Hello Everyone!

The SARS-CoV-2 virus and the disease it causes, “COVID-19" outbreak has become the world’s biggest social, healthcare pandemic in 21 st century. At the time of writing, there are over 10.71 million confirmed cases of COVID-19 across the globe causing 516,000 deaths. According to official reports, the largest numbers of confirmed cases are in the United States, Brazil, Italy, Spain, and France. However, even the countries that the new coronavirus has hit less aggressively are still under considerable strain. As many as 213 countries and territories have registered COVID-19 cases, and the entire world is buzzing with uncertainty and questions. The COVID-19 pandemic was first confirmed in Sri Lanka on 27 January 2020, after a Chinese woman from Hubei Province in China was admitted to the National Institute of Infection Diseases. As of 27th June 2020, 2054 confirmed cases have been reported in the country with 11 deaths.

The question which remain is how people can help the world to fight against this massive
outbreak. Especially from a technical perspective, this problem can be addressed with the help of information technology and the use of data. The Artificial Intelligence (AI) tools and data science techniques plays a major role in this fight against covid- 19 in different ways like predicting vulnerable suspects, support in medical experiments in developing a cure, maintain accurate data and control mislead information and infodemic situations worldwide, hospitals and healthcare process management, and helping out the people locked-down with the support information technology applications etc.. Among all the solutions and measures, I will focus on ‘How the data science and the Artificial Intelligence applications can help to fight against and survive lives.

Covid 19 cases analysis

Many countries have declared restrictive measures, such as lockdown, shelter in place, or stay at home orders, to contain the pandemic at a local level. As of 25 March 2020, Sri Lankan authorities also have tracked down over 14,000 people who had contacted the identified patients and had ordered self-quarantine for such people. Apart from taking those measure many countries have already taken the support of Information Technology, the AI and data science which have become a key weapon in tracking and tracing cases during this pandemic. Deploying those technologies has sometimes meant balancing the need to conquer the virus with the conflicting need to protect individual privacy. As the initial crisis gives way to long-term policies and public health practices, governments are required to build trust in AI to ensure future protections can be deployed and maintained.

As examples, AI’s surveillance superpowers are being used to help break the chains of viral transmission across the globe. Russia maintains COVID-19 quarantines through large-scale monitoring of citizens with CCTV cameras and facial recognition. China is using AI-powered drones and robots to detect population movement and social gatherings, and to identify individuals with a fever or who aren’t wearing masks. Meanwhile, Israel is using AI-driven contact tracing algorithms to send citizens personalized text messages, instructing them to isolate after being near someone with a positive diagnosis. Many of these measures were taken by analyzing rapidly gathered personal data. In fact, South Korea’s high-octane blend of data from credit card payments, mobile location, CCTV, facial scans, temperature monitors and medical records has been a key part of a broader strategy to trace contacts, test aggressively and enforce targeted lockdowns. The combination of these effects has helped the country flatten its curve. Even in Sri Lanka it is believed that data has highly help to take relevant measure on exact time and control the virus spread.

Contact tracing is an effective way to slow COVID-19. It involves getting in touch with a person's close contacts after that individual tests positive for the virus and telling them to self-isolate. Contact tracing is time-consuming, although it's getting easier as more people take social distancing seriously. Data scientists and medical experts teamed up at Oxford University to make contact tracing even more efficient. They are working on the project asserted that mathematical models showed them how traditional methods of contact tracing used in public health are not fast enough to thoroughly slow the spread of COVID-19.

Feedback Loop
Covid-19 detection with CT scan image processing

To identify the new cases, threats by the region, as well as to take re-opening decisions, a
feedback loop is another concept where data science can help with the support of general public. Social media data scraping, surveys and polls over social media can collect data using this feedback loop where same concept can be applied to maintain healthcare demand under the threshold of what is available in a region. Facebook & google already doing such analysis, and the visualized outcomes and predictions will provide a massive support to understand patterns of spreading, regions to re-open or to lockdown, and to provide necessary support to people by relevant authorities. AI can also help predict its progress. For example, BlueDot AI was able to predict the early spread of the illness from Wuhan to other Asian cities based on airline ticketing data. AI-driven predictions of disease spread can then guide public health authorities in their decisions for resourcing and actions required in certain locations. World Health Organization (WHO) considers testing to be vital in combating the spread of the disease, so there is research underway using AI to identify COVID-19 patients from other sources, such as CT scans. Machine learning is already used to identify all types of illnesses, from cancer to eye diseases, so this is a route with some potential, even if CT scans are unlikely to be useful as an early warning signal of the illness.

Today, many countries are taking decision on reopening where some countries (ex: European countries) have already taken necessary steps to reopen even if the spread continues. Otherwise all the countries must face a major issue due to this massive economic drop resulting over continuous lockdown. So, as well as for curing and minimizing the virus spreading, data sciencetechniques can help to these emerging concerns like predicting proper measures for reopening processes, building the economy etc.

When considering re-opening plans, data science can already provide ongoing, accurate
estimates of health system demand, which is a requirement in almost all reopening plans. We need to go beyond that to a dynamic approach of data collection, analysis, and forecasting to inform policy decisions in real time and iteratively optimize public health recommendations for re-opening. While most reopening plans propose extensive testing, contact tracing, and monitoring of population mobility, almost none consider setting up such a dynamic feedback loop. Having such feedback could determine what level of virus activity can be tolerated in an area, given regional health system capacity, and adjust population distancing accordingly.

Face-mask detection of general public

To maintain proper health measures and habits among general public such as wearing face
masks, keeping social distance is critical to follow as recommended by WHO. A few days ago, they have officially confirmed that the world has not yet even met the peak of the first ripple of the pandemic, where a second ripple has already emerged from a giant counties like China, South Korea and some states of US which are believed that the virus spread has been successfully controlled. So, monitoring general public will add a massive advantage to a country, as well as for an organization regarding its employees. But this task costs highly as well as not practically possible in some situation. With the proper data, AI models with use of image processing and Convolutional Neural Networks (CNN) can address those issues in detection of face masked and non-masked public as well as social distancing in a large scale as manual supervision won’t require. In Chinar they use drones with cameras, where visual feedback is analyzed with a CNN to monitor public and predict danger. During the quarantined period I was also able to build a simple CNN model which can be used to detect face-make crowd with an artificially createddataset. Those capabilities can also help in hospital task automation where workload of the health service workers can be reduced by automation.

The Infodemic

The Coronavirus pandemic has been accompanied by an unprecedented ‘infodemic'. Once again, online platforms such as Social media like Facebook, twitter are used as the main tools for disinformation and consumer hoaxes. Data science and AI tools like text processing and prediction tools, Natural Language Processing and Image Recognition, focuses on facilitating access to authoritative sources, tackling harmful content and systematic take down of exploitative or misleading ads while at the same time preserving the freedom of expression and information on the social media platforms as well as other digital platforms automatically. So, in this way, unnecessary fears and troublous situations among people and communities can be minimized.

However, the pandemic is still rising over the world where continuous alerts has been sent by authorities every day. Risk is still out there and the whole world has faced a situation where all measures are getting out of control day by day. In such situation, data science techniques and AI tools play a huge role with supporting decisions, inventing cures, controlling spreading, as well as handling infodemic. Data scientists and technology workers play an immense role in this fight against covid-19 as well as the healthcare service workers and defense services. As we discussed these techniques can be used in various innovative ways to fight against this pandemic for a better world.