Employing tech to tackle COVID-19
*New mathematical model uses information theory to improve epidemiological predictions
*App-based contact tracing may significantly reduce the pandemic spread in many countries
*Wearing surgical masks in public helps slow spread diseases including coronaviruses
*Pandemic drone designed to monitor people with infections could limit fatality in hotspots
*Experimental Artificial Intelligence tool predicts which patients develop respiratory disease
Scientists have made breakthroughs in using technology to tackle the novel coronavirus (COVID-19).
New research has shone further light on the different rates of transmission of Severe Acute Respiratory Syndrome (SARS)-Coronavirus type 2 (CoV-2) also called COVID-19, suggesting app-based contact tracing may significantly reduce the spread of the virus.
A study published in the journal Science suggests that a significant amount of the transmission of the SARS-CoV-2 virus may be from people who are pre-symptomatic.
As a consequence, the authors suggest that a mobile app-based contact tracing system would radically reduce the amount of time it takes to identify people who have come into contact with the person who has developed the disease COVID-19.
This could significantly reduce the overall rate of spread of the virus, paving the way for what the authors call “intelligent social distancing,” rather than national lockdown.
The scientific evidence that is informing government policy in the United Kingdom, and other countries around the world, currently recommends a policy of suppressing the SARS-CoV-2 virus rather than mitigating it. By this, the evidence suggests reducing its spread, as far as possible, primarily through significant and extensive social distancing.
The research suggests that this will significantly reduce the number of people who die as a consequence of the virus transmission, as well as reduce the pressure on public health services — particularly critical care units — that have been left underfunded following 12 years of austerity measures since the 2007–2008 financial crisis.
A suppression strategy requires widespread social distancing until scientists can produce an effective vaccine. While this approach has reduced the overall level of mortality, it is also likely to have a range of negative social, economic, and ethical effects.
The research in the new study helps in this regard by identifying the relative rates of transmission of the virus. The authors use this information to propose a mobile app-based tracing system that could play a significant part in reducing the spread of the virus and enabling people to spend as little time social distancing as possible.
After analyzing data on the different ways the virus has spread in China and Singapore, the researchers estimate that almost half of the transmissions of the virus are by people who have yet to show symptoms of COVID-19.
This means that once these people develop symptoms, rapidly tracing other people they have come in contact with could play a large part in reducing the spread of the virus.
The challenge, however, is that current approaches to contact tracing take a relatively long time, and the longer contact tracing takes, the more time the virus will have to spread to other hosts.
By using a mobile app-based contact tracing method, the authors predict that the authorities could radically reduce the contact tracing time.
Also, as the world grapples with the COVID-19 pandemic, a new mathematical model could offer insights on how to improve future epidemic predictions based on how information mutates, as it is transmitted from person to person and group-to-group.
The United States (U.S.) Army-funded this model, developed by researchers at Carnegie Mellon University and Princeton University, through the Army Research Laboratory’s Army Research Office, both elements of the Combat Capabilities Development Command.
The model suggests that ideas and information spread and evolve between individuals with patterns similar to genes in that they self-replicate mutate and respond to selective pressure as they interact with their host.
In their study, published March 17 in the Proceedings of the National Academy of Sciences, the researchers developed a mathematical model that takes the evolutionary changes of both disease and information into consideration. The researchers tested the model against thousands of computer-simulated epidemics using data from two real-world networks: a contact network among students, teachers, and staff at a U.S. high school, and a contact network among staff and patients in a hospital in Lyon, France.
The researchers said the epidemic model most widely used today is not designed to account for changes in the disease being tracked. This inability to account for changes in the disease can make it more difficult for leaders to counter a disease’s spread or make effective public health decisions such as when to institute stay at home orders or dispatch additional resources to an area.
While the study is not a silver bullet for predicting the spread of today’s coronavirus or the spread of misinformation, the authors say it is a big step.
In the future, the team hopes that their research can be used to improve the tracking of epidemics and pandemics by accounting for mutations in diseases and ultimately considering interventions like quarantines and then predicting how those interventions would affect an epidemic’s spread when the pathogen is mutating as it spreads.
Also, surgical masks may help prevent infected people from making others sick with seasonal viruses, including coronaviruses, according to new research that could help settle a fierce debate spanning clinical and cultural norms.
In laboratory experiments, the masks significantly reduced the amounts of various airborne viruses coming from infected patients, measured using the breath-capturing “Gesundheit II machine” developed by Dr. Don Milton, a professor of applied environmental health and a senior author of the study published
Milton has already conferred with federal and White House health officials on the findings, which closely follow statements this week from the head of the Centers for Disease Control and Prevention saying the agency was reconsidering oft-stated advice that surgical masks aren’t a useful precaution outside of medical settings. (The debate takes place at a time when clinicians themselves face dangerously inadequate supplies of masks — a shortfall other UMD researchers are scrambling to help solve.)
The question of masks has roiled society as well, with some retailers refusing to let employees wear them for fear of sending negative signals to customers, and cases of slurs and even physical attacks in the United States and elsewhere against Asians or Asian Americans who were wearing masks, a measure some consider a necessity during a disease outbreak.
The study, conducted prior to the current pandemic with a student of Milton’s colleagues on the Faculty of Medicine at the University of Hong Kong, does not address the question of whether surgical masks protect wearers from infection. It does suggest that masks may limit how much the infected — who in the case of the novel coronavirus often don’t have symptoms — spread diseases including influenza, rhinoviruses and coronaviruses.
Milton, who runs the Public Health Aerobiology, Virology, and Exhaled Biomarker Laboratory in the School of Public Health, demonstrated in a 2013 study that surgical masks could help limit flu transmission. However, he cautions that the effect may not be as great outside of controlled settings.
Nevertheless, he said, the chance they could help justifies taking a new look at whether all people should be encouraged to wear them when they venture out of their houses to stores or other populated locations during the current COVID-19 lockdown.
Previous studies have shown that coronavirus and other respiratory infections are mostly spread during close contact, which has been interpreted by some infectious disease specialists to mean that the disease could spread only through contact and large droplets, such as from a cough or sneeze — a message that has often been shared with the public.
Also, experts are set to unleash a ‘pandemic drone’ to help limit the spread of coronavirus. The drone is fitted with sensors and computer vision, allowing it to monitor and detect people with infectious respiratory conditions.
The system could also identify people sneezing and coughing in crowds, offices, airports, cruise ships, aged care homes and other places where groups of people may work or congregate.
Its creators hope to deploy the drone in six months and in various hotspots where ‘the most amount of detection is currently required.’
The pandemic drone is being developed in collaboration with the University of South Australia (UniSA) and drone maker Draganfly.
The unmanned aerial vehicle (UAV) has sensors and computer vision technology that can monitor temperature, heart and respiratory rates of people in a crowd, along with spotting those coughing and sneezing.
Researchers involved say the drone demonstrated that heart rate and breathing rate could be measured with high accuracy within 16 to 32 feet of people, using drones and at distances of up to 165 feet with fixed cameras.
And it uses special algorithms to spot someone sneezing and coughing.
The UniSA team led by Defence Chair of Sensor Systems Professor Javaan Chahl believes the UAV could be a viable screening tool for the COVID-19 pandemic.
“It might not detect all cases, but it could be a reliable tool to detect the presence of the disease in a place or in a group of people.”
Chahl said the technology was originally envisaged for war zones and natural disasters as well as remotely monitoring heart rates of premature babies in incubators.
“Now, shockingly, we see a need for its use immediately, to help save lives in the biggest health catastrophe the world has experienced in the past 100 years.”
Also, a new study found an artificial intelligence (AI) tool accurately predicted which patients newly infected with the COVID-19 virus would go on to develop severe respiratory disease.
NYU Grossman School of Medicine and the Courant Institute of Mathematical Sciences at New York University led the work, in partnership with Wenzhou Central Hospital and Cangnan People’s Hospital, both in Wenzhou, China.
Named “SARS-CoV-2,” the new virus causes the disease called “coronavirus disease 2019” or “COVID-19.” As of March 30, the virus had infected 735,560 patients worldwide. According to the World Health Organization, the illness has caused more than 34,830 deaths to date, more often among older patients with underlying health conditions. The New York State Department of Health has reported more than 33,700 cases to date in New York City.
Published online March 30 in the journal Computers, Materials & Continua, the study also revealed the best indicators of future severity and found that they were not as expected.
For the study, demographic, laboratory, and radiological findings were collected from 53 patients as each tested positive in January 2020 for the SARS-CoV2 virus at the two Chinese hospitals. Symptoms were typically mild, to begin with, including cough, fever, and stomach upset. In a minority of patients, however, severe symptoms developed with a week, including pneumonia.
The goal of the new study was to determine whether AI techniques could help to accurately predict which patients with the virus would go on to develop Acute Respiratory Distress Syndrome or ARDS, the fluid build-up in the lungs that can be fatal in the elderly.
For the new study, the researchers designed computer models that make decisions based on the data fed into them, with programs getting “smarter” the more data they consider. Specifically, the current study used decision trees that track a series of decisions between options, and that model the potential consequences of choices at each step in a pathway.
The researchers were surprised to find that characteristics considered to be hallmarks of COVID-19, like certain patterns seen in lung images (example ground-glass opacities), fever, and strong immune responses, were not useful in predicting which of the many patients with initial, mild symptoms would go to develop severe lung disease. Neither was age and gender helpful in predicting serious disease, although past studies had found men over 60 to be at higher risk.
Instead, the new AI tool found that changes in three features — levels of the liver enzyme alanine aminotransferase (ALT), reported myalgia, and hemoglobin levels — were most accurately predictive of subsequent, severe disease. Together with other factors, the team reported being able to predict the risk of ARDS with up to 80 percent accuracy.
ALT levels — which rise dramatically as diseases like hepatitis damage the liver — were only a bit higher in patients with COVID-19, researchers say, but still featured prominently in the prediction of severity. In addition, deep muscle aches (myalgia) were also more commonplace, and have been linked by past research to higher general inflammation in the body.
Lastly, higher levels of haemoglobin, the iron-containing protein that enables blood cells to carry oxygen to bodily tissues, were also linked to later respiratory distress. Could this explain by other factors, like unreported smoking of tobacco, which has long been linked to increased haemoglobin levels? Of the 33 patients at Wenzhou Central Hospital interviewed on smoking status, the two who reported having smoked, also reported that they had quit.