That said, 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.
Having enforced traditional measures in place, for instance, 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 16ft 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.
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. Health tech startups focused on the India market, too, are innovating and gearing up to diagnose patients, in a bid to ease the load on the healthcare system, according to Jayanth Kolla, founder and partner, Convergence Catalyst, a deep tech research and advisory firm.
He cited the example of Bengaluru-based startup, OneBreath, that has developed affordable, portable ventilators. These are aimed at the rural population in India which lacks adequate access to hospitals and doctors. Another Bengaluru-based startup DayToday has just developed a care management solution to keep diagnosed patients engaged at home, in quarantine facilities and hospitals and also cater to post-diagnosis activities such as health checks, diets, follow-up tests, etc.
“This solution reduces the load on the healthcare systems significantly, and keeps healthcare workers from the danger of contracting the infection. On average, 22% of healthcare workers tending to Covid-19 patients contract the infection and, as days pass by, the ratio of patients to doctors and nurses increases exponentially. Such solutions mitigate these issues," Kolla explained.
He believes there is significant potential and need for health tech companies to develop data analytics and profiling-based early disease detection solutions to help reduce the load on doctors and hospitals. Besides, Kolla concludes that there is a strong need in India to “take testing and diagnostics to consumers, and scale up the development of home kits".
Robots and 3D printers
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 2,000 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 coronavirus 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," said Claus Risager, CEO of 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 Wuhan 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 one of the world’s worst outbreak of coronavirus outside of China. 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, 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.
Then, 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 analyse 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," said 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 last Wednesday in the Association for Computing Machinery.
Al Hossain cites FluSense as an example of the power of combining AI with edge computing—a trend that enables data to be gathered and analysed right at the data’s source. The next step is to test FluSense in other public areas and geographic locations.
The app ecosystem
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," said 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 go 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 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 said 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 2002-03 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 catalyses 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.
The role of startups
Startups are also joining in the chorus. Early February, companies like BenevolentAI (a UK-based startup) and Deargen (a South Korean AI drug discovery specialist) 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 pre-trained 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.
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.
Leslie D’Monte is a consultant who writes on the intersection of science and technology.