Imagine making plans for a vacation during a disruption like the coronavirus. There are many factors to pay attention to in this situation. Will you be traveling to a virus hotspot? How many people will be sitting near you on the airplane, or staying at your hotel? What precautions have those businesses taken to ensure your safety? Compare this to the heightened awareness an emergency room doctor needs to have to evaluate the human factors and other elements that guide a split-second decision for treating a critically ill patient. Whether simple or complex – or low or high risk – many circumstances call upon the concepts behind situational awareness.
Situational awareness means being mindful of what is present and happening around you – and combining that with preexisting knowledge to determine what’s likely to happen next. Having perception of the elements in your environment leads to levels of situational awareness that help you decide how to respond at any given time. It’s as relevant for our everyday lives as it is for our front-line health care providers and emergency responders, assembly line workers, business and government leaders, and others.
Mica Endsley,1 who is well-known for her research on the topic, describes situational awareness as having three stages:
- Perception of the status, attributes and dynamics of relevant elements in the environment. This leads to awareness of objects, people or events in a specific volume of time and space, and their current states or actions.
- Comprehension of the meaning of those elements. This involves situational assessment, which is the process of how we collect, synthesize and analyze information. People who are experienced at making quick decisions in fast-moving, stressful or crisis situations can rapidly integrate information to build a comprehensive mental picture of how the current situation will affect their goals and objectives.
- Projection of the status (or future states) of the elements in the environment. This means you can extrapolate the information from stages 1 and 2 forward in time to understand how all the elements will affect the future operational environment.
COVID-19 data and analytics resource hub
Leaders can’t make good decisions without a solid understanding of the current situation. Accessing and organizing the best data and then creating visualizations of the analyses of the data creates a common understanding and early consensus among stakeholders, which improves downstream decision making and communication.
Situational awareness is important during COVID-19
The concepts behind situational awareness were thrust to the forefront of our daily lives during the coronavirus pandemic. Many people watched news updates frequently to understand how close the virus was to their communities, hear the latest updates and guidance from government and health officials, and find out how many people had been infected and how many had recovered. Some chose to stay at home longer than others, based on their age, health or their personal interpretation of when it was safe to venture out.
Good assessments of situations help us avoid costly and potentially dangerous mistakes and delays. In complex and constantly changing environments, individuals need to maintain an exceptionally high level of situational awareness to stay safe and make good decisions. For example, think of all the factors first responders must consider – such as people, physical surroundings, environmental elements and activities – each time they respond to a call for help.
Data, analytics and visualization expand situational awareness – across industries
Our scope of situational awareness extends into broader realms when we analyze vast amounts of data in real time and visualize the results. Having real-time information to inform situational awareness avoids the lag time inherent in manual methods of gathering and assessing information.
Organizations have continually needed to make fast, critical decisions during the COVID-19 pandemic. With lives and businesses on the line, the need for timely, accurate data to ensure the best outcomes has never been greater. Through real-time situational awareness, SAS® helps decision makers predict peaks, maximize resources and work together based on common mental models of an operational scenario – knowing instantly when threats begin to re-emerge. Data-driven decisions allow you to maintain complete situational awareness for now and for what comes next.
Let’s look at some examples of how SAS has helped organizations use data, analytics and visualization to achieve situational awareness during the coronavirus.
Rich dashboards for government
According to Grant Brooks, Vice President of the US Public Sector at SAS: “Most government dashboards were built for other purposes and cannot integrate and synthesize all the available and relevant data in a timely manner to facilitate a meaningful and nimble response. They also lack the predictive, simulation and at-scale data analysis capabilities required to truly enhance decision making.”
Brooks describes seven categories of data that government dashboards should incorporate to deliver optimal situational awareness in a crisis. The data includes public health data, medical resources data, employment and wage data, social benefit data, financial stress indicators, tax collection and revenue data, and banking system data. “By aggregating this data to provide insights on the trajectory of the virus, complemented by the counsel of public health experts,” Brooks says, “governors will have the best, most accurate information available to inform the monumental decisions that are being made to keep people safe and restart the economy.”
In India, some state governments turned to SAS to help activate their data and analytical resources when the pandemic struck.2 This included Odisha, for example, which relies on an analytics dashboard to monitor continually updated metrics. SAS worked with several states’ IT and health care departments to track COVID-19 metrics such as hotspots, infection growth curves, containment areas and hospital resource needs. Based on timely data from the states, SAS built analytic models that helped improve outcomes.
Real-time insights and models for health care
SAS helps health care organizations gain situational awareness through continuous data gathering and interactive, analytically derived visualizations that quantify the impact of the virus. These tools help identify where the greatest needs are – and how to target resources to meet those needs.
Visualizations reveal impacted populations, locations of virus transmission, rate of growth and how the situation is changing over time. Mapping the spread of disease over time allows health leaders to plan for the resources and support they’ll need next – based on the virus’ anticipated status in the near future. In turn, medical professionals can assess capacity and be prepared for how to allocate beds, resources, equipment and people.
The same type of data used for situational awareness is relevant for other health analytics, including predictive models and scenario analysis. Analytics helps us determine whether measures like social distancing or shelter-in-place policies worked to slow transmission, and analytics projects the spread of disease given certain assumptions. Epidemiological models help us understand the impact of the virus as we start to reopen. And evaluating multiple risk scenarios helps identify the most vulnerable populations, while uncovering factors that might complicate health protection strategies.
Predicting and planning for impacts to clinical research in life sciences
Clinical trials follow strict protocols and are subject to extensive regulations. As such, this type of life sciences research is particularly vulnerable to any disruption, especially on the level of a global pandemic.
Situational awareness helps pharmaceutical sponsors understand where trials are affected the most so that they can develop plans to mitigate delays, keep clinical research on track and make trials more resilient to change. This includes making trials more patient-centric and site-centric, while ensuring supplies make it to patient participants.
Real-world evidence plays a critical role in filling data gaps and identifying potential treatments. "COVID-19 will accelerate the use of real-world data and real-world evidence in clinical research. This is especially the case as pharmaceutical companies explore treatments and vaccines and options for keeping ongoing trials running with minimal disruptions,” said Sherrine Eid, MPH, SAS Global Health Care Principal.
AI and IoT for manufacturing and retail
Some manufacturers relied on IoT sensors with analytics and artificial intelligence (AI) techniques to help fill the gaps that arose during the pandemic. By collecting and analyzing real-time data from sensors and networks across their operating environments – and applying AI techniques – they optimized supply chain actions, streamlining their operations and assisting their retail partners and consumers.
For example, "what-if" scenario views help them improve supply planning, analyze product substitutions, respond better to demand fluctuations, identify at-risk inventories, increase visibility into production operations and strengthen workforce safety. Even the smallest improvements have big implications. Such analytics techniques have been especially valuable during the pandemic, as supply chains were affected by closed borders, shuttered facilities and stores, and more.
Cloud and machine learning for banking
Digital identity authentication is essential for banks. This has been especially important during the coronavirus pandemic, because criminals see times of crisis as an opportunity to commit fraud. Banks need to know immediately whether a virtual credit applicant is who they claim to be, or whether the person trying to access an online account is the real customer.
Conducting due diligence around such customer transactions is a process banks follow to gain situational awareness when there are just seconds to make a decision. With a cloud-based solution from SAS, banks can vet each digital encounter against diverse authentication data from leading digital, biometric, public and behavior data providers. The data is centralized and fed into SAS analytics and machine learning algorithms, layering methods to quickly and accurately detect fraud. This provides near-real-time insights so banks can distinguish legitimate versus fake customers – without reliance on slow, manual intervention by agents.
Data visualization can be a good starting point to understand trends and piece data points together into a meaningful story. The ability to visualize the spread of the virus can help raise awareness, understand its impact and ultimately assist in prevention efforts. Mark Lambrecht PhD, Director of the Global Health and Life Sciences Practice SAS
Situational awareness across the phases of COVID-19 response
Across industries, organizations may find it helpful to respond to the coronavirus pandemic following a three-phased framework: Respond, recover and reimagine. Situational awareness has played a big role in the first phase as we determined how severe, widespread and fast-moving the disruption was likely to be – and how to respond. But it’s relevant in other phases, too. Situational awareness should help guide our decisions as we recover from COVID-19. And it should inform the changes we make as we start to reimagine and rebuild our workplaces, health care systems, economies, policies and more.
- CECL: Are US banks and credit unions ready?CECL, current expected credit loss, is an accounting standard that requires US banking institutions and credit unions to estimate life-of-loan losses at origination or purchase.
- Unemployment fraud meets analytics: Battle lines are clearly drawnMany fraudsters seized opportunities presented by the COVID-19 pandemic. During the crisis, unemployment fraud became a battleground between international criminal networks and government agencies. Learn how analytics can save billions – and deliver benefits to those truly in need.
- ModelOps: How to operationalize the model life cycleModelOps is where analytical models are cycled from the data science team to the IT production team in a regular cadence of deployment and updates. In the race to realizing value from AI models, it’s a winning ingredient that only a few companies are using.