Loading...
You are here:  Home  >  Data Education  >  BI / Data Science News, Articles, & Education  >  BI / Data Science Blogs  >  Current Article

Push Not Pull: Using Data Science to Improve OR Operations

By   /  May 7, 2018  /  No Comments

Click to learn more about author Sanjeev Agrawal.

While virtually every hospital has implemented a version of an electronic health record (EHR) that tracks the patient journey, most hospital administrators still use the tool in a “pull” manner; they start with something in mind and then look for the data. This causes problems when people aren’t clear on what to look for or get lost in reams of data available to them. Health systems equipped with trend and anomaly detection powered by predictive analytics, machine learning and mobile technologies can transform “pull” into “push” and reclaim underutilized operating room time. Not only does pushing data create better efficiency, it leads to enhanced communication and improved operations overall.

First, let’s briefly clarify what we mean by “push” and “pull.” While the approach to improving hospital operations employed is deeply rooted in lean principles, the use of the “push not pull” construct in this case refers to how healthcare providers can more proactively share key operational data with surgeons, nurse managers, schedulers, perioperative business leaders and administrative leaders. It may be helpful to look at other instances of push in our lives:

Community-based traffic app – Traffic issues, as experienced and logged by users, get sent to drivers traveling the affected roads. Imagine a mobile traffic and navigation app that required you to request road condition updates or ask for your next turn-by-turn directions along the route to your destination.

Retail – Projected demand determines what appears in stores and when. For example, warmer clothing items get pushed to retailers as summer ends and the fall and winter seasons start. While this sometimes leads to inventory arriving before the colder weather hits in any given location, it is a much preferred alternative to each retail location calling the supplier when the weather in their area starts to turn.

Apps and OSs – Look no further than your mobile phone for perhaps the most obvious example of push. Users are automatically alerted to updates directly on the device. If phone makers relied on users to inquire about the availability of updated apps or OSs, many users would simply neglect to update their phone. While that may not seem like a big deal, OS updates frequently address not only new functionality but also bugs and important security flaws.

Travel notifications – As someone who spends an inordinate amount of time in congested, noisy airports, I can attest to the benefits of flight delays, gate changes, etc. being sent to me via text message. Asking travelers to frequently check their flights for delays, gate changes or other important announcements is inconvenient at best — and downright impractical in most cases.

In the operating room (OR) environment — where every minute of OR time can be worth hundreds of dollars in revenue — every operational decision has too much financial impact to rely on whatever data a perioperative leader can glean from a previous data request or periodic report. These administrators already spend an inordinate amount of time creating and pushing historical reports that no one reads — or worse, no one believes. These EHR reports and dashboards often allow little more than an opportunity to “admire the problem”; they do a fine job of recording what happened but are ill-suited to providing quick, relevant and targeted insight into important operational metrics. Their metrics are rear-facing and difficult to access by all stakeholders. A push-based approach keeps stakeholders apprised of their performance without digging through confusing, often obsolete reports. What’s more, the most commonly reported metrics, like first case on-time starts and turnover times, often mask what is really going on. Pushing more relevant metrics like “collectable time” help make the case for proper block allocation.

One specific example of a push-based approach UCHealth used is being able to push “release reminders” to surgeons who were unlikely to use block time through a predictive analysis of the likelihood of future blocks being used. Surgeons and schedulers at UCHealth can now release time as well as request portions of time right from their mobile device and be notified when time opens up. They can also put their names on a “wish list” so if time is released they or their schedulers can request that time easily.

After one year of using this push-based approach, UCHealth — consistently ranked as one of the top hospitals by U.S. News & World Report — has seen some impressive results:

  • Over 2,000 blocks were released prior to the hospital’s auto-release deadline; almost 1,500 of those were claimed and used by another surgeon. Pushing OR release notices to the surgeon population improved communication and encouraged surgeons to be more proactive.
  • Block release times, previously only slightly longer than the 14-day auto-release deadline, were made available on average more than 19 days prior to the surgery date. Release reminders ahead of the surgeon’s typical release schedule made it easier for other surgeons to claim a room sufficiently in advance.
  • The hospital hired 11 new surgeons without a guarantee of block time upfront. By pushing utilization and room availability notices, these new surgeons have been able to find enough opportunities to serve their patients.
  • Equipped with objective performance metrics, even casual hallway conversations have been less contentious. Surgeons are happier having greater access and much more visibility into OR time.
  • Most significantly, OR utilization increased by 4 percentage points. In financial terms, that is over $400,000 per OR per year in additional revenue (over $10 million in total).

In summary, given the tools and technologies available to healthcare providers today — Cloud Computing, mobile devices and more — there’s simply no need to rely on dense, almost instantly obsolete reports that no one has time to read. There’s also no reason to continue having non-data-based conversations between surgeons and administrators when objective metrics are quite literally at their fingertips. Finally, in a time where providers are being mandated by regulation, patient demographic changes, and economic reality, there’s no reason to leave money on the (operating room) table by failing to adopt an objective, prescriptive, comprehensive, push-based approach to improving OR operational performance.

 

Photo Credit: LeanTaaS

 

About the author

Sanjeev Agrawal is President and Chief Marketing Officer of LeanTaaS, a Silicon Valley-based innovator of Predictive Analytics solutions to healthcare’s biggest operational challenges. He works closely with dozens of leading healthcare institutions including Stanford Health Care, UCHealth, NewYork-Presbyterian, Cleveland Clinic, MD Anderson and more. Sanjeev was Google’s first head of product marketing. Since then, he has had leadership roles at three successful startups: CEO of Aloqa, a mobile push platform (acquired by Motorola); VP product and marketing at Tellme Networks (acquired by Microsoft); and as the founding CEO of Collegefeed (acquired by AfterCollege). Sanjeev graduated Phi Beta Kappa with an EECS degree from MIT and along the way spent time at McKinsey & Co. and Cisco Systems. He is an avid squash player and has been named by Becker’s Hospital Review as one of the top entrepreneurs innovating in healthcare. Follow Sanjeev and LeanTaaS at: Twitter, Facebook, LinkedIn

You might also like...

Data Literacy and the Colin Powell Rule: From Frontline Field Support to Back Office Operations

Read More →