Using AI and Data Science to Fight COVID-19
By Sarah Dimock
It might not be the first technology you think of when you wonder what cutting edge tech is being deployed to help us during the pandemic, but big data analysis is right there on the front lines. Artificial intelligence is currently being used in combination with predictive analytics and data science to combat the coronavirus.
Data science is a newer branch of analysis, where analysts use predictive modeling to help determine the answers to future problems. While it can’t quite substitute for a crystal ball, data science is one of our most effective tools at coming up with solutions to problems before they turn into a crisis.
Scientists are currently applying their powers of predictive problem solving to questions we need to be on top of during the spread of COVID-19. Anything from monitoring the availability of hospital resources to tracking the spread of inaccurate information on social media is a data science problem. One company, Black Swan Data is even attempting, in one of their several COVID related projects, to create a search engine for medical professionals on all of the facts we currently know to be true about the virus.
Data on almost everything to do with the virus is valid, even information from social media. Victoria Collins writing for Forbes noted of Black Swan Data, “They are investigating whether public social data can generate insight on diagnosis, treatment, prognosis and the effectiveness of PPE (Personal Protective Equipment). The lack of taste and smell has been one such symptom which has gained as much traction through social conversations as clinical evidence.”
While much of the information being tracked is promising in terms of helping us make smarter decisions, there’s also a ton of data coming in right now as the virus unfolds in real time. That’s where artificial intelligence comes in, helping scientists weed out unnecessary information to get to the data they need. “There are six areas where AI can contribute to the fight against COVID-19,” says Wim Naude’ writing for Towards Data Science. “i) early warnings and alerts, ii) tracking and prediction, iii) data dashboards, iv) diagnosis and prognosis, v) treatments, and cures, and vi) social control.”
James Hendler, the Tetherless World Professor of Computer, Web, and Cognitive Science at Rensselaer Polytechnic Institute (RPI) and director of the Rensselaer Institute for Data Exploration and Applications (IDEA), delved into numbers four and five on this list in an interview with HealthITAnalytics. “One component is biomedical research,” he says. “A lot of work is going on to try to develop a vaccine or to find out whether there are any current drugs that work against COVID-19. All of those projects require molecular modeling, and many of them are using AI and machine learning to map things we know about the virus to things in pharmacological databases and genomic databases.”
Data science and AI research on the coronavirus are aiding scientists right now, but we may see the real impact of this work in the event of another pandemic or relapse of COVID-19. The information being gathered now isn’t just about right now, but is vital for our future response.