Those who were great with data before the pandemic were better prepared when it struck. Here are three key takeaways from their experiences.
As COVID-19 struck, one of the most critical decisions governments and health care providers around the world faced was how to best allocate limited medical resources, including intensive care unit (ICU) beds and ventilators. Not that this was a new issue – providers are always managing the fickle, sensitive balance between supply and demand for medical resources. But the pandemic threatened to upend everything, on a scale never previously encountered.
Some organizations fared better than others. For example, most of us have read stories in the media about hospital systems that went through the effort and expense of expanding bed capacity by hundreds or even thousands of beds, only to find that they were not needed. Meanwhile, in contrast, many other providers were quietly making decisions based on data and forecasting capabilities that left them well positioned to respond effectively to rapid changes in demand.
What distinguished the health care providers that were able to make quick, effective decisions? A host of factors contributed to this gap in responses, as each faced a unique set of challenges. But one particular factor appears to have set leaders apart: They had a strong capacity already in place for using data to inform decisions. So when conditions suddenly changed, they were prepared to act with agility, updating models and adjusting decision making accordingly. Meanwhile, others scrambled to merely gather new data – much less analyze or use it to inform projections, forecasts and ultimately decisions.
While leading analytics users in health care and government have pursued different strategies for analytics-based decision making – based on everything from geographic location to patient demographics – they tend to share several approaches. These should be the starting points for any health care organization looking for ways to become more effective and responsive using data – during and beyond the pandemic.
The COVID-19 resource hub
Our data analytics resource hub is filled with important information about how SAS can help organizations better respond to the coronavirus pandemic. Get the latest insights on analytics practices and ideas as the situation evolves.
Articulate which decisions are most important
“We need some AI.” Regardless of the type of organization, in our conversations with clients, we often hear some variation of this request. The technology is important, so why not start with the technology? In reality, this approach is exactly backward.
For any kind of analytics, the starting point should always be the decision. You should ask: What insights do I need to make this decision better, faster or cheaper? It’s also important to remember that any new technology capabilities will require a human touch. As Rachel Mushahwar, Vice President and General Manager at Intel, says, “Technology isn’t meant to replace the human interaction – it’s meant to augment and hasten medical research, perform faster analysis, and speed up testing and trials.”
Should we open additional capacity? What are the staffing implications of the trends identified in the latest epidemiological models? We know what the trends look like nationally – but what’s happening in our local area? These are just a few of the types of questions health care leaders are frequently called to answer – and that’s where every analytics initiative, large or small, should start. Start with the end in mind, and the technology will fall into place along the journey. Start with technology, and your organization could be at risk of creating an advanced capability that ultimately gathers dust.
Build models focused on the most important questions
While a crisis such as a pandemic certainly changes the data fueling analytical models, as well as the forecasts and other outputs coming out of those models, in many cases the decision needs don’t change all that much. For example, resource capacity – such as staffing and available beds – is always important to hospitals, not just in a pandemic. What changes are the urgency, impacts and scenario options. Those already accustomed to using analytics to help make resource allocation decisions were better prepared for those same types of decisions in the context of a pandemic.
For example, Cleveland Clinic created a range of models that help forecast patient volume, bed capacity, ventilator availability and more. The models – freely available via GitHub – provide timely, reliable information for hospitals and health departments to optimize health care delivery for COVID-19 and other patients and to predict impacts on the supply chain, finance and other critical areas.
Unlike some forecasts that focus on a projection based on a single set of assumptions, these analytic models were used to create worst-case, best-case and most-likely scenarios. And they can adjust in real time as the situation and data change. For example, the models can factor in social distancing’s dampening effect on disease spread.
Cleveland Clinic is using the models to support its decision making on an ongoing basis. It can use this information to predict and plan for future demands on the health system, such as ICU beds, personal protective equipment and ventilators. After reviewing possible COVID-19 surge scenarios generated by the models, Cleveland Clinic elected to activate a plan that prepared it for the worst-case scenario and has built a 1,000-bed surge hospital on its education campus for COVID-19 patients who don’t need ICU care. The hospital system also used the models to inform decisions about organizing and activating new labor pools.
Accelerate transformation when in crisis mode
Necessity is the mother of invention. A number of health organizations have informally reported that they executed long-planned, multiyear digital transformation plans in a matter of weeks or even days due to the unique, acute challenges presented by COVID-19. These organizations embraced change because they simply had no choice. And it’s reasonable to assume that more transformative change is on the way, especially in areas such as virtual care and remote consultations.
For example, Glenn Gutwillig, who is a managing director at Accenture focusing on global public health, said recently that one health care client “literally, within the first few weeks, had a 3,000% surge in their use of telehealth – and I think it’s expanded since then.” Nobody could have anticipated that rate of change in such a short time, but for those ready for change – like this organization – they were able to make it happen.
Leaders recognize opportunities presented during critical moments. Rather than hesitate, they execute. As a result, they are often able to seize advantages that may have otherwise been years in the making. Which long-simmering issues could your organization address as part of a large-scale response to pandemic-related challenges?
The insight imperative
Beyond any single analytics capability or software, many health care and government organizations that have so far excelled in their response to COVID-19 have nurtured a culture of analytics. This is not a new idea. But it is rare to be able to see the benefits of an analytics culture in such stark terms.
For those who are earlier in their analytics journey, this may seem daunting – but it shouldn’t. The crisis we are facing today has presented an opportunity for health care and government leaders to refocus and accelerate their analytics efforts. Start by identifying which questions are most important for your organization to answer, and just get started – one question at a time.
Leaders recognize opportunities presented during critical moments. Rather than hesitate, they execute. As a result, they are often able to seize advantages that may have otherwise been years in the making.
About the Author
Steve Bennett is Director of the Public Sector Practice at SAS. He is the former Director of the National Biosurveillance Integration Center, US Department of Homeland Security.
- Model risk management: Vital to regulatory and business sustainabilitySloppy model risk management can lead to failure to gain regulatory approval for capital plans, financial loss, damage to a bank's reputation and loss of shareholder value. Learn how to improve model risk management by establishing controls and guidelines to measure and address model risk at every stage of the life cycle.
- What is a data lake & why does it matter?As containers for multiple collections of data in one convenient location, data lakes allow for self-service access, exploration and visualization. In turn, businesses can see and respond to new information faster.
- 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.