It started with a fever. A persistent cough followed, then difficulty breathing. When symptoms like these develop, it can be frightening. But when they develop during a global pandemic like COVID-19, it becomes even more alarming – for both the patient and the health care provider.
The person experiencing these symptoms worries whether they’ve contracted the new coronavirus, whether they’ve exposed their loved ones, whether they’re going to recover. At the same time, the health care provider worries whether their facility has capacity for another patient, whether they’ll have access to critical medical equipment and supplies, whether there will be enough medical staff and lab personnel to provide vital services.
Hospital systems have quickly activated pandemic response plans, paused non-emergency visits and elective surgeries, and implemented adaptive planning cycles. The crisis put an immediate strain on medical resources and exacerbated the already complex process of planning for a surge of infected patients. Will enough beds and ventilators be available? How many staff are themselves infected? How can providers triage and separate non-COVID patients? Fortunately, health systems and government agencies have something they can use to help inform their decisions – analytics.
Visit the SAS COVID-19 Resource Hub
While the COVID-19 pandemic has drastically affected societies around the world, SAS is committed to battling the disease with advanced analytics – and empowering others to do so as well. Visit our resource hub to learn more.
Proactive management of capacity, equipment and personnel
Though the pandemic poses unprecedented challenges, analytics provides vital insights based on reliable, timely data. Forecasting medical demand and optimizing response resources are essential to combat COVID-19 and mitigate its devastation. The health and well-being of patients and those who care for them are directly affected by the availability of essential medical resources like hospital beds, critical care capacity, medical equipment, personal protective equipment and staffing.
Yet when it comes to projecting the spread of infection, public health agencies must be cautious. If they underestimate the impact on health care systems, they won’t be prepared. If they overestimate, widespread fear could result. Advanced analytics can have a profound effect, helping health systems better plan and make modifications along the way. Guided decision making is empowered decision making.
The ability to gather real-time data, continuously monitor demand and supply, and proactively manage resources will help officials properly allocate equipment and supplies for the treatment and recovery of patients. Analytical methods help project things like the next outbreak hotspots, the number of infected people who will require medical intervention, and the number of caregivers needed as the pandemic evolves. Ultimately, insights gleaned from analytics can help save lives.
Cleveland Clinic partnered with SAS to create innovative models that help forecast patient volume, bed capacity, medical equipment availability and more ... And as the dynamics of the pandemic evolve, the models can adjust in real time – like taking social distancing into account to “flatten the curve” and lessen the spread.
An analytics partnership to track, treat and inhibit the spread of COVID-19
One medical center that’s operationalizing analytics to combat COVID-19 is Cleveland Clinic, a renowned global health care provider that operates in the US, Canada, England and United Arab Emirates. Cleveland Clinic is on the frontlines of the coronavirus pandemic, determined to optimize hospital preparedness before, during and after regional peaks.
Cleveland Clinic partnered with SAS to create innovative models that help forecast patient volume, bed capacity, medical equipment availability and more. Armed with this information, Cleveland Clinic is better positioned to support its decision making, addressing the COVID-19 challenges it’s facing today as well as planning for future demands. And as the dynamics of the pandemic evolve, the models can adjust in real time – like taking social distancing into account to “flatten the curve” and lessen the spread.
Another unique aspect of the models is that they do not forecast a projection based on a single set of assumptions. Instead, they create worst-case, best-case and most-likely scenarios. This multi-scenario analysis informs resource planners to adequately prepare for what’s next. One example is Cleveland Clinic’s response to possible COVID-19 surge scenarios generated by the models. The medical center activated a plan that prepared it for the worst-case scenario – it built a 1,000-bed surge hospital on its education campus in Cleveland for COVID-19 patients who don’t need ICU care.
Join the fight to mitigate COVID-19
SAS and Cleveland Clinic are excited to announce that their COVID-19 predictive models are freely available via GitHub, and hospitals and agencies are encouraged to access and use them. Additionally, there's another collaboration space specifically devoted to medical resource optimization models for data scientists to use when informing an optimum hospital restarting plan. Not only do these models provide essential information to optimize health care delivery, they also predict impacts on supply chain, finance, workforce and other key areas.
“These predictive models were developed jointly by two organizations that understand patient populations, data and modeling,” says Chris Donovan, Executive Director of Enterprise Information Management and Analytics at Cleveland Clinic. “We are sharing the models publicly so health systems and government agencies globally can use them in their own communities. Our hope is that others contribute their ideas and improvements to the models as well.”
The analysis is centered around the epidemiological SEIR model, which models the flow of individuals through four stages of a disease: Susceptible, Exposed, Infected and Recovered. The SEIR model developed by SAS and Cleveland Clinic is based on a University of Pennsylvania open source model that has been recoded and expanded on the SAS platform. The model is continuously improved with real-time feedback from epidemiologists and data scientists at Cleveland Clinic. Resulting models include flexible control of model parameters and different model approaches accounting for regional health and demographic variations and state-level assumptions.
“These models can help hospitals, health care facilities, state departments of health and government agencies forecast the impact of COVID-19 and prepare for the future,” says Steve Bennett, Director of SAS’ Global Government Practice. “The models can also assist more vulnerable, less developed health systems in the fight against COVID-19.”
- Containing health care costs: Analytics paves the way to payment integrityTo ensure payment integrity, health care organizations must uncover a broad range of fraud, waste and abuse in claims processing. Data-driven analytics – along with rapid evolutions in the use of computer vision, document vision and text analytics – are making it possible.
- Five ways your organization can enhance resilience for years to comeInnovation, agility and customer-centricity frequently top the list of companies’ strategic objectives, and now the most urgent priority is resilience. Given this new urgency, it’s worth taking a close look at the underpinnings of resilience and how they could be applied in any industry. This article explores how analytics can help boost resilience and includes key elements to keep your organization resilient.
- Health care cost containment through big data analyticsHealth insurers are plagued by fraud, waste and abuse. For health care cost containment, an enterprise approach to payment integrity using data management and analytics can help. With this approach, payers can detect and prevent fraud; influence provider, employee and patient behavior; and substantially reduce costs.