- Some of the methods we have used in the past to combat malaria, including bed nets, insecticides and repellents, are all useful intervention strategies to control the spread of malaria but they could be even more effective when combined with machine intelligence.
The term Artificial Intelligence (AI) is largely assumed to be one of those future technologies that will invariably destroy humanity’s progress.
This is a wrong assumption and if we are not careful, we may throw the baby out with the bath water.
The application of this technology in healthcare is showing promising results. A recent study, Novel Exploration Techniques (NETs) for Malaria Policy Interventions by a team of scientists at the IBM Lab in Kenya and Oxford University, reveal that some of the methods we have used in the past to combat malaria, including bed nets, insecticides and repellents, are all useful intervention strategies to control the spread of malaria but they could be even more effective when combined with machine intelligence.
The technology can augment the decision-making abilities of officials, to explore multiple “what if” intervention strategies for specific locations prior to any spending.
Preliminary results show that with AI, and machine learning, policy makers will begin to know what to use, where and when, and be more effective.
Malaria is a major problem in Kenya that according to World Health Organisation (WHO) affects in excess of 70 per cent of the population.
Although malaria remains the leading disease transmitted by mosquitoes, other diseases like Zika, Rift Valley Fever, Dengue, and Chikungunya are becoming increasingly common.
Globally, WHO’s 2015 report says that there were more than 212 million malaria cases and an estimated 429,000 malaria deaths. While the disease is more prevalent in sub-Saharan Africa, almost 50 per cent of world’s population is at risk.
Although current control measures have led to a 29 per cent reduction in mortality rates since 2010 in Kenya, we could do better with new technologies like AI and machine learning that the paper says can provide some potential answers.
Sekou Lionel Remy, a computer scientist at Nairobi-based IBM Research-Africa, says “We have access to decades of data for healthcare policy makers and public officials to make decisions, but it’s too much for any human to analyze alone.”
He further noted, “Thankfully, due to recent advancements in technology, including artificial intelligence (AI) and cloud computing, we can now augment the abilities of these decision-makers to combine their own intellect with hard evidence to make data-driven decisions.
"We have demonstrated this in a new scientific paper which shows how AI combined with data from OpenMalaria can aid officials in knowing what prevention strategies to use, where and when, to be most effective to prevent the spread of malaria -- this is particularly critical as budgets become even more constrained.”
Most scientists think that this is just the beginning of great things that will come out of these emerging technologies.
The possibilities are endless including: “how AI may be used to tackle such Grand Challenges, they are continuing to research how we can achieve more nuanced decisions through training machines to understand the impacts of seasonality; explore more intervention options; target interventions to specific populations; deploy across locations; and account for dynamic changes in the environment as we observe new real-world data. This I believe would bring us closer to the objective of malaria eradication with AI.”
We are at the margins of making cost effectiveness of malaria intervention strategies, levelling the playing field and co-ordinating how we can do the most good for the greatest number of people.
Perhaps the best example is “a 2017 study which reported that insecticide-treated nets are consistently the most cost effective intervention across a range of transmission locations.
Yet, their results suggest that for simulated scenarios in Western Kenya, it may be more cost effective to perform indoor residual spraying programmes for a small proportion of households, instead of continuing to scale the deployment of insecticide-treated nets.”
With these new findings, policy makers have the ability to determine the most effective intervention strategies for different locations, thus reducing the cost of managing malaria.
Each technology comes with its threats but it is imperative that we look into what opportunities it presents before destroying it even before we fully understand its applications.