Evaluating Chronic Disease Progression With Artificial Intelligence

With artificial intelligence, University of Buffalo researchers have developed a novel system that models chronic disease progression as patients age.

The AI model examines metabolic and cardiovascular biomarkers to determine the health status and disease risks across a patient’s lifespan. According to researchers, these findings are critical due to the increased risk of developing metabolic and cardiovascular diseases as individuals age.

“There is an unmet need for scalable approaches that can provide guidance for pharmaceutical care across the lifespan in the presence of aging and chronic co-morbidities,” lead author and professor of pharmaceutical sciences in the UB School of Pharmacy and Pharmaceutical Sciences, Murali Ramanathan, PhD, said in a press release.

“This knowledge gap may be potentially bridged by innovative disease progression modeling.”

According to the American Heart Association, cardiovascular disease can refer to many conditions, including heart disease, heart attack, stroke, heart failure, arrhythmia, and heart valve problems.

According to the Centers for Disease Control and Prevention, one person dies every 36 seconds in the United States due to heart disease, and around 659,000 people die from the condition each year.

The model could promote risk assessment for long-term chronic drug treatments and assist clinicians in monitoring treatment responses for conditions including diabetes, high cholesterol, and high blood pressure, which also become more frequent with age.

Additional researchers included first author and UB School of Pharmacy and Pharmaceutical Sciences alumnus Mason McComb, PhD; Rachael Hageman Blair, PhD, associate professor of biostatistics in the UB School of Public Health and Health Professions; and Martin Lysy, PhD, associate professor of statistics and actuarial science at the University of Waterloo.

The research team studied data from three case studies within the third National Health and Nutrition Examination Survey (NHANES) that assessed the metabolic and cardiovascular biomarkers of almost 40,000 people in the US.

Biomarkers, which also feature measurements such as temperature, body weight, and height, are used to diagnose, treat, and monitor overall health and countless diseases. 

The team examined seven metabolic biomarkers, including body mass index, waist-to-hip ratio, total cholesterol, high-density lipoprotein cholesterol, triglycerides, glucose, and glycohemoglobin. The cardiovascular biomarkers examined were systolic and diastolic blood pressure, pulse rate, and homocysteine.

By evaluating the changes in metabolic and cardiovascular biomarkers, the AI model can learn how aging impacted those measurements. With machine learning, the system used memory of previous biomarker levels to predict future measurements to reveal how metabolic and cardiovascular disease can progress over time.