Oladipo Kolawole, an infectious disease expert, says Africa must strengthen its capacity to own, analyse and develop artificial intelligence tools from its genomic data to improve disease surveillance and public health outcomes.

Mr Kolawole, an associate professor of Infectious Diseases, made the call at the fourth Annual Scientific Symposium organised by the Institute of Human Virology Nigeria on Monday in Abuja.

Mr Kolawole said Africa could not achieve effective genomic intelligence if AI models continued to rely largely on datasets generated from populations outside the continent.

He said Whole Genome Sequencing, combined with machine learning, could help African countries predict disease trends and antimicrobial resistance, provided the technologies were trained with locally generated data.

According to him, models developed from data outside Africa may not accurately reflect the continent’s diverse genetic and pathogen profiles.

Mr Kolawole cited antimicrobial resistance prediction as an example, saying some global AI models predicted ciprofloxacin resistance with about 75 per cent accuracy in England but recorded only about 50 per cent accuracy when applied to African data.

He said the disparity demonstrated the need for African researchers to develop models based on the continent’s own data.

The expert, however, said the absence of comprehensive genomic datasets should not prevent African researchers from beginning the process. He advised researchers to use available high-quality data to develop foundational models that could be improved as more metadata and genomic information became available.

On concerns about the potential misuse of advanced biotechnology and AI tools, Mr Kolawale said biosecurity measures were already being institutionalised in research settings. He said researchers and students at his institute were required to sign biosecurity agreements before commencing their engagements.

Mr Kolawole added that researchers must remain legally and ethically accountable for the technologies they develop and use.

The session chairperson, Alash’le Abimiku, also stressed the importance of accurate metadata collection, recalling difficulties encountered during COVID-19 research in linking genomic information to clinical profiles because of missing metadata.

She urged researchers to incorporate comprehensive metadata documentation and quality control into genomic data collection from the outset.

(NAN)