South Africa harnesses artificial intelligence, machine learning in Covid-19 fight

In the “new normal”, Sivasubramanian says, organisations are also developing new cloud services to meet customer needs and to ensure business continuity.

South Africa harnesses artificial intelligence, machine learning in Covid-19 fight

artificial intelligence

South Africa has joined its global counterparts in the use of artificial intelligence (AI) and machine learning (ML) to tackle the Covid-19 pandemic, says Swami Sivasubramanian, Vice President for Amazon Machine Learning at Amazon Web Services (AWS).

He says now more than ever, AI and machine learning innovation is critical because of its potential to help communities and businesses overcome the coronavirus pandemic.

According to Sivasubramanian, in the past months, organisations spanning all industries across public sector, pharmaceuticals, non-profit organisations and more, have deployed ML to respond to this unprecedented situation.

“We’re seeing three main areas where ML is having an impact right now – scaling customer communications, understanding how Covid-19 spreads, and speeding up research and treatment,” he notes.

For him, ML technology plays an important role in enabling that shift by providing the tools to support remote communication, enable telemedicine, and protect food security.

“In South Africa, we have seen how providing access to advanced technologies such as AI and ML is vital to stopping the spread of Covid-19 and helping individuals quickly find medical help when they fall ill.”

GovChat, South Africa’s largest citizen engagement platform, launched a Covid-19 chatbot in less than 2 weeks using Amazon Lex, an AI service for building conversational interfaces into any application using voice and text.

The chatbot provides health advice and recommendations on whether to get a test for Covid-19, information on the nearest Covid-19 testing facility, the ability to receive test results, and the option for citizens to report Covid-19 symptoms for themselves, their family, or household members.

Another example is APN partner – A2D24. In just three days, A2D24 was able to develop and deploy an automated AI platform using Amazon Lex for a private hospital group, to inform anyone who has been in one of their hospitals of possible exposure to a confirmed Covid-19 patient.

The system automatically sends an alert message and conducts an SMS-based triage where, each day, patients are asked questions about the symptoms they are experiencing and, based on the responses, the chatbot recommends what to do, and whether to seek further medical help.

Another tool A2D24 developed is a Covid-19 self-declaration, WhatsApp integrated Amazon Lex chatbot for a well-known South African mine to connect with employees directly verses relying on briefs floating around in the workplace. The solution allows employees to self-declare before returning to work whether they or their family members have attended large gatherings, weddings or other situations that may heighten their vulnerability to Covid-19.

Those cleared to return to the mine have their temperatures put into the WhatsApp chatbot and are permitted entry into the mine. The AI-powered self-declaration tool also enable mines employees to receive timely and convenient medical care, and reduces potential Covid-19 exposure to others.

Information overload

Sivasubramanian is of the view that healthcare providers and researchers are faced with an exponentially increasing volume of information about Covid-19, which makes it difficult to derive insights that can inform treatment.

In response, he says, AWS launched CORD-19 Search, a new search website powered by machine learning, which can help researchers quickly and easily search research papers and documents for answers to questions.

CORD-19 Search produces precise answers as well as source documents. “Built on the Allen Institute for AI’s CORD-19 open research dataset of more than 128 000 research papers and other materials, this machine learning solution can extract relevant medical information from unstructured text and delivers robust natural-language query capabilities, helping to accelerate the pace of discovery, where the speed of Covid-19 disease intervention, progression, and treatment is critical.”

Sivasubramanian is inspired by the innovation already happening in Africa regarding the use of AI and ML to fight the coronavirus.

He points out that organisations on the continent are leveraging advanced technologies such as AI,ML Internet of Things, mobile services, and more to drive innovation.

“And, the addition of the AWS Africa (Cape Town) Region has made innovation possible for more businesses of all sizes and helped accelerate the adoption of AI and ML.”

He explains that the AWS Africa Region also enables organisations to provide lower latency to end users across Sub-Saharan Africa and spin up remote learning programmes or standing-up remote working platforms.

“We have seen how providing access to scalable, dependable, and highly secure computing power is vital to keep organisations moving forward.”

Sivasubramanian notes that one example in Africa is Aella Credit – a financial services technology start-up based in Lagos, Nigeria, that provides easy access to credit for the world’s underbanked.

Aella uses Amazon Rekognition to help verify new customers’ identities in order to provide instant financial loans, all without human intervention. Such a pioneering business solution has obvious application during the pandemic, he says.

He says one of the important ways to improve patient care and accelerate clinical research is by understanding and analysing the insights and relationships that are “trapped” in free-form medical text, including hospital admission notes and a patient’s medical history. Amazon Comprehend Medical is a natural language processing service that makes it easy to use machine learning to extract relevant medical information from unstructured text.

The South African National Department of Health is working to create paperless hospitals in the country. Paper-based clinical records in healthcare facilities result in extended patient waiting times (sometimes between 60 and 80 minutes); reduced clinical care due to files being lost in overcrowded filing rooms; and increased litigation costs.

Using Amazon Comprehend Medical, regional public hospitals implemented indexing systems for easier retrieval of scanned patient records. Called Hybrid e-scripting, the solution enables electronic data storage without typing, an e-sketch pad for electronically accessible medical diagrams, and easy-to-use automated pharmacy labelling to reduce medication dispensing time. The impact to implementing this solution was a 90% reduction in patient wait time for fulfilling prescriptions, a 10% reduction in patient hospital wait time, and a cost savings of R12 million in software licenses.

Sivasubramanian also observes that well-established financial services organisations in Africa are moving to AWS to become more agile, modernise legacy systems, and speed up innovation. As an example, he says Africa’s largest and oldest financial services provider, Old Mutual, selected AWS as its preferred cloud provider and is migrating its applications, including more than 1 000 core insurance applications and product administration systems, to AWS, shutting down its data centers by early 2022.

Old Mutual is using a range of AWS machine learning services including Amazon Lex and is developing a chatbot for their oldmutual.co.za website to provide responses to customers instantly, through the customer’s preferred channel – voice, email, web, or text. This has significantly improved customer service and has reduced operational costs and decreased the time between deployments. The insurer has also started exploring additional AWS ML technologies, such as Amazon SageMaker, to develop ML-powered automated investment options to help customers make the right decision when saving to achieve their financial goals.

“At AWS, we have been focused on bringing the same 20 plus years of Amazon.com’s knowledge and capability in machine learning to our customers,” Sivasubramanian says.

“Our mission is to put machine learning into the hands of every developer and data scientist. Our customers have responded in turn as the vast majority of machine learning being done in the cloud today is being done on AWS.

He notes that with an extensive portfolio of services at all three layers of the technology stack, more customers reference using AWS for machine learning than any other provider.

“With the broadest and deepest portfolio of machine learning services available in the cloud, AWS fuels its innovation from the feedback it receives from Amazon, as well as the thousands of other customers using its machine learning capabilities. In 2019 alone, AWS launched more than 250 machine learning features and capabilities.”