The ability to recognise the earliest signs of an infectious disease outbreak can determine how effectively health authorities contain its spread. Turning that critical window of opportunity into actionable intelligence is the focus of a new artificial intelligence innovation developed by Nigerian researcher Oluwatobi Akinbode, whose work is bringing statistical science and predictive technology together to address a major global health challenge.
Based in the United States, Akinbode has developed PRISM-EW™ (Probabilistic Rt-Integrated Surveillance Model for Early Warning), an AI-powered framework designed to analyse disease surveillance information, track transmission patterns and identify potential outbreaks before they develop into public health emergencies.
The innovation addresses a longstanding challenge in epidemiology: making sense of fragmented health data and translating it into reliable information that can guide public health decisions. Rather than examining reported infections, transmission trends and other outbreak indicators independently, PRISM-EW™ integrates these functions into a unified statistical AI framework.
Its architecture comprises five interconnected components: Preprocess, Reproduction, Incidence, Signal and Multi-Signal Fusion. Together, they combine surveillance data processing, transmission modelling, probabilistic forecasting and statistical outbreak detection.
A central feature is the Outbreak Pressure Index, a scoring mechanism that evaluates transmission trends, disease burden, unusual patterns in reported cases and forecast risks. By bringing these indicators together, the system classifies emerging threats according to their severity, providing public health professionals with a structured basis for assessing potential outbreaks.
The scientific expertise behind the development draws on Akinbode's research across statistical modelling, artificial intelligence and population health. At Duke University, he conducted quantitative research examining HIV risk factors through network analysis and statistical methods. His work contributed to a reported 30 per cent improvement in identifying individuals eligible for HIV pre-exposure prophylaxis, a preventive medication for people at risk of contracting the virus.
He also expanded his research into environmental health at North Carolina A&T State University, where he applied Bayesian statistical methods to investigate relationships between heavy-metal exposure and cardiovascular-disease risk. The study used data from the National Institutes of Health's All of Us Research Program, with findings published in the International Journal of Environmental Research and Public Health.
His professional experience extends beyond academic research. Akinbode's portfolio includes AI engineering at LexisNexis, National Science Foundation-supported statistical computing research, scholarly publications and international technology judging. He has also received competitive research awards and contributed to academic peer review, reflecting his involvement in scientific research and emerging technologies.
Explaining the thinking behind his innovation, Akinbode stressed that effective disease surveillance must move beyond documenting outbreaks after they occur. He believes intelligent systems should be capable of recognising early warning signals, quantifying uncertainty and providing health authorities with dependable evidence for intervention.
He further noted that disease prediction is not simply about generating forecasts but about understanding how infections spread, measuring associated risks and equipping decision-makers with information that can guide action before conditions worsen.
PRISM-EW™ is designed for public health agencies, epidemiological researchers and healthcare surveillance programmes seeking to strengthen their preparedness against infectious diseases. Its intended applications include monitoring threats such as influenza, COVID-19, measles and cholera.
Akinbode explained that the system brings established statistical and epidemiological methods into a coordinated predictive framework, enabling more consistent assessments of outbreak risks. He added that artificial intelligence delivers meaningful value in healthcare when its predictions are interpretable, scientifically grounded and useful to professionals responsible for critical decisions.
The development adds to the growing body of Nigerian expertise contributing to scientific research and technological advancement on the international stage. It also demonstrates how the application of advanced statistical methods and artificial intelligence can help address complex challenges affecting populations across the world.
As infectious diseases continue to test the capacity of healthcare systems, innovations that strengthen surveillance and improve preparedness remain important to protecting communities. Through PRISM-EW™, Akinbode is contributing to the advancement of predictive public health tools with the potential to support earlier interventions and reduce the human and economic consequences of disease outbreaks.
No comments:
Post a Comment