Page 38 - EngineerIT February 2022 UPDATED

INDUSTRY, TECHNOLOGY, PRODUCTS AND INNOVATION

MACHINE LEARNING CAN SOLVE SOME OF

AFRICA’S BIGGEST CHALLENGES

rom better healthcare access to improved food security, For example, analytics of crop data can help identify diseases,
machine learning could tackle a wide range of challenges in enable soil health monitoring without the need for laboratory
Fdeveloping countries. testing infrastructure, and facilitate the creation of virtual
In 2020, a study published in Nature showed that Google’s cooperatives to aggregate crop yields and broker better prices with
machine learning artificial intelligence programme, DeepMind suppliers.”
AI, outperformed radiologists in detecting breast cancer. After
being trained on thousands of mammograms, the system was able Healthcare developments
to accurately identify 89% of breast cancer cases, compared to Machine learning can not only analyse tests and images to suggest
radiologists’ 74%. Just imagine what a difference the deployment diagnoses, but also aggregate data and update patients’ charts. It’s
of such a system could make in sub-Saharan Africa, where there are also rapidly expanding into other healthcare areas, including early
0.2 doctors per 1000 people, according to the World Bank. detection of diseases, treatment and research, says Moodley. “This
And that’s just the start. Marilyn Moodley, country leader for would free up physicians’ workloads, allowing them to spend more
South Africa and WECA (West, East, Central Africa) at SoftwareONE, time with patients and on actual patient care. Japan is already
says machine learning can help with some of the region’s most looking at augmenting its doctors with artificial intelligence to
pervasive problems, from reducing poverty and improving combat its doctor shortage.”
education to delivering healthcare and addressing sustainability In Africa, machine learning could plug the same gap, but also
challenges such as food demand. “Machine learning democratises address other challenges, she says. “Health systems in Africa
access to innovative and productivity-boosting technology to fuel face several structural challenges such as shortages of qualified
the growth the continent needs. It’s fundamentally reshaping how professionals or supplies, resulting in divergent outcomes for
work is done, allowing for a more efficient allocation of resources, patients. Even when facilities and staff are available, affordability
leading to increased productivity and, in the case of government, and rural/urban disparities can put needed services out of reach of
improving the delivery of services to citizens.” patients.”

Agricultural improvements For more information visit www.SoftwareONE.com.
The agriculture sector employs over 65% of Africa’s labour force
and accounts for 32% of gross domestic product (GDP), says
Moodley. “The World Bank estimates that African food markets
will be worth US$1 trillion by 2030, up from the current $300
billion. Demand for food is projected to at least double by 2050,
yet the sector is burdened with limitations. Land is degrading,
soil is becoming less fertile, water tables are dropping, pests are
becoming more resistant, and the climate is more vulnerable
and unpredictable. All this could have disastrous effects on food
availability in the future.”
Machine learning has the potential to improve productivity and
efficiency at all the stages of the agricultural value chain, she says.
“These technologies can empower small-holder farmers to increase
their income through higher crop yield and greater price control.

Send technical and news articles to engineerit@nowmedia.co.za

EngineerIT | February 2022 | 36