How health executives implemented analyzes when the crisis hit

Formulate which decisions are most important

We need some AI. “Regardless of the type of organization, we often hear some variation in this request in our conversations with customers. Technology is important, so why not start with technology? In fact, this approach is exactly behind.

For any kind of analysis, the starting point must always be the decision. You should ask: What insights do I need to make this decision better, faster or cheaper? It is also important to remember that any new technology feature requires a human touch. As Rachel Mushahwar, Vice President and CEO of Intel, says, “Technology is not meant to replace human interaction – it is meant to amplify and accelerate medical research, perform faster analyzes, and accelerate testing and experimentation.”

Should we open additional capacity? What are the personnel consequences of the trends identified in the latest epidemiological models? We know what trends look like nationally – but what’s happening in our local area? These are just a few of the types of questions that health leaders are often called upon to answer – and this is where every analytical initiative, big or small, needs to start. Start with the end in mind and the technology falls into place during the journey. Start with technology and your organization may risk creating an advanced capacity that will eventually gather dust.

Build models with a focus on the most important issues

While a crisis like a pandemic certainly changes the data that promotes analytics models, as well as the forecasts and other outputs that come out of those models, the decision need in many cases does not change that much. For example, resource capacity – such as staffing and available beds – is always important for hospitals, not just in a pandemic. What changes are urgent, effects and scenario possibilities. Those already accustomed to using analytics to help make resource allocation decisions were better prepared for the same types of decisions in a pandemic.

E.g, The Cleveland Clinic created a number of models which helps predict patient volume, bed capacity, ventilator availability and more. The models – freely available via GitHub – provide reliable and dependable information to hospitals and healthcare departments to optimize healthcare delivery to COVID-19 and other patients and to predict effects on the supply chain, economy and other critical areas;

Contrary to some forecasts that focus on a projection based on a single set of assumptions, these analytical models were used to create worst-case, best-case, and likely scenarios. And they can adjust in real time when the situation and the data change. For example, the models may have a dampening effect on social distancing on the spread of disease.

The Cleveland Clinic uses the models to continuously support the decision-making process. It can use this information to predict and plan future requirements for the healthcare system, such as ICU beds, personal protective equipment and fans. After reviewing possible COVID-19 surge scenarios generated by the models, the Cleveland Clinic chose to activate a plan that prepared it for the worst-case scenario and has built a 1,000-bed surge hospital on its training campus for COVID-19 patients who do not ‘do not need ICU care. The hospital system also used the models to inform decisions about organizing and activating new labor pools.