Chronic Disease Progression Could be Evaluated with Artificial Intelligence
Researchers at University of Buffalo have tapped into the power of artificial intelligence for developing a novel system that models the progression of chronic disease with the aging of the patients. Cardiovascular and biological markers are examined by the AI model for determining the health status of the patient, along with the disease risks across their lifespan. PhD Murali Ramanathan, a professor of pharmaceutical sciences at the University of Buffalo and lead author, said in a press release that there was an unmet need for approaches that can give guidance regarding pharmaceutical care in the presence of chronic and aging co-morbidities across the lifespan. He stated that innovative modeling of disease progression could help bridge some of this knowledge gap.
The American Heart Association states that a number of conditions can be referred to as cardiovascular disease, such as heart attack, heart disease, heart valve problems, arrhythmia, heart failure and stroke. The statistics provided by the Centers for Disease Control and Prevention show that every 36 seconds, a person dies in the United States because of heart disease. It also added that the total number of deaths in a year due to this problem is around 659,000. This model could come in handy for assessing the risks in chronic drug treatment in the long term.
Clinicians can also take advantage of it for monitoring the responses to the treatment for conditions, such as high cholesterol, diabetes as well as high blood pressure, which could become more frequent with age. Other researchers who were also involved in the project included PhD Martin Lysy, who is employed at the University of Waterloo as an associate professor of actuarial science and statistics, PhD Rachael Hageman Blair working at the UB School of Public Health and Health Professions as associate professor of biostatistics and first author PhD Mason McComb, who is an alumnus of UB School of Pharmacy and Pharmaceutical Sciences.
There were three case studies that were used for providing the data to the research team for their evaluation and they came from the third National Health and Nutrition Examination Survey (NHANES), which assessed the cardiovascular and metabolic markers of almost 40,000 people in the United States. Measurements like body weight, temperature, and height are also included in biomarkers, which are used for diagnosing, treating and monitoring countless diseases and overall health. A total of seven metabolic biomarkers were examined by the team, which included waist-to-hip ratio, body mass index, high-density lipoprotein cholesterol, total cholesterol, glycohemoglobin, glucose and triglycerides.
Pulse rate, homocysteine and diastolic and systolic blood pressure were the cardiovascular biomarkers examined. The AI model evaluates the changes in cardiovascular and metabolic biomarkers, which allows it to learn how those measurements are impacted by aging. Thanks to machine learning, the memory of previous biomarker levels was used by the system for predicting future measurements. This can help in revealing just how cardiovascular and metabolic diseases can progress with time. The data can undoubtedly be useful for clinicians because they can use it for prescribing the appropriate treatment in order to combat or treat the disease or condition, depending on the case.
