Blog: COVID-19 and Artificial Intelligence

Misti Paul, April 2020

As COVID-19 continues to spread all over the world, threatening to bring healthcare systems to their knees, there are now over 1.2 million cases reported worldwide and sadly over 70,000 deaths. At Research Partnership, we wanted to take a look at how organisations worldwide are employing AI to try and combat the Coronavirus:

COVID19 AI
COVID19 AI

As COVID-19 continues to spread all over the world, threatening to bring healthcare systems to their knees, there are now over 1.2 million cases reported worldwide and sadly over 70,000 deaths. At Research Partnership, we wanted to take a look at how organisations worldwide are employing AI to try and combat the Coronavirus:

Baidu’s AI Team Open Sources LinearFold: The AI team at Baidu has released a tool, LinearFold, which reduces 2019-nCoV prediction time from 55 minutes to 27 seconds. This reduction in prediction time is crucial for understanding the virus and accelerate drug discovery.

BlueDot Surveillance: A Toronto-based health surveillance company, BlueDot, is working towards making predictions on the spread of COVID-19 by gathering disease data from myriad online sources. Earlier last month they used airline flight information to make predictions about where infectious diseases may appear next, since air travel is a common vector in communicable diseases.

AliBaba’s AI system: Alibaba’s Jack Ma claimed that its new AI system can detect coronavirus in CT scans of patients’ chests with 96% accuracy against viral pneumonia cases. In March, Alibaba sent their first consignment of 500,000 testing kits and 1 million masks to the US and consignments of supplies to Europe. According to Alibaba, their new algorithm cuts down the whole process of recognition to a record 20 seconds.

Machine Learning and AI scouring scientific research: Almost 2,000 papers have been published on Coronavirus since the pandemic emerged. AI is being used to mine through the huge repository of research that could help medical and public health experts. By cross-referencing and searching for patterns, AI may help discover new possible health patterns or factors that may make the virus worse for some patients. The National Library of Medicine, The Allen Institute of AI, and Microsoft Research have prepared over 29,000 papers related to the new virus and the wider Coronavirus family. Thirteen thousand of them have been processed so computers can read the underlying data, plus information about the authors and their affiliations to find more subtle connections that may accelerate insights into the pandemic. Several governments, including the US have called for scientific publishers to open up research on coronavirus, and a number of the larger players in publishing have said they will offer free access to their papers.

Kaggle- Data Science competition platform: Kaggle, a platform for running data science competitions, is now creating challenges with 10 primary questions related to COVID-19 and the broader family of Coronavirus. These questions are based around risk co-morbidities and risk factors, treatments that do not involve drugs, efforts to develop vaccines and the genetic properties of the virus. This project involves the Center for Security and Emerging Technology at Georgetown University and the Chan Zuckerberg Initiative.

China’s InferVISION for scanning patients: Scientists and Engineering teams at Infervision have launched the Coronavirus AI solution, which specifically reduces the time for CT diagnosis. CT scans can take up to a few hours but with Infervision’s AI system this has been cut down to a large extent, identifying and screening out suspected Coronavirus infected patients for immediate isolation and treatment. The software relies heavily on NVIDIA’s Clara SDKs, which is NVIDIA’s AI healthcare application framework for AI-powered Medical Imaging. InferVISION can identify typical signs or partial signs of COVID-19 in suspected patients. In order to do this, the software looks out for signs of pneumonia that can be caused by the virus.

BenevolentAI’s Potential Drug Discovery: Another illustration is BenevolentAI’s algorithm that connects molecular structure data to biomedical information about relevant receptors and diseases to find potential drug targets. Their software pointed to the enzyme adaptor-associated protein kinase 1 (AAK1) as a possible target for the disease. AAK1 regulates endocytosis, the process that brings material into cells, which also is a common mode of viral infection. The researchers, with the help of BenevolentAI’s software, have identified a possible drug called ‘Baricitinib’, a JAK inhibitor usually used for the treatment of Rheumatoid Arthritis. Scientists are now testing the use of Baricitinib for the treatment of COVID-19.

UVD Robots: UVD Robots, based in Denmark, are leveraging their robots to disinfect patient rooms with zero human interference. The nature of the pandemic and the highly contagious COVID-19 pose a serious threat to medical personnel who are at severe risk of catching the disease. UVD’s roving robotic pods emit ultraviolet light over the region to be disinfected and destroy any kind of virus.

Facial Recognition from SenseTime: Facial recognition is a much safer alternative than fingerprinting for obvious reasons, as it mitigates the chances of disease being spread through human-to-surface contact. So SenseTime is applying AI to scan the faces of the people with masks. They are promoting contactless identification of the infected with their temperature detection software that’s been deployed at underground stations, schools and other community places in Beijing, Shanghai and Shenzhen.

Drag the Drones In: In order to reinforce contactless monitoring of the outbreak, Chinese firms are using drones. Pudu Technology from Shenzhen has reportedly installed its machines in more than 40 hospitals around the country to aid medical staff. MicroMultiCopter, another company based out of Shenzhen, is deploying drones to transport medical samples and conduct thermal imaging.

Deepmind using AlphaFold: DeepMind have announced that they are releasing structure predictions of several proteins that can promote research into the ongoing research around COVID-19. They have used the latest version of AlphaFold system to find these structures.

We hope that all these initiatives and several more ongoing AI research and solutions can soon impede the rapid and exponential growth and spread of COVID-19 in several countries and also help better treat those affected by the disease.

Sign up to receive Rapport

Rapport is our e-newsletter and online resource for sharing our expertise and experience in global healthcare market research.

Sign up here