During the first three days of this month’s epic flooding in Louisiana, Our Lady of the Lake Regional Medical Center in Baton Rouge saw patient volume swell by more than 30% from around 300 to nearly 400 patients a day.
Many of the patients needed both clinical and emotional care resulting from the event, and others needed basic medical supplies or couldn’t get to their local clinic. More than 150 helicopters landed on its helipad, bringing evacuees in need of care and support.
Nearly 700 of the hospital’s team members worked 12- to 18-hour shifts, bedding down in conference rooms to rest up for subsequent shifts. About 30% were directly impacted by the event.
“Our leadership closely monitors severe weather forecasts in order to prepare team members for potential disaster staffing,” says hospital spokeswoman Lauren Davidson. “While river crests were forecasted to be at record heights, no one had predicted the massive extent of this historic flooding.”
OLOL leadership issued a Code Grey — a weather event that impacts the community and could impact the availability of care — and took steps to ensure the hospital would remain staffed with necessary personnel throughout the crisis.
Meanwhile, OLOL’s Livingston campus was completely surrounded by water and only accessible by boat. But with the help of the U.S. Coast Guard and Louisiana National Guard, it was able to transport supplies by helicopter and meet the needs of the heavily impacted community.
Ochsner Medical Center – Baton Rouge also remained fully operational throughout the event, but moved some of its most critical patients to eight other hospitals in its system. “The continuation of patient care was seamless through Epic our electronic medical record system, and MyOchsner, our patient portal, as physicians and patients always have access to their medical records at any facility in our system,” Ochsner CEO Eric McMillen tells Healthcare Dive.
Since Hurricane Katrina in 2005, Ochsner has upgraded all of its campuses to ensure they are prepared for major storms and able to provide continuous care, including having agreements in place for the delivery of additional supplies and back-up generators, if needed, McMillen says.
“We also have redundant communication abilities including ham radios, satellite phones and out-of-state area code cell phones to ensure that staff can constantly communicate with each other in the event of a disaster,” he adds.
Both hospitals’ response is in sharp contrast to New Orleans’ Memorial Medical Center in the aftermath of Katrina when generators failed and intensive care patients wallowed in suffocating heat. By the time evacuations got underway, 45 patients had died.
While hospitals managed better in this summer’s unnamed storm, could big data have helped them to prepare even more?
Today, companies like IBM and Smart Oceans BC are using predictive analytics to detect storms, tsunamis and other natural disasters and determine early response plans. At IBM, for example, The Weather Company couples real-time weather forecasts with a detailed map of a city’s infrastructure, pinpointing where the greatest impact is likely to occur.
“Using historic data from natural disasters … predictive models can be developed to provide instant assessments of infrastructure failure within a disaster zone under various weather conditions—just consider, for instance, wind’s effects on power lines,” Michael Stevens, government market segment manager for IBM’s information management division, wrote in an IBM blog.
With the growing connectedness of the Internet of Things, the ability exists to build predictive models for specified uses that take into account the weather, he adds. Take, for instance, law enforcement, where some departments are creating models to identify crime “hot zones.” One of the factors that goes into such models is weather.
Kaitlin Noe, a social specialist on IBM’s Analytics Solutions team, points out in another blog how data analytics is transforming emergency management, automating emergency preparedness drills and ensuring continuous cloud-based communication and access to up-to-date information during a disaster, even when infrastructure is weakened or broken.
“Thanks to the opportunities presented by new technologies, we are seeing another stage of emergency management,” Noe writes. “This new stage balances the historical approach to emergency management with the potential of technology to unify resources and adapt plans in real time.”
These tools can also help with recovery, she notes, maximizing the effectiveness of strained resources. “Big data tools can analyze post-even reports to determine how successful the response was and how it could be improved," she says. "They can also track the success of recovery plans over the course of years to aid reevaluation of long-term strategy."
Healthcare can take a lesson from “big weather,” which uses sensors to track atmospheric events, says Stuart Sim, director of advanced analytics at consulting firm West Monroe Partners. Alerts from the National Weather Service typically indicate the severity of a storm and its potential for damaging effects, as well as the localities that are in its path. But “in order for a healthcare provider to automatically derive a meaningful impact from this message, it needs to be parsed and mapped into a location grid,” Sim wrote in Healthcare IT News.
While legacy computer systems would be taxed to process these messages, newer alternatives are available that could help providers prepare for and respond to natural disasters, he says. They include IBM’s Deep Thunder, which can “deliver hyper-localized weather predictions up to three days in advance, with calculations as fine as one kilometer and as granular as every 10 minutes,” Sim notes.
Another example is StormTag, a Bluetooth-enabled app that bundles multiple sensors — temperature, barometric pressure, humidity and UV light — and delivers real-time information to a smartphone.
The Internet of Things has also made it easier to track the location of patients and equipment,” Sim adds. “Hyper location tracking of medical devices such as wheelchairs, infusion pumps and defibrillators that might need to be mobilized in the event of an emergency can be routed to targets without having to first discover where they may have been put in storage.”
As Louisiana struggled to meet the needs of flooded communities, the National Oceanographic and Atmospheric Administration announced a new tool that simulates how water courses through the nation’s rivers and streams, enabling street-by-street forecasts and inundation maps to improve flood warnings.
The new supercomputer collects data from more than 8,000 U.S. Geological Survey sites to simulate water conditions in 2.7 million locations in the 48 contiguous states, updating forecasts on an hourly basis. According to Bloomberg, the tool allows forecasters to target floods up to three days in advance and, with the aid of other forecasting systems, identify storms that may cause flooding 10 to 30 days before they occur.