Virtualization Technology News and Information
LeanTaaS 2020 Predictions: Data Science-Driven Metrics Will Start Being Adopted Due to Meaningless Averages

VMblog Predictions 2020 

Industry executives and experts share their predictions for 2020.  Read them in this 12th annual series exclusive.

By Sanjeev Agrawal, President, LeanTaaS

Data Science-Driven Metrics Will Start Being Adopted Due to Meaningless Averages

Operations teams seem to run on "averages," especially in the healthcare arena. Committees and leadership look at all kinds of averages to make decisions - average LOS, average case length, average turns per infusion chair, average block utilization, and average wait times, to name a few. The simplest way to illustrate the problem with averages is as follows: "If I put my head in the freezer and my feet in the oven, my average body temperature might be 98.6 degrees Fahrenheit, but I will soon be dead." 

Some practical examples:

  • Take the way global averaging works for estimating case lengths for spinal surgeries that every operating room has to decide on. Global averaging of a 2-level spine fusion and a 5-level procedure to come up with the "average length of a spine case" is like putting my head in the freezer and feet in the oven to come up with a meaningless answer. There is a much more useful and sophisticated way of looking at specific case types and the notes for the procedure and coming up with data science models that are far more useful to estimate lengths of the two very different types of spine cases.
  • How clinics anticipate and plan for the volume of patient arrivals requires much better planning than "40 patients per day." The data now exists for us to understand and staff within each 15-minute window of each day the mix of the various appointment types in the incoming arrivals; the time spent by a specific provider with a patient for each type of appointment that they encounter; and the probability of an add-on, cancellation, late arrival or no-show. Only then can clinic provider templates be optimized to lower patient wait times and have a smoother day for staff, physicians and patients.

These are two of hundreds of examples - the morning huddle for the expected number of discharges in inpatient units, the length of an infusion appointment, the expected wait in the emergency room - there are now tons of historical data that can be used to come up with far more meaningful and accurate predictions.

Given the need for better utilization of resources in enterprises in general - but particularly hospitals - operations teams will have to start moving to use more science with the data to determine and review metrics.


About the Author

Sanjeev Agrawal 

Sanjeev Agrawal is president 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, 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. For more information on LeanTaaS, please visit and follow the company on Twitter @LeanTaaS, LinkedIn at and Facebook at

Published Tuesday, November 12, 2019 8:01 AM by David Marshall
There are no comments for this post.
To post a comment, you must be a registered user. Registration is free and easy! Sign up now!
<November 2019>