In an era of inflation, talent shortages, supply chain challenges and shrinking capital, healthcare decision-makers must be more adept than ever at saving money. And those headwinds are leading some healthcare leaders to chart modern paths with emergency medical providers in the world of AI.
“AI and predictive modeling drive everything we do, and these tools help our hospital partners significantly increase patient throughput,” said Larry Richardson, a former paramedic and chief business officer at AmeriPro Health, an Atlanta-based provider of 911 EMS and medical transport services. AmeriPro operates in nine states and has seen year-over-year growth of more than 100% since launching in 2018.
“We’re a data company that happens to run ambulances,” he continued. “We know where we need to be and have the resources in place long before we need to be there, which creates a much better chance of optimizing the level of advanced pre-hospital care.”
PROBLEM
As Richardson explained, the problem facing one of AmeriPro Health’s partner hospitals was a combination of familiar issues that nearly every healthcare CEO in the country has grappled with over the past few years: overcrowding, bottlenecks that ponderous patient throughput, excessive outages in departments, and a lack of readily available, actionable, real-time data to overcome these challenges.
“It was a perfect storm of cascading events that disrupted day-to-day operations and threatened to limit long-term growth prospects,” he said. “Those were the immediate issues within the facility, but there was also a knock-on effect that rippled out into the broader community.
“It was not uncommon to see a queue of our ambulances outside waiting for several hours due to a lack of beds,” he continued. “These units were now temporarily out of service, unable to respond to other emergencies that may be occurring in the area. This is just one example of why optimising patient flow is so critical.”
In healthcare, every second counts, he added.
“You can have a world-class team of professionals, cutting-edge technology and a facility that is unmatched in the marketplace, but if you don’t have an effective logistics network that gets patients the right care in the right place at the right time, you’re never going to solve the patient flow problem,” he said. “Fortunately, this health system has been ahead of the curve in identifying these challenges and has demonstrated the necessary determination to address them quickly.”
APPLICATION
AmeriPro Health’s proprietary technology The AI platform will create and evolve predictive models to identify recurring bottlenecks and provide decision makers with clear guidance on what needs to be done to fill the gaps.
“If you understand what’s coming up ahead in terms of daily patient flow, equipment demand, peak utilization and staffing needs, you’re inevitably going to be able to reduce the burden on physicians and nurses while improving patient outcomes and overall satisfaction,” Richardson said. “Our AI system would allow us to pull in real-time and historical hospital data to develop a preliminary algorithm that would provide guidance in minutes.
“It was all about removing bottlenecks and creating a coherent, unified strategy,” he notes. “The hospital leadership had one vision of what patient throughput should be. The middle managers and directors had a different way of looking at it. So we had to align all the perspectives into a working game plan that tied everything together based on the data we were collecting.”
As time goes on, the predictive value generated will be further optimized with an ever-expanding pool of real-time data, enabling patient flow managers to adjust accordingly and adapt much more quickly to rapidly changing circumstances, he added.
MET THE CHALLENGE
The technology AmeriPro Health deployed for the health system represented a modern chapter in the evolution of the artificial intelligence program AmeriPro Health already had in place on its internal network.
“How As an EMS transport provider, patient care is at the heart of everything we do,” Richardson said. “But we’re also a data company. With our AI platform, we know where we need to be and have our resources set up well before we need to be there, which creates a much better chance of optimizing the level of advanced pre-hospital care.
“Building on this foundation of success, the next logical step was to engage one of our larger partner hospitals, who quickly approved the pilot after we explained to them how the same technology could be used to their own advantage,” he continued.
“Our AI tool is a layer. We extract the raw data, run it through the Microsoft platform, and then inject it into the AI to get a predictive model that gives you all the guidance you need on daily volume/peak times, recommended staffing, and potential bottlenecks before they actually happen.”
After receiving the data, EMS staff made recommendations on how the hospital could change its operations to optimize patient flow. For example, EMS staff used an online ordering profile through computer-generated shipping, which allows the hospital to reduce shipping costs by sending correct data back and forth between AmeriPro and the hospital’s EHR system.
“The data also revealed ways the hospital could modify and find new efficiencies in its discharge process,” Richardson noted. “With the hospital’s permission, AmeriPro Health came in and staffed a discharge room where we could monitor patients and then facilitate all transfers out of the room so the hospital staff could devote their time and attention to filling beds for other patients.
“As our AI program evolves, our goal is to be able to go to a hospital, overlay that information on their EHR, and drill down into logistical needs and acuity behaviors,” he said. “If someone is having chest pain, we can use the data to predict how long they’re going to need to stay, and ultimately when they’re going to be discharged from the hospital and where they need to go.”
RESULTS
Within a few months By implementing the AmeriPro artificial intelligence program, the average length of hospital stay was shortened by a full day.
“These results prompted decision makers to quickly replicate the program at other hospitals in the system, resulting in a projected 4,700 additional admissions per year across the network,” Richardson reports. “We are currently developing strategies for other campuses and will implement them in the coming months.
“We have also dramatically reduced ambulance response times, and with the staffing crisis, our technology is helping us significantly optimize our resources to their maximum potential,” he continued. “Before our program was implemented, most of our hospital partner discharges occurred between 3:00 p.m. and 7:00 p.m. Now, 11 to 12 months later, ambulance discharges were occurring by 10:30 a.m..”
The math is uncomplicated: more capacity in the ER earlier in the day, which allows for more patients to be admitted, he added. It also directly resulted in increased community outreach, as more ambulances provided better access to care, rather than waiting on the hospital wall, he said.
ADVICE FOR OTHERS
“Data is the currency of truth,” Richardson advised. “That’s why it’s critical for healthcare leaders to work with a logistics partner that stays current with technology trends, understands the hospital’s mission and knows how to effectively leverage AI so resources and assets can be fully optimized.
“One of the most important lessons learned from this experience is how important it is for the ambulance provider to have a seat at the table when decisions are being made about how patients are transported,” he continued. “The potential savings in dollars and time are simply too great to ignore. We are not a provider, we are a strategic logistics partner.”
In this case, AmeriPro Health was able to add value to its partner hospital because the hospital accepted the technology and was able to view the problem through the lens of the hospital as a shared responsibility involving multiple parties working toward a common goal.
“There will always be uncertainty in our industry, but “By leveraging AI and other technological tools that allow us to better anticipate what might happen, healthcare systems will be better prepared to adapt and thrive, regardless of the inevitable crisis or sudden change,” he concluded.