NeoGuard

Universiti Malaya
Socio-Economics Driver
Science & Technology Driver
Sensor Technology
Technology Readiness Level
Intellectual Property
PI2023006600

A significant number of babies affected by Small-for-Gestational-Age (SGA) conditions go undetected before birth, with studies showing that up to 50% of SGA cases are missed. This lack of early detection leads to serious consequences, including a 5 to 10 times higher risk of fetal death. Current clinical methods in Malaysia lack the precision and personalisation needed to reliably identify at-risk pregnancies, resulting in poor outcomes and increased emotional and financial strain on both families and healthcare systems. There is a pressing need for a more accurate, locally relevant, and accessible method to detect SGA early in order to improve pregnancy outcomes.

NeoGuard offers an AI-powered solution designed to improve the early detection of Small-for-Gestational-Age (SGA) babies. The system uses AI models trained on local Malaysian data, ensuring predictions are tailored to the specific characteristics of the population. By analysing both maternal and fetal biometric information, NeoGuard can accurately predict whether a baby is at risk of being SGA. The platform provides a simple three-step process: input relevant patient information, predict infant growth outcomes, and recommend appropriate next steps for care. This approach enables earlier intervention, supports clinical decision-making, and ultimately helps to reduce the risk of fetal complications and deaths. The solution also lowers the financial and emotional burden on families and healthcare providers by facilitating more targeted and timely prenatal care.

NeoGuard is innovative because it uses AI models trained on Malaysian data to detect Small-for-Gestational-Age (SGA) babies more accurately than current methods. By combining maternal and fetal information, it gives personalised predictions and clear recommendations for doctors. The system is easy to use with just three steps: enter patient details, get a prediction, and follow the suggested care plan. It works better than existing tools and can be used in both cities and rural areas. Its key strengths are local personalisation, high accuracy, and simple, practical use in real-world healthcare settings.

Project

Showcase Your Project Here

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.