What a crazy year 2020 has been. From December 30th 2019, when BlueDot from Canada first issued alerts about the new coronavirus taking shape in Wuhan, the world did not expect the COVID-19 pandemic¹ to last this long. Pandemics come and go but the coronavirus has defied all odds and continues to persist as 2020 draws to a close. From wearing masks, sanitizing and temperature checks, these have been the common trends in response to the outbreak and our lives have become strained by this pandemic.

With surging infections in the United States, all indications show that the coronavirus will continue for the better part of 2021. Expectations of curve flattening have not been achieved and with more hospitalizations and the second coronavirus wave evident in Europe and some parts of Asia, this outbreak is taking a toll on everyone. Mental health problems have spiked with domestic violence rising at the same time as the world went into a lockdown.

The good news is that the world is getting closer to a vaccine for COVID-19 as companies including Pfizer announced vaccines with over 90% efficacy. The United States, UK, Germany and French governments are the latest in the world to make plans of using these vaccines as infections surge. In the United States, the government expects to start rolling out vaccines in December this month and January 2021. The Food and Drug Administration will play a critical role in the implementation of vaccines to the public as the approval remains pending.

A special vote of thanks to all medical workers in the United States and around the world who have been in the frontline and continue to give care and save lives. Medical workers have risked their lives and unfortunately, some lost their lives in the process of saving others. The collaboration between medical workers and artificial intelligence² is the key moment of 2020 that the world should look back with appreciation. That is why I’m nominating medical workers and AI as the Time Persons of the Year.

Machine learning enables #artificialintelligence and works by taking large amounts of data and learns to detect patterns in the data³. This enables it to predict future outcomes as well as reveal other insights about the data. By using large amounts of data, a high confidence level can be assigned to these predictions. Medical workers use these patterns to make decisions including mapping infection rates, detecting infected patients and predicting those at risk and require extreme measures such as oxygen for treatment.

AI-Powered Contact Tracing

Contact-tracing apps are already in widespread use in Asia and they are also now being used in other parts of the world such as India, Italy, and Israel. They vary in the way they work but generally use the fact that smartphone users whereabouts are detectable and therefore, can detect close contact with other users.

AI #algorithms can then determine the risk of cross infection and then alert users of such risks. For example, an app is being trialled for use by the British government that works by using the Bluetooth protocol to identify other smartphone owners who are in close proximity to each other. Thus, a person who is not infected but in close proximity to someone that has COVID-19 symptoms, could receive an alert.

Contact-tracing smartphone apps, described later, were rolled out in Wuhan, China, very quickly after the city was quarantined to contain the virus. AI has been combined with other technologies to track and flag possible carriers of the virus. They also adopted AI for detecting people with fever in large crowds by the use of AI-powered smart glasses. Worn by security guards, they can check hundreds of people within a few minutes without making contact.

A variation of this type of surveillance technology were used in bus and train stations as well as other public places in China where there is a high concentration of people. They did it by combining AI with new temperature measurement technology using #computervision⁶. This technology made it possible to take body temperature, a key symptom of COVID-19, in a contactless way without affecting people’s normal behavior.

With this technology in place, those whose body temperatures exceeded the threshold could quickly be located. This proved to be an effective method because manual temperature measurement is time-consuming, and would increase the risk of cross-infection because of the necessary contact with others.

Analysis of Coronavirus Infections

Coronaviruses invade cells through spike proteins but they take on different shapes in different coronaviruses. Understanding the shape of the spike protein in SARS-Cov-2⁷ that causes coronavirus is crucial to figuring out how to target the virus and develop therapies. Dozens of research papers related to spike proteins are in the CORD-19 Explorer to better help people understand existing research efforts.

The University of Washington’s Institute for Protein Design mapped out 3D atomic-scale models of the SARS-CoV-2 spike protein that mirror those first discovered in a University of Texas Austin lab. The team is now working to create new proteins to neutralize the coronavirus. These proteins would have to bind to the spike protein to prevent healthy cells from being infected.

Apart from vaccines, several scientists and pharmaceutical companies are collaborating to develop therapies to combat the virus. Some treatments include using antiviral remdesivir, developed by Gilead Sciences, and the anti-malaria drug hydroxychloroquine.

AI-enabled Collaboration of Medical Research

One of the best things artificial intelligence can do now is help researchers scour through the data to find potential treatments. The COVID-19 Open Research Dataset, an initiative building on Seattle’s Allen Institute for Artificial Intelligence (AI2) Semantic Scholar project, uses natural language processing to analyze tens of thousands of scientific research papers at an unprecedented pace.

Semantic Scholar, the team behind the CORD-19 dataset at AI2, was created on the hypothesis that cures for many ills live buried in scientific literature. Literature-based discovery has tremendous potential to inform vaccine and treatment development, which is a critical next step in the COVID-19 pandemic.

The White House announced the initiative along with a coalition that includes the Chan Zuckerberg Initiative, Georgetown University’s Center for Security and Emerging Technology, Microsoft Research, the National Library of Medicine, and Kaggle, the #machinelearning and data science community owned by Google.

Chest Screening and X-ray Scanning by AI

Detecting COVID-19 in most health systems currently involves testing symptomatic patients presenting to stand-alone fever clinics, general practices or emergency departments. This takes time, consumes personal protective equipment and testing reagents, and poses transmission risk to staff. Digital symptom checkers soliciting information about symptoms and risk factors may screen out persons with very low likelihood of COVID-19 who do not require testing.

Health authorities are keen to increase the numbers being tested but the main testing methods are labor-intensive and time-consuming. But AI is now assisting with other forms of testing, such as x-ray scanning. Various AI programs are now available for chest screening that can highlight lung abnormalities in a chest X-ray scan and provide a COVID-19 risk evaluation much faster than human radiologists.

AI Technology-enabling Social Distancing

Arange of AI-based robots have emerged during recent months that help in the COVID-19 battle by reducing contact between patients and health care workers — minimizing the risk of cross-infections.

Chinese firms are using drones and #robots to perform contactless delivery and to spray disinfectants in public areas to minimize the risk of cross-infection. Other robots are checking people for fever and other COVID-19 symptoms and dispensing hand sanitizer foam and gel. Robots⁸ are also being used to serve food and medicine to patients and disinfecting rooms to minimize contact with human staff.

Robot dogs are helping doctors assess patients in US hospitals. A company called Boston Dynamics have produced a robot dog, known as Spot. This robot is being used to reduce the contact health workers must have with potentially contagious patients.

People can order groceries through Alexa without stepping foot inside a store. Robots are replacing clinicians in hospitals, helping disinfect rooms, provide telehealth services, and process and analyze COVID-19 test samples.

Uniting to Defeat the Pandemic

Akey lesson learned in 2020 with respect to COVID-19 is that this pandemic unlike other outbreaks persists and this requires collaboration across the board. The public should heed all government measures such as social distancing and wearing masks as these support efforts in combating the virus. At the same time, medical workers need support at this time as the pandemic continues to rage in the U.S and other parts of the world.

While AI and ML can support #COVID19 responses across various domains, most applications have not reached operational maturity. The speed of research means many reports are pre-prints awaiting peer review, although still attracting media coverage and clinician adoption prior to proper evaluation.

Sharing data about the virus in an ethical way is another way the public can offer medical workers support as they battle this virus. With the vaccine news creating a sigh of relief, there is optimism about containing this pandemic. In the meantime, more needs to be done. To continue saving lives. That is why I’m recognizing the efforts of medical workers and artificial intelligence in battling this pandemic.

Works Cited

¹COVID-19 Pandemic, ²Artificial Intelligence, ³Data, ⁴AI Algorithms, ⁵AI-Powered Smart Glasses, ⁶Computer Vision, ⁷SARS-Cov-2, ⁸Robots