Researchers at West Virginia University have developed artificial intelligence models aimed at improving the diagnosis of heart failure in rural populations, particularly those in Appalachia. The initiative responds to concerns that existing AI diagnostic tools, which are often trained on data from urban and suburban patients, may not be effective for people living in rural areas.
Prashnna Gyawali, assistant professor in the Lane Department of Computer Science and Electrical Engineering at WVU’s Benjamin M. Statler College of Engineering and Mineral Resources, explained the significance of this work. “Imagine Jane Doe, a 62-year-old woman living in a rural Appalachian community,” he said. “She has limited access to specialty care, relies on a small local clinic, and her lifestyle, diet and health history reflect the realities of her environment: high physical labor, minimal preventive care, and increased exposure to environmental risk factors like coal dust or poor air quality. Jane begins to experience fatigue and shortness of breath — symptoms that could point to heart failure.
“An AI system, trained primarily on data from urban hospitals in more affluent, coastal areas, evaluates Jane’s lab results. But because the system was not trained on patients who share Jane’s socioeconomic and environmental context, it fails to recognize her condition as urgent or abnormal,” Gyawali continued. “This is why this work matters. By training AI models on data from West Virginia patients, we aim to ensure people like Jane receive accurate diagnoses, no matter where they live or how their lives differ from national averages.”
The research team analyzed anonymized records from over 55,000 patients who received medical care in West Virginia. They identified which AI models were most accurate at diagnosing heart failure and determined which parameters improved diagnostic accuracy. Their findings were published in Scientific Reports.
Doctoral student Alina Devkota noted that the AI models were trained using electrocardiogram (ECG) results instead of echocardiogram readings typically used for patient data from urban areas. Electrocardiograms use electrodes attached to the torso to record electrical signals from the heart and are accessible even in clinics with limited resources.
“One of the criteria to diagnose heart failure is by measuring the ‘ejection fraction,’ or how much blood is pumped out of the heart with every beat, and the gold standard for doing that is with echocardiography, which uses sound waves to create images of the heart and the blood flowing through its valves,” Devkota said.
“But echocardiography is expensive, time-consuming and often unavailable to patients in the very same rural Appalachian states that have the highest prevalence of heart failure across the nation. West Virginia, for example, ranks first in the U.S. for the prevalence of heart attack and coronary heart disease, but many West Virginians don’t have local access to high-tech echocardiograms. They do have access to inexpensive electrocardiograms, so we tested whether AI models could use electrocardiogram readings to predict a patient’s ejection fraction.”
Devkota added that she worked with Gyawali and other colleagues to train several types of AI models using patient records from 28 hospitals throughout West Virginia. These included both deep learning approaches—using multilayered neural networks—and simpler algorithms known as non-deep learning methods.
The study found that deep-learning models such as ResNet performed best when predicting ejection fraction based on 12-lead ECG data. The researchers also observed that providing specific combinations of electrode data improved prediction accuracy further.
Gyawali emphasized that while these AI tools are not yet ready for clinical practice due to reliability concerns, successfully training them could help clinicians better protect cardiac health among rural populations.
“Heart failure affects more than six million Americans today, and factors like our aging population mean the risk is growing rapidly — approximately 1 in 4 people alive today will experience heart failure during their lifetimes. The prevalence is even higher in rural Appalachia, so it’s critical the people here do not continue to be overlooked.”
