Connect with us

Africa News

How machine learning can save your life

Over 11000 people died during the 2014-2016 Ebola outbreak in West Africa.The virus hopped between Guinea, Leone, Nigeria and Liberia, before making its way to the UK and US. But what would have happened if analysis and machine learning stepped in to help solve the problem, asks ANESHAN RAMALOO of SAS.

Published

on

Over 11000 people died during the 2014-2016 Ebola outbreak in West Africa.The virus hopped between Guinea, Leone, Nigeria and Liberia, before making its way to the UK and US. But what would have happened if analysis and machine learning stepped in to help solve the problem, asks ANESHAN RAMALOO of SAS.

But what if we could have predicted the outbreak months before it happened, buying us time to take proactive measures to contain it and curb its spread?

With access to overwhelming volumes of data, the computational power needed to store and analyse this data in real time, and sophisticated algorithms that can find patterns in the data and alert authorities to health problems before they become, well, problems, pandemics don’t have to be as devastating as they have been in the past.

In fact, with advanced data analytics, we can better manage any disease – long-term, short-term or pandemic – resulting in better patient treatment, more efficient use of resources and cost savings.

It’s been done before.

By analysing data from social media, blogs, online forums and keyword searches, we were able to predict the 2012-2013 US flu season three months before the Center for Disease Control (CDC) issued its first official warning.

Imagine the impact if the same analytical power was applied across the entire healthcare spectrum – not only on a national and global level, but right down to the individual level.

Data evolution

In the past, health workers relied on manually intensive, paper-based systems to record infections and deaths during disease outbreaks. Not only was it easy for errors to slip through but because the data was anecdotal and historical, authorities did not get a complete understanding of the reach and impact of the outbreak.

During the Ebola outbreak, the CDC adopted a mobile data collection system that enabled health workers to instantly submit information to a database via text messages. This low-cost method of information gathering not only resulted in fewer errors but also allowed analysts to draw up detailed maps of population movements, which made it easier to understand how the disease was likely to spread, and where to set up treatment centres.

While this was certainly an improvement on the paper-based systems of old, the drawback was that mobile data was historic and did not provide researchers with the ability to track developments and population movements in real time.

Data-driven action

But mobile phones are just one source of data. Today, health authorities can overlay thousands of data sources – including social media, health and physician reports, keyword searches, media reports, transactional data from retailers and pharmacies, airline ticket sales, geospatial data and more – to not only better manage diseases and outbreaks when they do happen, but to see them coming months in advance – and what could happen if we don’t act on the information.

By mining structured and unstructured data, we can track the movements of infected populations and who they come into contact with; we can measure the success of containment policies, education campaigns and treatments – and what to do if they’re not working; we can determine the effect of weather and other environmental factors on the spread of diseases.

Never before have we been able to act on information to save lives, not just during pandemics but through better understanding and treatment of diseases.

Personalised treatment

Until now, standard treatments for diseases such as cancer and HIV have been applied to all patients, regardless of their unique profiles and with little understanding as to why some people respond well to certain treatments and others don’t.

But by analysing and creating ‘medical maps’ of individuals that take into account their anatomy, physiology, DNA, RNA and chemical composition, doctors can prescribe personalised treatments that have a greater chance of success.

There are many other benefits of data analysis in healthcare:

·        Personalised treatment can result in fewer hospital admissions and can produce faster results and better experiences for patients;

·        By better understanding the impact of lifestyle and diet on health, medical aid providers can educate their members with the aim of improving their health, which could result in cost savings for both the provider and the member;

·        Governments can use data to develop proactive approaches to protecting and promoting public health, to prioritise services and to find ways to cut costs so that they can provide healthcare to more citizens.

·        By sharing data and results from clinical trials and combining that data with academic, patient and industry data, medical researchers can better understand the genetics of viruses, why some strains are more deadly than others, and why some people are more resistant to viruses. This could spark innovation and generate new insights that ultimately improve treatment and outcomes.

AI and machine learning

As the use of intelligent algorithms, machine learning and natural language processing becomes more entrenched in advanced data analytics, technology will increasingly supplement the skills of humans to produce faster and more accurate medical diagnoses.

We’re already seeing successful applications of artificial intelligence (AI) in predicting relapse in leukaemia patients and in distinguishing between different types of cancer.

Machine learning can extract valuable insights from unstructured data like clinical notes and academic journals to provide even larger datasets that will transform the medical industry into a proactive front against diseases.

There are plenty of doomsday theories about how machines will supersede our intelligence and rise against us. But there aren’t enough stories about the potential of data analytics, AI and machine learning to supplement human skills and knowledge to drastically changes lives for the better – and even save them. Right now, it’s looking more likely that machines will actually help us to live longer – and I don’t know many people who would object to that.

 

  • ANESHAN RAMALOO, ‎Data Scientist and Senior Business Solutions Manager at SAS.

Africa News

IoT’s answer for Africa

IoT and digitization enables us to efficiently, proactively and predictively address the sustainability challenges that are faced globally and on the African continent, RESHAAD SHA, CEO of Liquid Telecom.

Published

on

With Africa’s population set to increase from around 1.3-billion in 2018 to 1.7-billion in 2030, both challenges and opportunities are presented with regards managing issues including food production and security pose  as well the utilization of limited natural resources in a sustainable manner.

Water scarcity and quality for example are realities that negatively impact health, food production and security. Population growth rates and climatic changes place an exponential demand on this scarce and dwindling resource. These are just some of the sustainability challenges facing not just the African continent, but other developing nations and the world as a whole. In addition to this, the demand for the delivery of basic services as healthcare and sanitation also increases.

Against this background of African population growth lies the grim projection that Africa will account for more than 50% of child deaths (under 5) by 2030, while each day, nearly 1000 children die owing to preventable water and sanitation-related diarrheal diseases according to the UNICEF 2017 trends in child mortality report. It’s an alarming fact, given that while some 2.6-billion people have gained access to improved drinking water sources since 1990, 663-million people still do not have access.

The department of Water Affairs and Forestry estimate that the agricultural sector accounts for more than 50% of water use in South Africa and experience water losses of between 30 and 40 per cent. Further, the department states that around 35% of irrigation system losses, often nutrient enriched and containing herbicides, pesticides, and other pollutants, return to rivers. These are just some of the ways in which reactive, inefficient, and manually driven processes have limited us in responding in an impactful manner and timeously mitigating these risks

It is for these reasons and other socio economic and environmental concerns that the United Nations has established its Sustainable Development Goals strategy, addressing the global challenges we face, including those related to poverty, inequality, climate, and environmental degradation.

We need to look at smarter ways that leverage technology in order to addressing these challenges. The situation requires a radical response that delivers a proactive, predictive and data driven approach to addressing these issues with exponentially growing levels of speed and impact.

The IoT ecosystem, comprising of sensors, connectivity, data analytics and workflow automation platforms, and applications are at the core of acquiring, analyzing and harnessing the insights that can be integrated into agriculture, service delivery, health and resource management processer – IoT is at the core of a digitization

One such sector which has benefited immensely from technology is in agriculture pest control, with the implementation of AI and IoT by Spanish startup AgroPestAlert. The innovation makes use of “smart” traps that capture insects and analyse their wing beats to identify their species and even their sex. Placed throughout the fields, the traps communicate with the system to predict an imminent invasion. The system will send alerts to phones, tablets and computers and use an easy-to-understand visual tool to cue farmers instantly.

Around 200-million Africans use approximately 1-million manual pumps across the continent to manually access clean drinking water.  IoT applications have been utilised in assuring the delivery of water through manual these pumps, According to estimates, at least one-third of those pumps will break down at least once in its lifecycle, and up to 70% will break in the second year of operation. The impact of not having access to clean drinking water is dehydration or water borne pandemics.

In the Kenyan Region of Kyusoa, Oxford University began a proof of concept project in 2013, which made use of motion sensors) to capture the movements of the pumps’ handle which was transmitted and analysed in real time. A decision support system based on real data was  used to predict pump malfunctions, allowing for a better planning and shortening the time needed to repair broken pumps, or avoiding malfunctions altogether, directly improving the access to clean drinking water for the rural population.

Liquid Telecom realise that the future of sustainability lies in technology and innovations such as IoT. We provide high speed fiber connectivity to interconnect as well as access platforms to build IoT solutions, in addition to access to Microsoft Azure suite of platforms for analytics and algorithm driven based processing and execution. Our Pan African network enables collaboration and cross border innovation and learning, fast well as the capability to efficiently scale out these solutions on Africa’s Liquid Cloud.

Continue Reading

Africa News

Africa start-up ecosystem can drive blockchain

Through nurturing and technical support, Africa’s tech start-up ecosystem can be a major driver of Blockchain-based innovation says BEN ROBERTS, Liquid Telecom’s Group Chief Technology and Innovation Officer.

Published

on

African communities have always come-up with inventive solutions to local problems. Take Somalia as an example. The country is said to have one of the largest diaspora populations in the world. It has few commercial banks and relations with international creditors remain fro­zen due to debts incurred in the late 1980s. 

So its population uses Hawala; an infor­mal value transfer system based on the per­formance and honour of a large network of money brokers. For example, it would mean a Somali based in the US would give money to a local branch agent, where it is sent to a cen­tral country clearing house, then onto a clear­ing house based in another country (typically somewhere in the Middle East). From there it goes to a Somali agent, before the funds are finally collected by an individual in Somalia.

Much like blockchain, the Hawala system is built on trust – but that’s where any similarities end. In fact, cryptocurrencies – many of which are blockchain-powered – may eventually be­come a replacement for Hawala and other exist­ing forms of international remittances. Cryptocur­rencies can enable people to exchange currency online without any middleman – even banks. 

International remittance is one of many compelling use cases for blockchain. The technology’s ability to digitise trust makes it a unique fit for many African countries, par­ticularly those where processes and supply chains remain poorly designed and susceptible to corruption.

At Liquid Telecom, we’re excited about the potential for blockchain technology across the region. Along with other emerging tech­nologies, we recognise this as another major new digital opportunity for businesses that utilises our network infrastructure and servic­es. The rise of blockchain innovation will rely on the skills and talent of the region’s soft­ware developers, who themselves rely on a high-speed internet connection and access to cloud-based tools. Our fibre footprint – which will soon stretch all the way from Cape Town, South Africa, to Cairo, Egypt – is providing the foundations for digital innovation, while our partnership with Microsoft is enabling access to the cloud-based services and tools needed to create digital solutions for local problems.

Last year, with support from Microsoft, we set-up our Go Cloud initiative, which is helping to provide the region’s start-up communities with technical support, training and access to software. Using Azure Cloud, start-ups can cut development time and experiment easily with modular, preconfigured networks and infra­structure, enabling them to iterate and validate blockchain scenarios quickly by using built-in connections to Azure.

We’re starting to see the first crop of African start-ups experimenting with blockchain and cryptocurrencies. Take Rwandan start-up Up­lus, which is utilising blockchain to secure all transactions on its digital crowdfunding plat­form. The technology also allows the platform to take contributions from any country and covert it to the local currency.

A lot of existing applications in Africa tend to fall short when it comes to user experience, and blockchain could certainly help address some of these issues – be it by creating a new trusted way to make payments or verify user identification. During this early stage of block­chain experimentation and proof of concept, it will be crucial for start-ups and businesses to develop solutions that are relevant for Afri­can communities. Without that, the technology won’t gather momentum.

Regulation can nurture or constrict the tech­nology and will have a role to play in being a ‘make or break’ for blockchain. Living in Ken­ya, I’m proud to see how proactive the gov­ernment has been in seizing the blockchain opportunity. The creation by the President of a taskforce earlier this year dedicated to blockchain – led by the former permanent secretary for Ministry of Information and Com­munications, Dr. Bitange Ndemo (see page 7) – shows how committed the country is to being a leader in emerging technologies. As more African countries follow Kenya’s lead, blockchain should hopefully find itself reso­nating more powerfully with local businesses and consumers.

Continue Reading

Trending

Copyright © 2018 World Wide Worx