Artificial intelligence technologies such as for example machine learning, natural-language processing, computer vision and deep learning might help track and identify the novel coronavirus.
On Dec. 31, BlueDot, a Toronto-based company that uses artificial intelligence to track the spread of infectious diseases, alerted its customers in regards to a cluster of unusual pneumonia cases in Wuhan, China. Nine days later, the World Health Organization confirmed the discovery of a novel coronavirus, later named COVID-19, in Wuhan.
Today, COVID-19 is a pandemic which has spread to 180 countries, claimed a lot more than 50,000 lives, and triggered a near-global lockdown. And for as soon as, the very best solution to support the spread of the virus is to boost personal hygiene and exercise social distancing.
For the time being, politicians, scientists, and researchers are teaming up to find systematic methods to fight the virus and look after patients. And they’re getting some much-needed help from artificial intelligence.
BlueDot runs on the mix of artificial intelligence and human expertise to track the spread of infectious diseases around the world. Its algorithms consolidate and analyze data from sources including news reports, statements from health organizations, commercial flights, and livestock health reports.
Using machine learning and natural language processing, BlueDot peruses the ocean of data to find patterns that may hint at the start of an infectious outbreak. The email address details are then reviewed by a team of experts made up of epidemiologists, doctors, veterinarians, and data scientists, who decide which of the signals need further investigation. The ultimate report is delivered to BlueDot’s customers, such as for example governments and businesses.
Furthermore to hotspots, the AI may also predict the spread of infectious and contagious diseases using flight data and movement patterns. BlueDot successfully predicted several cities where COVID-19 would first spread, after it surfaced in Wuhan.
Under normal circumstances, BlueDot provides its platform as a commercial application. But nowadays, the business is helping governments track the spread of COVID-19. Later on, AI technologies like BlueDot’s can serve as early warning systems to greatly help governments nip pandemics in the bud.
“BlueDot is humbled and grateful for the chance to mix our expertise in infectious diseases, big data analytics, and digital technologies with the efforts of the federal government of Canada to safeguard lives and mitigate the impacts of COVID-19 at home and all over the world,” said Dr. Kamran Khan, infectious disease physician and CEO of BlueDot.
“We are in uncharted territory as a microscopic virus is currently disrupting our entire planet. The COVID-19 pandemic has revealed the necessity to implement systems that proactively manage infectious disease risks which, inside our rapidly changing world, are increasing in frequency, scale and impact. In fact it is with enhanced preparedness that people can get before these threats to make a healthier, safer, and more prosperous world.”
Viral test kits are an issue, and scientists and researchers have already been looking for alternative methods to find COVID-19 infections. One possible solution may be the study of chest X-rays and CT scans, which are more easily available in hospitals and will show infections due to COVID-19.
The task in using chest imaging in diagnoses is that it’s hard to tell the difference between COVID-19 and other infections such as for example influenza. The American College of Radiology (ACR) issued a statement in March, advising against the usage of chest CT scans and X-ray as the first-line test of COVID-19. “Viral testing remains the only specific approach to diagnosis,” ACR wrote in its advisory.
The positioning can be supported by the CDC, which states, “Given the variability in chest imaging findings, chest radiograph or CT alone isn’t recommended for the diagnosis of COVID-19.”
But AI researchers are hoping that computer vision can help where human vision fails. Several companies have deployed AI systems to detect COVID-19 cases in X-ray and CT scans. One recent effort is COVID-Net, an open-source deep-learning system produced by DarwinAI and the University of Waterloo.
Alex Wong, chief scientist at DarwinAI, says there are subtle differences between COVID-19 and other infections that radiologists may not notice when examining chest X-rays. “The hope here with COVID-Net is that people can leverage AI (specifically, deep learning) to get these subtle visual indicators to raised differentiate between COVID-19 and other styles of infections, and unveil these visual indicators to clinicians to improve specificity,” he says.
Deep-learning algorithms are specially proficient at finding small details in visual data that may go unnoticed to the naked eye. COVID-Net has been trained on COVIDx, a public database that includes 16,756 chest X-Rays across 13,645 patient cases from not merely COVID-19, but other styles of lung infections aswell. The diversity of the info will enable the deep learning model to select the characteristics define each kind of illness and detect them in new X-ray images.
Wong says that as the model isn’t production-ready, preliminary email address details are very promising in differentiating between COVID-19 and other infections. The model will be improved as more data becomes available.
“We feel strongly a large-enough sample size would make a siginificant difference in improving COVID-Net and also develop new deep-learning models for detecting COVID-19 infection,” Wong says.
Nonetheless, Wong stresses that, as advised by CDC and ACR, chest X-rays and CT scans should be regarded as complementary screening tools. They could be found in facilities where test kits are an issue or not available. Additionally, there are situations where chest X-rays or CT scans should be done even in a positive diagnosis with viral tests to measure the extent of the infection for treatment and care planning.
“The hope is that the AI might help radiologists to quicker and accurately differentiate between COVID-19 infections and other styles of infections (especially important since flus are prevalent still this time around of year), and moreover, decrease the burden for radiologists but enabling other front-line health workers with less expertise to raised make diag