means, including testing on datasets from clinics not involved in the original study. Gyawali expressed aspirations for the model to extend its applicability beyond West Virginia, potentially benefiting rural populations in other states as well.

“Finally, and this is perhaps beyond what I can do, is ensuring policy-level interventions so we can start trials on these algorithms in real-world clinical settings,” Gyawali remarked. The pathway to integrating these AI tools into healthcare systems is complex, but the potential benefits for rural populations could be transformative, providing much-needed support in the fight against heart disease.

As this project continues to evolve, Gyawali and his team remain dedicated to ensuring that the AI model is both reliable and unbiased, paving the way for a future where advanced technology can enhance healthcare access and outcomes in rural areas.