A team of researchers from the University of Buffalo has developed a new system that models the progression of chronic disease according to the age of patients using artificial intelligence. The study was published in the ‘Journal of Pharmacokinetics and Pharmacodynamics’.
The model assessed metabolic and cardiovascular biomarkers – measurable biological processes such as cholesterol levels, body mass index, blood sugar and blood pressure – to calculate health status and disease risks throughout of a patient’s life. The results are critical due to the increased risk of developing metabolic and cardiovascular diseases with aging, a process that has adverse effects on cellular, psychological and behavioral processes.
“There is an unmet need for scalable approaches that can provide guidance for lifelong pharmaceutical care in the presence of aging and chronic co-morbidities,” said lead author Murali Ramanathan, PhD, professor of pharmaceutical sciences at the UB School of Pharmacy and Pharmaceutical Sciences. “This knowledge gap can potentially be filled by innovative modeling of disease progression,” he added.
“The model could facilitate the evaluation of long-term chronic drug therapies and help clinicians monitor responses to treatment for conditions such as diabetes, high cholesterol, and high blood pressure, which become more common with age. “said Ramanathan. Additional researchers included first author and UB Faculty of Pharmacy and Pharmaceutical Sciences alumnus, Mason McComb, PhD; Rachael Hageman Blair, PhD, associate professor of biostatistics at 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 looked at data from three case studies as part of the Third National Health and Nutrition Survey (NHANES) which assessed the metabolic and cardiovascular biomarkers of nearly 40,000 people in the United States. The biomarkers also included measures such as temperature, body weight, and height, which are used to diagnose, treat, and monitor overall health and many diseases.
The researchers looked at seven metabolic biomarkers: body mass index, waist-to-hip ratio, total cholesterol, high-density lipoprotein cholesterol, triglycerides, glucose, and glycohemoglobin. Cardiovascular biomarkers examined include systolic and diastolic blood pressure, pulse rate, and homocysteine. By analyzing changes in metabolic and cardiovascular biomarkers, the model “learned” how aging affects these measures. With machine learning, the system used the memory of previous levels of biomarkers to predict future measurements, which ultimately revealed the progression of metabolic and cardiovascular disease over time. (ANI)
(This story was not edited by Devdiscourse staff and is auto-generated from a syndicated feed.)