A little over a century ago, governments tackled the 1918 influenza with a combination of isolation, quarantine, better personal hygiene, disinfectants, and limits on public gatherings.
Yet, the pandemic claimed around 50 million deaths worldwide at a time when the world population was around 1.8 billion.
With considerable advancements in the areas of health technology, disease surveillance, medical care, medicines and drugs, vaccines and pandemic planning, governments were better equipped to handle pandemics in the years 1957 and 1968, and most recently in 2009 with the Swine Flu, or H1N1 flu, virus.
Governments also managed to ably control severe acute respiratory syndrome (SARS), Ebola and avian flu, or bird flu.
Despite these stellar achievements, SARS coronavirus 2 (SARS-CoV-2), which is causing the COVID-19 disease, has brought the world and its estimated 7.8 billion population to its knees. There are around 1.65 million confirmed cases so far, and slightly over 100,000 deaths, according to Johns Hopkins University.
Tech to the rescue
While the global lock down and paralysis can be attributed to several reasons including overconfidence and a lackadaisical attitude on the part of governments, which resulted in downplaying the impact of the virus, there are silver linings in the cloud too.
One among these is that technologies such as big data, cloud computing, supercomputers, artificial intelligence (AI), robotics, 3D printing, thermal imaging and 5G are being used to effectively complement the traditional methods of increased hygiene, self- and forced quarantines, and enforced global travel bans.
Consider these examples. Having enforced traditional measures in place, police officers in China now wear AI-powered helmets that can automatically record the temperatures of pedestrians.
The high-tech headgear has an infrared camera, and sounds an alarm if anyone in a radius of 16 feet has fever. Equipped with the facial-recognition technology, it can also display the pedestrian’s personal information, such as their name, on a virtual screen inside.
Officials at railway stations, airports and in other public areas in India, too, are using smart thermal scanners to record temperatures from a distance, thus helping in identifying potential coronavirus carriers.
Robots, 3D printers, are helping too
On 19 February, Danish company UVD Robots signed an agreement with Sunay Healthcare Supply—a medical equipment supplier to the Chinese market, to ship self-driving Danish disinfection robots to over 2000 hospitals in China to help fight COVID-19. With ultraviolet light, the Danish robot can disinfect and kill viruses and bacteria autonomously, effectively limiting the spread of coronaviruses without exposing hospital staff to the risk of infection.
“We are now helping solve one of the biggest problems of our time, preventing the spread of bacteria and viruses with a robot that saves lives in hospitals every day,” says Claus Risager, CEO of Blue Ocean Robotics and Chairman of the Board of UVD Robots–a portfolio company in Blue Ocean Robotics.
Similarly, robots delivered medication, patrolled and cleaned infected areas, led patients in exercises, and even performed robo-dances to entertain bored quarantined patients at the Whuhan Wuchang Hospital in China, according to an 18 March CNBC report.
This, even as 5G-powered temperature measurement devices flagged patients with fever symptoms at the entrance of the smart hospital that was jointly built by telecom carrier China Mobile and a communications company China Potevio Co. The robots were donated by Cloud Minds Technology–a SoftBank-backed startup based in Beijing.
Additive manufacturing, or 3D printing as it is better known, is also coming to the aid of medical workers to combat COVID-19. A 3D printing company in Italy, Isinnova, used a 3D printer to redesign a Venturi valve early this month.
Italy is battling the world’s worst outbreak of coronavirus outside of China, and these valves connect oxygen masks to respirators used by coronavirus patients suffering from respiratory complications. More valves were later 3D printed by another local firm, Lonati SpA, thus saving many lives in the process, according to a 14 March article by 3D Printing Media Network.
AI is proving its worth
Machine- and deep learning, subsets of AI, can sift through mountains of data and make very good predictions subject to the data being good.
As an example, Toronto-based health surveillance company, BlueDot, issued a warning to its customers to avoid Wuhan (where the virus originated) nearly three months back–31 December, 2019. BlueDot gathers disease data from myriad online sources. It, then, uses airline flight information to make predictions about where infectious diseases may appear next.
Similarly, Healthmap scrapes information about new outbreaks from online news reports, chatrooms and more, and is being used to track COVID-19 in real-time.
The tool was built by John Brownstein, chief innovation officer at Boston Children’s Hospital and a professor at Harvard Medical School, and his team. Developed shortly after the SARS outbreak, Healthmap organizes disparate data and generates visualizations that show how and where communicable diseases like the coronavirus are spreading.
University of Massachusetts Amherst (UMass) researchers have developed a portable surveillance device powered by machine learning. Called FluSense, it can detect coughing and crowd sizes in real time, then analyze the data to monitor flu-like illnesses and influenza trends such as the COVID-19 pandemic or SARS.
The FluSense platform comprises a microphone array (multiple microphones), Raspberry Pi (credit-card sized computer that plugs into a monitor or TV, and uses a standard keyboard and mouse), neural computing stick (using deep neural networks to draw inferences from data) and thermal camera (to detect temperature by recognizing and capturing different levels of infrared light).
“This may allow us to predict flu trends in a much more accurate manner,” says co-author Tauhidur Rahman, assistant professor of computer and information sciences at the university, and lead author Forsad Al Hossain. Results of their FluSense study were published Wednesday in the Association for Computing Machinery.
Al Hossain cites FluSense is an example of the power of combining AI with edge computing–a trend that enables data to be gathered and analyzed right at the data’s source. The next step is to test FluSense in other public areas and geographic locations.
…there’s more
Elsewhere, Dr. Arni S.R. Srinivasa Rao, director of the Laboratory for Theory and Mathematical Modeling in the MCG Division of Infectious Diseases at Augusta University, is developing an AI-powered coronavirus app to enable individuals to get free at-home risk assessment in just about a minute, based on how they feel and where they’ve been or travelled.
“People will not have to wait for hospitals to screen them directly,” says Rao. “We want to simplify people’s lives and calm their concerns by getting information directly to them.” Once the app is ready, it will live on the augusta.edu domain and likely in app stores on the iOS and Android platforms.
The app will also ask users to fill in details about common symptoms of infection and their duration including fever, cough, shortness of breath, fatigue, sputum production, headache, diarrhoea and pneumonia. An AI algorithm developed by Rao will, then, rapidly assess the individual’s information, and send them a risk assessment—no risk, minimal risk, moderate or high risk. This, even as it alerts the nearest facility with testing ability that a health check is likely needed.
If the patient is unable to travel, the nearest facility will be notified of the need for a mobile health check and possible remote testing.
Likewise, engineers of Bengaluru-based Vee Technologies and Salem-based Sona College of Technology are developing two apps to aid the cause of detecting COVID-19.
While ‘Corona-Scan’ proactively allows public health officials to map individuals who were in close proximity with a possibly infected or active coronavirus patient, the other complementary app ‘Corona-Support’ asks the public for voluntary registration.
If an individual tests positive, a voluntary status update can be entered in the app, helping health authorities and experts tracking the spread of the virus get accurate information.
“The third-year students of Sona College of Technology — Bernotsha, Aravind Kumar and Naveen Kumar — under guidance of Prof Akilandeswari J and Vee Technologies team have built a robust app pair ‘Corona-Scan’ and ‘Corona-Support in a matter of days’. This will go a long way to contain spread of Covid-19,” says Chocko Valliappa, CEO of Vee Technologies, who conceived the apps.
By tracking and recording people within 3-5 metres every two minutes, the ‘Corona-Scan’ app generates live data of people in proximity to one another.
By mapping people who may have been infected and risk infecting others, Public Health officials can identify and take appropriate action to connect with them over the phone and keep them under observation, isolation or recommend testing.
AI is accelerating drug development too
The real promise of AI, though, appears to be in speeding up the process of designing, testing, and even making potential new drugs.
Researchers at the US Department of Energy’s Oak Ridge National Laboratory (ORNL) said on 5 March that they used the world’s fastest supercomputer, the IBM AC922 Summit, to identify 77 small-molecule drug compounds that might warrant further study in the fight against COVID-19 disease outbreak. They published their results on ChemRxiv.
Powered by thousands of NVIDIA (Tensor Core V100) GPUs (graphics processing units) and IBM (POWER9) CPUs, the Summit can perform 200 quadrillion calculations each second–roughly a million times more powerful than the average laptop’s computing power.
“Summit was needed to rapidly get the simulation results we needed. It took us a day or two whereas it would have taken months on a normal computer,” said Jeremy C. Smith, Governor’s Chair at the University of Tennessee (UT) and director of the UT/ORNL Center for Molecular Biophysics.
A team led by Dr. Rolf Hilgenfeld at the University of Lubeck says it has decoded the 3D architecture of the main protease of SARS-CoV-2. Hilgenfeld is an expert in the field of virology and had developed an inhibitor against the SARS-virus during the 2002/2003 SARS pandemic. In 2016, he succeeded in deciphering an enzyme of the Zika virus.
The protease in this case (Mpro, or also 3CLpro) is an enzyme that catalyzes proteolysis–the breakdown of proteins into smaller polypeptides or single amino acids.
Responsible for replication of the coronavirus, it was decoded using the high-intensity X-ray light from the BESSY II facility of the Helmholtz-Zentrum Berlin. The complex shape of the protein molecule and its electron density was then calculated by AI algorithms.
The function of a protein is closely related to its 3D architecture. Hence, the analysis of the 3D architecture of the special protein will allow systematic development of drugs that can inhibit reproduction of the coronavirus.
Google-owned DeepMind Technologies, too, released the structure predictions of several proteins associated with COVID-19 on Github this month (5 March). Once we understand a protein’s shape, we can guess its role within the cell, and scientists can develop drugs that work with the protein’s unique shape.
The predictions, published in Nature, were done by DeepMind’s deep learning system AlphaFold, thus demonstrating the utility of AI for scientific discovery.
Startups are also joining in the chorus.
Early February, companies like BenevolentAI–a UK-based start-up; Deargen–a South Korean AI drug discovery specialist; and US-based Insilico Medicine pitched in with their respective AI-based solutions to tackle coronavirus.
Researchers from BenevolentAI and Imperial College London, for instance, said they have used AI to find an already-approved drug that might limit the coronavirus’s ability to infect people.
Similarly, Deargen said it used it pretrained deep learning-based drug-target interaction model called Molecule Transformer-Drug Target Interaction (MT-DTI) to identify commercially available drugs that could act on viral proteins of COVID-19. Their work is published on the bioRxiv preprint server.
Insilico Medicine, too, announced that its AI algorithms had designed six new molecules that could stop the virus from replicating in people’s bodies. These molecules have to be tested so it remains to be seen whether these compounds ever become medicines.
To be sure, while companies are putting technologies like AI to good use in healthcare by analysing mountains of data and making accurate predictions, governments and institutions need to take cognizance of these predictions and act in a timely manner. Else, even the most powerful and smartest AI won’t be able to arrest this pandemic or the ones to follow.
This article was first published on livemint
