Chinyere Okpara

With a background in applied mathematics and statistics, my proficiency lies in quantitative cohort research studies. My work focuses on retrospective analysis that supports evidence-based decision-making in patient care. Particularly in the field of oncology, I often apply machine learning and statistical methodologies to derive insights from electronic health records (EHR) and other clinical data sources.

One ongoing project involves leveraging machine learning to improve the detection of common bile duct (CBD) stones during cholecystectomy, a challenging problem that affects up to 2% of patients. This work aims to develop predictive models that enhance clinical decision-making and reduce post-operative complications related to retained stones.

My research also explores health disparities, with an emphasis on the impact of political and social determinants of health on patient outcomes. I aim to highlight patterns of inequity in healthcare access and treatment, with an objective of identifying areas for improvement.

A recent publication examines the correlation between baseline health, healthcare coverage, and COVID-19 disease severity during the pandemic peak. The study underscores the consequences of missed routine care and unmanaged chronic conditions, highlighting the strain on hospital resources and the need for more affordable healthcare access.

In addition to retrospective studies, I collaborate on surgical operations-research projects, working closely with administrative teams to develop data-driven solutions for resource allocation. My contributions include data analysis, visualization, and the development of tools to improve decision-making processes.