By Dickson Omobola
Nigerian physician and healthcare administrator, Dr Ifiala Ifiala, has called for wider adoption of data-driven healthcare systems to improve access to medical services and reduce disparities affecting underserved populations.
Ifiala made the call during an interview, where he argued that advances in medicine alone would not guarantee better health outcomes unless healthcare systems were intentionally designed to identify and address inequities.
According to him, millions of patients still experience unequal access to quality healthcare because many health systems fail to adequately identify barriers that prevent vulnerable groups from receiving timely care.
“Improving health outcomes requires more than excellent clinical care. It requires healthcare systems that use data to identify barriers to care, allocate resources efficiently, and ensure that underserved populations are not left behind,” he said.
Drawing from his experience as a Nigerian-trained physician, healthcare administrator and Programme Director in a nonprofit healthcare organisation focused on human services in Massachusetts, United States, Ifiala said health disparities were often driven by inefficiencies in healthcare delivery rather than disease alone.
He added that unequal access to quality healthcare was not limited to low-income countries, noting that disparities also existed across demographic groups such as income level, race, educational background, age and place of residence.
The researcher explained that predictive analytics could help healthcare organisations identify high-risk populations, improve patient access, optimise resource allocation and support operational decisions that enhance healthcare outcomes.
Highlighting one of his recent research works published in the International Journal of Healthcare Sciences, Ifiala said the study addressed the persistent underrepresentation of minority groups, older adults and economically disadvantaged communities in clinical trials. According to him, the research introduced a framework known as Constrained Multi-Objective Fair Representation Optimization, which combines machine learning and constrained optimisation to improve demographic representation while maintaining scientific standards.
“Clinical trials should generate evidence that reflects the diversity of the patients who will ultimately receive these therapies. Our findings demonstrate that equity and scientific excellence are complementary goals, not competing ones,” he said.
Ifiala urged clinicians, healthcare administrators, policymakers and data scientists to work together in developing evidence-based solutions that improve healthcare access. He said, “Health equity should not remain an aspiration discussed only in policy documents. It should become a measurable outcome of every healthcare system. When healthcare systems are intentionally designed around equity, everyone benefits.”
