High tech vs. coronavirus: Using artificial intelligence, analytics are weapons SAS brings to the fight

CARY – The ongoing spread of the coronavirus is sparking urgent searches for a vaccine to counteract it. Several Triangle firms such as Lenovo and Heat Biologics have joined the fight. Also bringing powerful and emerging technology to the battle is software and data analytics giant SAS, a heavy investor in artificial intelligence and a world leader of tools to extract information from so-called “big data” – information gathered from many sources.

In an exclusive Q&A with WRAL TechWire, Theresa Do, Support Manager for Federal Healthcare at SAS, talks about the potential uses of AI, machine learning and analytics to combat the corornavirus and future health threats. Do also is a Professor of Epidemiology & Biostatistics at George Washington Univ. in Washington, DC.

Can SAS technology be used to help vaccine developers speed up research? Is that happening?

Developing new treatments and creating vaccines and antiviral medications for newly discovered viruses is a difficult and time-consuming process, traditionally involving lots of trial and error. AI and advanced analytics can help improve the application of current treatments and speed up the development of new ones.

Theresa Do

For example, AI – specifically deep learning – is currently being used to help radiologists make better treatment decisions based on medical imaging. Chest x-rays of patients infected with the new coronavirus may serve as input into AI models that can help physicians make faster diagnoses as the outbreak continues. AI can also help here by examining data from similar viral diseases and using that data to predict what types of vaccines and medicines might be more effective.

What steps is SAS taking to apply its data expertise to track, analyze and offer possible means for clients and countries to deal with the coronavirus outbreak?

Data and analytics are the lifeblood for decision-making during infectious-disease outbreaks. Analytics can provide insights about the spread of a disease and the effectiveness of public health action, which can improve the response. The more information people have about case counts, mortality rates, how a disease spreads and how contagious it is, the better decisions they can make to limit, prevent and treat the disease. Public health and scientific data must be shared freely and rapidly with stakeholders and key decision makers so they can take action.

For decades, SAS has provided analytics software to public health and government agencies in the United States and around the world, helping them improve the health and well-being of their citizens. Governments hold much of the critical data needed to understand current conditions during an outbreak, but analytics companies like SAS offer an ability to synthesize this data with other non-government data and specialized tools to get the most insights from this unified data. These data-driven insights support better, faster government and public health decision-making. Events like the ongoing COVID-19 outbreak require public and private sectors to work closely together to limit disease spread and save lives.

Compiling of “big data” for analysis could create data sets that healthcare providers and governments could then use to track outbreaks better than in years past, correct? How so? Is this being done and if so by whom?

Collaboration, integration and rapid information sharing are essential to improve response and recovery for infectious disease outbreaks. Gone are the days when only governments and public health organizations had valuable data to fight epidemics. Disparate, non-traditional data sets can serve as sentinel sources – everything from travel and census data, to demographic information and animal migration patterns – can be applied to the public health threats. But the key is how to take advantage of all this data and emerging new data like genetic sequences.

Advanced analytics and AI (particularly machine learning) are essential tools to put data to work and save lives. With more and diverse data sets, the challenge is to synthesize everything to derive the insights needed to make decisions. A solid data management ecosystem and platform where the data can be stored, cleaned, scaled and shared among key stakeholders and decision makers is essential. So, it’s not just about the data, but also how that data can be used effectively in global collaboration to fight the emergence and spread of disease.

Finally, having enough good data is a challenge when a new, or novel virus is causing a disease outbreak. Advanced analytics are only as good as the data they can explore, analyze and sift through. For COVID-19, collaboration will continue to improve as more data is shared.

What roles could Artificial Intelligence and machine learning play in analysis and recommendations for dealing with the coronavirus and future outbreaks?

Analytics has an important and growing role to play in the detection and monitoring of all viral-disease outbreaks. Critical insights about disease spread and the effectiveness of public health action can be derived from analytical approaches, which helps decision-makers adjust and adapt their strategies and responses.

AI and machine learning in particular are valuable tools for healthcare professionals and policymakers to reduce or better manage the impact of emerging infectious diseases like COVID-19. Machine learning is designed to consider large amounts of data, find patterns in that data and detect anomalies, and in many cases offer predictions.

AI can help health authorities better detect infectious disease outbreaks by analyzing sentinel data sources for early warning of potential threats. AI can be applied to models on common themes or topics to help identify common symptoms among new and evolving public health threats. Moreover, AI can help to automate data analysis, identify patterns and build models of risk factors to help in scenario analysis of transmission. And when it comes to identifying paths of transmission, AI can aid in the search for a host and/or index case, as well as tracking possible contacts.

How did SAS employ its tech in the SARS crises – and what lessons learned then are being applied now?

When SARS emerged, there were fewer data sources that could be leveraged, such as social media, Internet of Things (IoT) devices and technologies to help with diagnostics. Phone apps for tracking of health data and diagnostics were not yet present. (The iPhone came out in 2007, four years after SARS broke out). With the advent of the iPhone and new types of apps and technologies, scientists can leverage a lot more data for analysis in addition to the available sentinel sources.

Today there are more ways that people can communicate to quickly distribute public health prevention efforts and quell misinformation regarding public health threats such as the some of the misinformation around COVID-19. Providers have more information at their fingertips via technology versus when SARS first broke out during the early stages, as well as the availability of the internet. However, with COVID-19, there is still a lot more to be uncovered and learned.

For any infectious disease outbreak, good responses need good data that can be shared readily and acted upon quickly. That was true then for SARS, and it’s true today for COVID-19.