Hyderabad: An Artificial Intelligence (AI)-based prediction model to detect obesity risk has been developed by researchers at Woxsen University in collaboration with a US scientist.
The research team, consisting of Bobba Bharath Reddy, Dr. Hemachandran Kannan, Dr. Shahid Mohammad Ganie, and US scientist Prof. Manjeet Rege, investigated the combination of multiple machine learning methods to predict obesity risk from lifestyle data.
The healthcare sector, online medical repositories, and hospitals are generating vast amounts of data, which provide valuable resources for researchers aiming to leverage AI techniques to tackle real-life health issues.
The researchers selected three algorithms from each ensemble method, each with distinct characteristics and strengths, to demonstrate the effectiveness of their proposed model from various perspectives.
While BMI (body mass index) is commonly used as the primary indicator of obesity risk, the researchers identified limitations in BMI's ability to capture the full complexity of obesity, which is influenced by behavioral, environmental, and genetic factors.
They noted that BMI does not account for critical health indicators such as muscle mass, fat distribution, or other variables, which may reduce the accuracy of obesity classification.
The findings were published in a paper titled 'Investigation of Ensemble Learning Techniques for Obesity Risk Prediction Using Lifestyle Data' in the Decision Analytics Journal by Elsevier.