Muscat – An Omani research team has developed an artificial intelligence-powered health system capable of predicting childhood obesity with 97% accuracy, marking a regional first in the use of Internet of Health Things (IoHT) and machine learning to combat the growing threat of obesity.

The project – led by Nabila al Rashdi, Senior Lecturer at the College of Engineering at the National University of Science and Technology, and funded by the Ministry of Higher Education, Research and Innovation – combines IoHT devices, health sensors and electronic medical records to support early prediction, prevention and management of obesity in children.

Nabila said the system analyses biometric indicators and electronic health records, particularly those collected from birth to age two, to forecast the risk of childhood obesity. “By analysing biometric indicators and electronic health records, especially those collected from birth to age two, we can now predict the risk of childhood obesity with remarkable accuracy,” she said.

Among several machine learning models tested, including Random Forest, Support Vector Machine and XGBoost, Logistic Regression proved the most accurate, predicting childhood obesity risk by age 10 with 97.09% accuracy. The team also developed a mobile and web application allowing users to monitor calorie intake, weight, sleep and physical activity, and to receive customised weight loss advice and health tips.

The platform’s system evaluates factors such as age, gender, BMI, dietary habits and physical activity to deliver real-time, evidence-based recommendations for both patients and healthcare professionals.

Based on its findings, the research team recommends integrating the smart healthcare platform into national health programmes to enhance early detection and intervention, especially for children. It also urges greater investment in AI-powered healthcare to advance predictive and personalised medicine across Oman and beyond.

The team, supervised by Dr Varghese M J, has submitted a scientific manuscript detailing its findings to a peer-reviewed journal and is awaiting publication.