Data Science and Healthcare During the Covid-19 Pandemic

By: Sarah Thompson

            Covid-19 has altered our world immensely – casting a net of uncertainty that holds us in a state of eerie permanence. Cradled in captivity, many of us are waiting for the world to return to normal, occupying ourselves in the meantime by organizing our closets or sewing N95 masks for local hospitals. Covid-19’s rapid spread has put a strain on hospitals, drug companies, and resources, causing an onslaught of issues along with lags in care for those critically ill. All the while, healthcare professionals and public policy experts are working overtime to lay out a tangible escape plan.

            As a soon to be data scientist, I was intrigued when my father, the Chairman of the Department of Psychiatry at Tulane University and the Chief of Staff at one of Louisiana’s state hospitals, texted me: “data scientists are saving the world right now, Sarah.” To be clear, I am the sole data enthusiast in a family with a strong medical predilection. From my point of view, healthcare professionals like my family members were saving the world right now, not the data people. His text prompted me to explore how data scientists were also on the front-lines—not from a health perspective, but from the technology perspective. As usual, my dad was not wrong.

            By leveraging data science, hospitals and healthcare professionals are automating time intensive tasks to meet the increased demands for patient care. In addition, researchers and data scientists are working together with a global community to scan chemical compounds for a cure to the virus. Chat bots, AI x-ray scans, and crowd-sourcing computing power are just some examples of how AI is being tailored to address the Covid crisis, freeing up medical professionals and researchers to attend to the most pressing cases.

Chat Bots

            As Covid-19 – and the fear of getting the illness – spread, hospitals and virus-specific hotlines experienced surges in the number of calls and questions they were receiving about the illness and related symptoms. According to a press release from IBM, wait times for calls to be answered could often exceed two hours, causing many people to hang up before receiving the answers they sought (IBM News Room 2 Apr. 2020). The human system was not working fast enough to provide the answers to those experiencing mild symptoms and the care to those seriously ill.

            In response, utilizing Natural Language Processing and AI, IBM leveraged their Watson Assistant for Citizens technology to create a chat bot that answers common Covid-19 questions. The chat bots use the Watson Discovery search functionality to take in information from the Center for Disease Control (CDC) as well as local sources, providing insight on school closures and important local government information. Not only can they disseminate valuable information; they also enable staff to help with other urgent tasks. For example, the University of Arkansas for Medical Sciences in collaboration with IBM deployed a chat bot agent that has reduced registration time of patients by fifty percent, freeing up staff and speeding up the triage process. Providence Hospitals also created a similar chat bot system in collaboration with Microsoft. Launched in the beginning of March at St. Joseph health system in Seattle, this chat bot served 40,000 people in the first week according the Harvard Business Review (Wittbold 2020).

AI X-Ray Scans

            At Zhongnan Hospital of Wuhan University in Wuhan China, the staff in the radiology department altered an AI algorithm used for determining cancer from chest x-rays into one capable of identifying pneumonia, an illness which is related to Covid-19. The head of the radiology department, Haibo Xu emailed Wired magazine about his successful implementation of the altered AI algorithm saying, “the software helps overworked staff screen patients and prioritize those most likely to have Covid-19 for further examination and testing” (Simonite  2020). While detecting pneumonia is not perfectly correlated with Covid-19, it does allow the staff at Zhongnan to isolate those suspected of having contracted the virus, reducing the spread and prioritizing the needs of healthcare workers.

            When Infervision, the creator of the aforementioned cancer-detecting AI system, realized the potential use for Covid-19, the company worked through the Chinese Lunar New Year to retrain the algorithm with Covid-19 x-rays. The algorithm was trained on 2,000 images and is being used in 34 hospitals around China, having scanned over 32,000 chest x-rays so far. However, there was no mention of the accuracy of the AI system, which can be worrisome. Algorithms with a high false negative rate could lead doctors to missing critical patients that need to be seen. Alternatively, a high false positive rate would result in patients with less critical needs receiving more hands-on care, which does not serve those who need it most.

            In the US and Canada, the skepticism about the accuracy of these AI x-ray scans prompted data scientists to use crowd-sourcing in an attempt to improve the current algorithms. Covid-NET was created to detect Covid-19 cases in chest x-ray scans. Designed by Linda Wang and Alexander Wong at the University of Waterloo, it relies on a convolution neural network structur. Convolutional neural networks are known for their ability to detect patterns in images. The algorithm, along with 5941 chest images, were made available through the Covid-NET platform on March 24th. This collection of images includes chest x-rays from individuals with Covid-19, as well as healthy individuals, those with other lung conditions, and/or those with other bacterial infections. The design architecture and images were shared so that other data scientists can tweak the structure and hopefully improve the algorithm. MIT Technology Review warns that until the accuracy has been confirmed, the information should not be used (Heaven 2020).

Borrowing Compute Time

            Finding a cure for Covid-19 involves scanning the troves of known chemical compounds to identify any that may be suitable to treat the quickly-spreading disease. In the past, scanning this amount of data would have taken lifetimes, but thanks to modern technology, it is possible to amass the processing power capable of making the necessary computations.

            To do this, organizations like IBM’s World Community Grid are asking lay people to lend their computer’s idle time to science (IBM News Room 1 Apr. 2020). Those wanting to get involved only need to download the app on a computer connected to the internet and go about their day. The app waits until the computer is either idle or being lightly used and then begins creating simulations and scans on known chemical compounds. All findings are sent to Scripps Research, a non-profit biomedical research facility spearheading the initiative with the help of IBM (Palmer 2020). Initiatives like this one have been used in many other studies including those for cancer, Ebola, and AIDS. All data amassed by the World Community Grid is made available to the public and according to an IBM press release, “more than 770,000 people and 450 organizations have contributed nearly two million years of computing power to support 30 research projects” using World Community Grid.

            Folding@home, an initiative created at Standford University, is also borrowing compute time from citizens to scan potential chemicals for a Covid-19 cure. Historically, Folding@home has been used to map disease proteins connected to Alzheimer’s and cancer which it has been doing for the past twenty years, according to an article in NS Tech (Clarke 2020). Towards the end of February, Folding@home pivoted to performing similar simulations for Covid-19, prompting an influx of users. 

            As of March 31st, 600,000 citizens were donating idle compute time to the scientific research. NS Tech reports, “The network is now operating at an ‘exaflop’ of computing power: 1,000,000,000,000,000,000 (a billion billion) operations per second.” For reference, this network is generating roughly three times more computing power than the world’s leading supercomputers. In order to accommodate the distributed computing style of the network, large calculations can be broken up into small ones that run on thousands of computers at once. By breaking up the large computations and drawing on citizen’s computing power, researchers are able to generate insights into Covid-19 at a scale that has never been seen before.

These three examples – using chat bots to share information and answer questions, redesigning artificial intelligence algorithms to read chest x-rays, and using distributed computing to amass computing power to perform data-intensive computations – only begin to scratch the surface of the countless applications of data science unleashed in the current global pandemic. Due to their ability to scale up in ways that human beings cannot, these AI systems can facilitate in managing otherwise overwhelming situations. As a result, healthcare providers can either take a much-needed break or turn their attention to critical patients. Additionally, rather than having to develop new systems, altering the current systems provides faster insight, informing scientists and helping medical professionals develop solutions to free us from the pandemic. The synergy of data science and healthcare has created unprecedented advances in AI, enabling both data scientists and healthcare professionals to collaborate in saving the word.

Works Cited:

“Announcements.” IBM News Room, 1 Apr. 2020,       Can-Help-Scientists-Seeking-Potential-COVID-19-Treatments.

“Announcements.” IBM News Room, 2 Apr. 2020,            Watson-Assistant-for-Citizens-to-Provide-Responses-to-COVID-19-Questions.

Clarke, Laurie. “How a Supercomputer Network of 700,000 PCs Is Helping to Find a Covid-19 Cure.”    NS Tech, 6 Apr. 2020,    covid-19-cure.

Heaven, Will Douglas. “A Neural Network Can Help Spot Covid-19 in Chest x-Rays.” MIT         Technology Review, MIT Technology Review, 24 Mar. 2020,    chest-x-ray-pneumonia/.

Palmer, Danny. “Coronavirus: How Your PC’s Spare Computing Power Could Help Discover Potential             COVID-19 Treatments.” ZDNet, ZDNet, 1 Apr. 2020,   your-pcs-spare-computing-power-could-help-discover-potential-covid-19-treatments/.

Simonite, Tom. “Chinese Hospitals Deploy AI to Help Diagnose Covid-19.” Wired, Conde Nast, 26        Feb. 2020,

Wittbold, Kelley A., et al. “How Hospitals Are Using AI to Battle Covid-19.” Harvard Business   Review, 3 Apr. 2020,