In Nigeria and globally, HBV is associated with substantial morbidity and mortality, posing a significant threat to public health. Approximately 300 million people live with this virus, and 90% of infected people are unaware of their infection status and risk infecting others. Immunoassay is the current gold standard for hepatitis B surface antigen detection, involving assays that are prohibitively expensive and require specialised facilities. However, access to this specialised test in resource-constrained settings like Nigeria is limited, particularly for rural and isolated laboratories. Routine pathology data in tandem with machine learning provides potentially important opportunities to advance innovation in HBV diagnosis.

 

In this seminar, I will discuss findings from my research which aimed to develop a machine learning decision support system for early detection of HBV infection, and build evidence to optimise its generalisability and potential clinical utility.

 

The research draws on HBV data and contextualises findings through a meta-analysis to understand the burden of HBV in Nigeria. It further evaluates the development and completeness of reporting of machine learning models for predicting clinical outcomes associated with blood-borne viral infections. This generates evidence for the development of HepB LiveTest, a machine learning enabled diagnostic model (translated into a web-accessible app) that uses routine pathology markers to predict a patient HBV infection status, with a suit of real-time decision support. Findings from this research provide a platform to offer timely decision support to clinicians and optimise the quality of life for HBV patients in vulnerable populations.

 

Busayo Ajuwon has a background in microbiology, during which time research endeavours evolved on the epidemiology of Shiga toxin-producing Escherichia coli O157:H7. Prior to undertaking his PhD, Busayo worked with the Department of Microbiology, Kwara State University, Nigeria.

 

His current research interests lie at the intersection of machine learning and public health. Busayo is particularly interested in the application of machine learning to fundamental infectious disease to improve patient care and health outcomes, particularly for marginalised populations.

 

His PhD research focuses on developing a machine learning decision support system for early detection and clinical management of HBV infection.