– The end of 2020 marks the conclusion of one of the most formidable years the healthcare industry has seen in recent memory.
The COVID-19 pandemic brought new challenges with it, while also shining a harsh light on longstanding issues. Leaders acted quickly to leverage big data analytics tools, including AI and machine learning, to make sense of the virus and control its spread, resulting in a year of technological achievements and rich data resources.
In a list of the top ten stories from the past 12 months, HealthITAnalytics describes the events and trends that dominated readers’ attention. While many will be glad to see 2020 go, a look back on some of its major incidents indicates that the crisis sparked innovations that will live on long after the new year.
Soon after the Trump administration declared COVID-19 a national emergency, officials sought the help of big data analytics tools to better understand virus transmission, risk factors, origin, diagnostics, and other vital information.
The White House Office of Science and Technology Policy issued a call to action for experts to develop artificial intelligence tools that could be applied to a COVID-19 dataset – the most extensive machine-readable coronavirus literature collection available for data mining at that point.
The call to action showed leaders’ confidence in the potential of AI, and foreshadowed the critical role advanced analytics tools would play in mitigating the impact of the pandemic.
With the FDA recently granting emergency use authorizations for new COVID-19 vaccines, many people in the US are looking forward to the beginning of the end of the pandemic.
However, as this MIT study showed, these vaccines may not be the all-encompassing solutions they’re believed to be.
Researchers used an artificial intelligence tool to examine a kind of vaccine similar to COVID-19 vaccines and found that it could be less effective in people of black or Asian ancestry. The results further emphasize the stark racial and ethnic disparities that have been consistently highlighted throughout the pandemic.
As the pandemic has worn on, public health officials are continually searching for innovative tools to help allocate resources and guide decision-making. A team from Johns Hopkins School of Public Health leveraged big data analytics to develop a COVID-19 mortality risk calculator, which could inform public health policies around preventive resources, like N-95 masks.
The risk calculator could also help allocate early vaccines, acting as a companion to guidelines from other organizations and ensuring that the right people are vaccinated first.
The onset of COVID-19 sparked a new wave of data sharing and access in healthcare. In late March, Google Cloud announced that it would offer researchers free access to critical coronavirus information through its COVID-19 Public Dataset Program, which aims to accelerate analytics solutions during the global pandemic.
The program will make a hosted repository of public datasets free to access and query, including the Johns Hopkins Center for Systems Science and Engineering (JHU CSSE) dashboard, Global Health Data from the World Bank, and OpenStreetMap data.
Early in the pandemic, researchers were working to discover potential therapies for COVID-19 using AI and machine learning tools. Two graduates from the Data Science Institute at Columbia University launched a startup called EVQLV that creates algorithms capable of computationally generating, screening, and optimizing hundreds of millions of therapeutic antibodies.
Using this technology, the pair aimed to discover treatments that would likely help individuals infected by the virus that causes COVID-19. The machine learning algorithms are able to rapidly screen for therapeutic antibodies with a high probability of success.
When the virus began spreading throughout the US, it quickly became clear that some population groups were at higher risk than others. The virus has disproportionately impacted not only the elderly and people with underlying conditions, but also minority populations and individuals of lower socioeconomic status.
To get ahead of these trends, Medical Home Network leveraged artificial intelligence to identify individuals who have a heightened vulnerability to severe complications from COVID-19. The predictive analytics model has helped the Chicago-based organization prioritize care management outreach to patients most at risk from the virus.
With the surges of COVID-19 patients coming into hospitals and health systems, providers are in need of innovative tools that can help them prioritize and manage care. A team from NYU developed an artificial intelligence algorithm that could accurately predict which patients newly diagnosed with COVID-19 would go on to develop severe respiratory disease.
The study showed that characteristics thought to be hallmarks of COVID-19 – like certain patterns in lung images, fever, and strong immune responses – were not useful in predicting which patients with initial mild symptoms would go on to develop severe lung disease.
Data has been at the center of every COVID-19 research effort. The global spread of the virus, in conjunction with its complex nature, requires investigators to analyze massive amounts of information – too much for the human brain to comprehend on its own.
In an interview with HealthITAnalytics, 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), discussed the ways in which researchers and developers are using AI, machine learning, and natural language processing to understand, track, and contain coronavirus.
RPI also offered government entities, research organizations, and industry access to innovative AI tools, as well as experts in data and public health to help combat COVID-19.
The rapid spread of COVID-19 meant that hospitals had to prepare for the worst. In a system that is already strained, the potential for waves of highly contagious patients can only translate to disaster.
With big data analytics tools, organizations were able to track and monitor the use of critical resources. Definitive Healthcare, in partnership with Esri, launched an interactive data platform allowing people to analyze US hospital bed capacity, as well as potential geographic areas of risk, during the COVID-19 outbreak.
The platform shows the location and number of licensed beds, staffed beds, ICU beds, and total bed utilization in the US.
Real-time data has been a primary focus throughout the COVID-19 pandemic, as evidenced by the most-read story on HealthITAnalytics in 2020.
Months before the US had implemented quarantine and social distancing measures, the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University released a web-based dashboard tracking real-time data on confirmed COVID-19 cases, deaths, and recoveries for all affected countries.
First publicly shared on January 22, 2020, the dashboard signified the pivotal role data and technology would play in the coming months, as leaders across the industry hurried to get ahead of the virus.
While 2020 may be not be a year that many remember fondly, it certainly could ignite some much-needed change in healthcare. From increased data sharing and access, to enhanced data analytics and AI tools, the pandemic has prompted researchers and developers to design innovative ways to mitigate the impact of COVID-19.
The COVID-19 pandemic will subside, but the strategies and advancements developed during this period may endure long after the crisis ends. Big data analytics tools have featured largely in the industry’s response to coronavirus infections, and these technologies will likely continue to be an integral part of healthcare going forward.