Follow Us on Google
By Rita Okoye
In a ground breaking contribution to public health research, Bolaji Adekunle has developed a framework for AI-driven patient risk stratification models that could redefine preventive healthcare delivery in Nigeria and across the globe.
His 2023 journal article, “AI-Driven Patient Risk Stratification Models in Public Health: Improving Preventive Care Outcomes through Predictive Analytics”, demonstrates how predictive analytics can help healthcare systems anticipate disease risks and allocate resources more effectively ushering in a new era of prevention rather than reaction.
Preventive healthcare remains a pressing challenge in Nigeria. With limited hospital capacity, overstretched medical staff, and rising cases of chronic conditions such as diabetes and hypertension, many patients are only diagnosed at advanced stages when treatment is costly and outcomes are poor. Traditional care models focus on illness after it appears, often too late to make a meaningful difference.
Adekunle research proposes a shift: using artificial intelligence to stratify patients by risk levels before illnesses develop. By analysing large-scale data, including patient histories, demographics and lifestyle factors, AI systems can classify individuals into high, medium or low-risk groups. This allows health providers to proactively target high-risk patients with early interventions such as screenings and lifestyle programs, support medium-risk patients through continuous monitoring and counselling, and sustain low-risk patients with routine preventive services. The goal is not to replace doctors but to empower them, Adekunle explained.
“Artificial Intelligence can help identify hidden risks and give healthcare workers sharper tools to act early before diseases escalate.”
The potential benefits are significant. Predictive analytics could reduce preventable hospital admissions, optimize resource allocation, and improve patient outcomes, especially in resource-constrained systems like Nigeria’s. Yet the research also highlights key challenges: ensuring data privacy, addressing bias in algorithms, and building the digital infrastructure required to support Artificial Intelligence integration in healthcare facilities across the country.
Despite these hurdles, the promise of predictive analytics is undeniable. Imagine a future where a patient in Lagos visits a local clinic for a routine check, and the system quietly flags them as high-risk for hypertension. Instead of waiting for symptoms to appear, the clinic can act immediately, offering preventive advice, monitoring, and treatment.
For Nigeria, where the majority of healthcare spending goes toward treatment rather than prevention such a system could save lives and reduce costs on a national scale.
“Public health systems are strongest when they prevent illness, not just treat it, with AI, we have the opportunity to shift healthcare from reactive to proactive, building a healthier future for all.” Adekunle emphasized.
While his article lays the theoretical and practical foundation, Adekunle envisions further research, collaborations with Nigerian health institutions and pilot projects that could bring these models into real-world application. His work has already begun attracting attention in academic and public health circles, positioning predictive analytics as a vital tool in reshaping healthcare systems in Africa and globally.
For Adekunle, the mission is clear: “If predictive models can help even one community reduce the burden of preventable illness, then we are moving in the right direction.”
With its focus on innovation, prevention, and public impact, this research underscores how artificial intelligence can be more than a buzzword it can be a lifeline for millions of patients in Nigeria and beyond.
