Share with your friends










Submit

Analytics Magazine

Executive Edge: Command center analytics revolutionize healthcare

New and different approach to care logistics helps caregivers and patients 24/7.

Jeff TerryBy Jeff Terry

A program of work at Humber River Hospital in Toronto recently delivered startling results: 52 percent reduction in acute conservable bed days (defined as patients staying longer than the evidence supports), 38 percent reduction in ultrasound turn-around time and 23 percent reduction in emergency department (ED) patient waiting. All of these improvements came during the hospital’s busiest winter season on record, when daily ED visits increased by 8 percent [Source: Humber River Hospital Command Centre Scorecard].

Meanwhile, a program at Johns Hopkins Hospital in Baltimore improved access for very sick patients by 78 percent, reduced ED patient waiting by 35 percent, and reduced patient waiting following surgery by 70 percent – all during an 18-month period when inpatient occupancy grew 8 percent.

These step-function improvements occurred at leading organizations. Both hospitals have great electronic medical records (EMRs) and mature lean-based project management organizations. Johns Hopkins has been ranked the No. 1 hospital in America for a record 22 consecutive years, while Humber River is North America’s first all-digital hospital, with everything from a fully automated lab and pharmacy to robots distributing supplies.

What changed? How did these organizations improve some of their most important metrics? What new toolkit powered their next-level performance? The answer is clear.

Johns Hopkins and Humber River Hospitals both opened command centers powered by predictive real-time analytics. The Johns Hopkins Command Center opened in February 2016, and Humber River Quality Command Centre opened in November 2017. To get a sense of what these command centers mean to a hospital, think NASA Mission Control for healthcare. They represent a new and different approach from what’s been done with hospital transfer and care logistics centers.

The breakthrough results speak for themselves. Even more impressive is that:

  • These improvements represent only a fraction of the impact delivered.
  • The command centers are enabling both organizations to sustain the improvements.
  • Both organizations are already expanding the functionality and reach of their command centers to deliver more clinical, quality, patient safety and operational impact

In short, analytics-powered command centers have revolutionized performance at these two great organizations by helping caregivers and patients 24 hours a day, seven days a week. And the work has only just begun.

Hopkins and Humber are in the vanguard of a movement that is extending these concepts to other health systems and new problems every day. This movement is revolutionizing healthcare by combining culture change, co-located cross-functional decision-makers, new “mission controllers” backstopping care teams in real-time and advanced analytics. These analytics are the magic at the heart of command centers or “mission control” as they are sometimes called. These analytics put cross-system data to work in real-time and apply cutting-edge artificial intelligence to help orchestrate, synchronize and de-risk patient care. These analytics enable command centers to act now, right now, all the time. That small statement is revolutionary.

Figure 1: Every provider is trying for better quality, service and viability, but the oceans of data are deep, salty and disconnected. Source: GE Healthcare Partners

Figure 1: Every provider is trying for better quality, service and viability, but the oceans of data are deep, salty and disconnected.
Source: GE Healthcare Partners

Why are healthcare analytics so difficult? We all recognize the opportunity, of course. Hospital networks sit on oceans of underutilized data. Every provider is trying for better quality, service and viability, but the oceans of data are deep, salty and disconnected. Snorkelers create on-demand dashboards, scuba teams survey locations for data lakes, and a few brave researchers in deep-water submersibles create predictive algorithms. These valiant efforts lack the scale and sophistication to close the gap to real-time all-the-time action. Command centers are changing that.

Here’s the issue. Every major health system has teams exploring the depths to create value from data, but meanwhile, back on shore, charge nurses, surgeons, hospitalists and care coordinators still don’t have easy access to “freshwater” when its needed in the form of critical answers to questions like: Which patient is likely to have a cardiac arrest tomorrow? Which care team will soon be overwhelmed and might miss something soon? Which surgery is likely to be cancelled tomorrow due to a patient’s changing condition now? How should we sequence care progression tasks among medically-ready patients to create needed capacity for tomorrow’s pending admissions? And thousands more …

Why do caregivers need command center analytics? Bedside patient care teams work in real time, all the time serving patients. To help, command center analytics must also be real time, all the time. Monthly, daily and even hourly updates just aren’t enough. Neither are dashboards or reports because staff don’t have time to play “where’s Waldo?” to find the interesting bit for their patient. Moreover, caregivers already face a deluge of alerts and cannot tolerate another false alarm. They don’t need something else to dismiss; they need something highly reliable. They need help, not second-guessing. They need work taken off their plates, not more added.

How are command center analytics helping? Command center analytics are revolutionizing healthcare by supporting care teams 24×7, systemically, reliably and in a manner that’s action-oriented. This last bit – action – is critically important. In the moment, the mission controller and care team don’t care that machine learning, natural language processing and discrete-event simulation combined to identify the patient who may be a candidate for an evidenced-based pathway. The mission controller is focused on action: See the alert; research and confirm the situation; help the care team to remove a barrier, close a loop, intervene, expedite, prioritize, learn, trigger a process improvement…make a difference. Repeat.

Figure 2: Command center analytics help hospitals predict occupancy rates. Source: GE Healthcare Partners

Figure 2: Command center analytics help hospitals predict occupancy rates.
Source: GE Healthcare Partners

How does a command center work? Command centers serve the needs of caregivers with a special combination: co-located decision-makers empowered to make things happen, advanced analytics that focus action now, and mission controllers who apply their judgment to help care teams – a powerful new combination.

While every command center is different, each GE Healthcare Partners command center has common elements: physician and administrative leaders, co-located and newly empowered support functions, new “mission controllers” with the bandwidth for new tasks, advanced analytics, new learning mechanisms and a purpose-built space. These elements combine to create something new: A “second level” node that backstops care teams and support functions and provides a new “center of gravity” for culture, learning and innovation.

Command centers are usually designed, built and activated over 12 to 18 months with initial impact in about six months. GE’s approach is to design them with the involvement of hospital and/or healthcare system staff through a massively collaborative process.

What are the characteristics of command center analytics? Command center analytics are predictive, prescriptive and current. They must automatically sift through many signals to identify the needle in the haystack that merits attention by mission controllers. In short, command center analytics should be:

  • Cross system, drawing data from software and machines
  • Based on an integrated real-time data model that fuses data from all sources
  • Enabled by artificial intelligence, including machine learning, natural language processing (NLP), computer vision and other modes
  • Independent of any single transactional or source system
  • As predictive and prescriptive as possible
  • Simple enough for mission controllers to interpret in seconds
  • Searchable retrospectively for continuous learning and improvement

What are examples of command center analytics? Today, GE Healthcare Partners has analytics that help improve access for transfer patients, manage patient pathways, manage patient safety risk, synchronize care progression tasks, prioritize local resources to support enterprise optimization, accommodate inpatient imaging procedures, reduce delays in care and more. Command center analytics are organized as “tiles” with each tile focused on a specific topic and fine-tuned for simple interpretation. Behind the scenes, GE Healthcare Partners’ analytics “engine” updates a real-time data model with 3-20 incoming messages per second and applies analytical horsepower to find needles in the haystacks. All of this is hosted in the cloud or in a health system’s private data center.

The most exciting part is that command center staff and GE Healthcare Partners are working all the time to desalinize more data. To answer more questions for mission controllers. So mission controllers can help more care teams. So caregivers can help more patients get high quality care. All the time. Right now.

Jeff Terry is the CEO, Healthcare Command Centers, GE Healthcare Partners.

Analytics data science news articles

Related Posts

  • 60
    July/August 2015 By Sagar Anisingaraju and Mo Kaushal (l-r) The healthcare industry in the United States is going through a major transformation and is becoming much more consumer friendly. This process of “consumerization” will drive healthcare executives to pay close attention to what patients feel and think about healthcare organizations…
    Tags: data, patient, healthcare, patients, hospital, analytics
  • 58
    Following the 2016 presidential election, the first two months of the new year were quite tumultuous for the U.S. healthcare system. Interestingly, the Affordable Care Act (ACA) has survived so far, albeit the process to repeal the law has begun.
    Tags: healthcare, analytics, care, data
  • 57
    The CUNY School of Professional Studies is offering a new online master of science degree in data analytics. The program prepares its graduates for high-demand and fast-growing careers as data analysts, data specialists, business intelligence analysts, information analysts and data engineers in such fields as business, operations, marketing, social media,…
    Tags: data, analytics
  • 57
    The Johns Hopkins Hospital has launched a state-of-the-art, advanced hospital control center. The Judy Reitz Capacity Command Center, designed and built with GE Healthcare Partners (GE), combines the latest in systems engineering, predictive analytics and innovative problem-solving to better manage patient safety, experience, volume and the movement of patients in…
    Tags: center, hospital, command, patients, patient, percent, care, healthcare, analytics
  • 54
    Benjamin Franklin offered this sage advice in the 18th century, but he left one key question unanswered: How? How do you successfully drive a business? More specifically, how do you develop the business strategy drivers that incite a business to grow and thrive? The 21st-century solution has proven to be…
    Tags: data, analytics


Headlines

Does negative political advertising actually work?

While many potential voters dread campaign season because of pervasive negative political advertising, a new study has found that negative political advertising actually works, but perhaps not in the way that many may assume. The study “A Border Strategy Analysis of Ad Source and Message Tone in Senatorial Campaigns,” which will be published in the June edition of INFORMS’ journal Marketing Science, is co-authored by Yanwen Wang of the University of British Columbia in Vancouver, Michael Lewis of Emory University in Atlanta and David A. Schweidel of Georgetown University in Washington, D.C. Read more →

Meet Summit, world’s most powerful, smartest scientific supercomputer

The U.S. Department of Energy’s Oak Ridge National Laboratory on June 8 unveiled Summit as the world’s most powerful and smartest scientific supercomputer. With a peak performance of 200,000 trillion calculations per second – or 200 petaflops – Summit will be eight times more powerful than ORNL’s previous top-ranked system, Titan. For certain scientific applications, Summit will also be capable of more than three billion billion mixed precision calculations per second, or 3.3 exaops. Read more →

Employee engagement a top concern affecting customer experience

Employee engagement has surfaced as a major concern in delivering improvements in customer experience (CX), with 86 percent of CX executives in a Gartner, Inc. survey ranking it as having an equal or greater impact than other factors such as project management and data skills. “CX is a people issue,” says Olive Huang, research vice president at Gartner. “In some instances, the best technology investments have been derailed by employee factors, such as a lack of training or incentives, low morale or commitment, and poor communication of goals." Read more →

UPCOMING ANALYTICS EVENTS

INFORMS-SPONSORED EVENTS

INFORMS Annual Meeting
Nov. 4-7, 2018, Phoenix

OTHER EVENTS

Advancing the Analytics-Driven Organization
July 16-19, noon-5 p.m.


Making Data Science Pay
July 30-31, 12:30 p.m.-5 p.m.


Predictive Analytics: Failure to Launch Webinar
Aug. 18, 11 a.m.


Applied AI & Machine Learning | Comprehensive
Sept. 10-13, 17-20 and 24-25

CAP® EXAM SCHEDULE

CAP® Exam computer-based testing sites are available in 700 locations worldwide. Take the exam close to home and on your schedule:


 
For more information, go to 
https://www.certifiedanalytics.org.