This year, there have been many milestones in the healthcare industry including the authorization of two COVID-19 vaccines. To arrive at these vaccines in record time, researchers used the power of data paired with machine learning (ML) techniques. With the help of ML, scientists were able to sift through COVID-19 research quickly to develop and deliver vaccines.
“Data is, undoubtedly, a critical component as we navigate today’s public health crisis,” explained Heather Gittings, Principal Strategic Advisor, Global Public Sector and Healthcare, Qlik. “But it’s not just data that’s needed. What’s also needed is the ability to sift through this data to reveal insights that lead to breakthroughs like the COVID-19 vaccines by Moderna and Pfizer-BioNTech.”
At the start of the COVID-19 pandemic, the medical community began compiling key information for the COVID-19 Open Research Dataset (CORD-19). And, according to Nabeel Asif, Principal Solution Architect, Qlik, “my goal was to give researchers the ability to find COVID-19 related articles then apply ML techniques within the chosen context.”
Asif used two ML techniques — named entity recognition and clustering — to provide the context to the data. “The first technique is used to extract biomedical entities from the title and abstract of each article using a pre-trained deep learning model. This becomes a rich new dimension for search and exploration,” explained Asif. “While this is done during the reload process, the clustering algorithm is used in real-time for interactive analysis. As a user drills down by making selections, an algorithm groups research articles into clusters based on the similarity of entities appearing in titles and abstracts. In short, the solution results in [greater] human intelligence and ability.” And while the insights extracted led to the successful vaccine development what was needed was an end-to-end data analytics solution to do the work.
“The value of data in the fight against COVID-19 cannot be overstated,” explained Julie Kae, Executive Director of Qlik.org.“The ability to bring unstructured data and research information into [a] solution and combine it with data sets from the WHO, CDC, Johns Hopkins, and others will accelerate our society’s ability to leverage knowledge and resources to stop the pandemic.”
This year has been a momentous one for healthcare. While providers battled COVID on the frontlines of patient care, researchers were putting data to work to develop a safe and effective vaccine in record time. Being able to aggregate and analyze vast amounts of data quickly, using machine learning, enabled researchers to identify important patterns in both the virus and the manifestation of disease from a variety of sources were the keys to this historic effort. As data management and application tools become more accessible in the coming months and years this pace of development will surely become the norm, leading to many more breakthroughs in understanding and treating diseases.
Ready to learn more? Click here.