Lean Six Sigma has long been a cornerstone methodology for process improvement. Thanks to its flexible nature, Lean allows organizations to bring other tools into the mix that can lead to even better results.
That approach proves especially beneficial in the healthcare industry when combining Lean with big data analysis.
The term “big data” is essentially a catch-all phrase that includes anything to do with the management, collection and analysis of massive data sets. In healthcare, this data can include digital patient records that store a vast amount of information on doctor’s visits, medications taken and procedures undergone.
But healthcare data also includes information on wait times for patients, time that diagnostic machines remain idle and time spent by medical staff on various procedures and paperwork, some of which is wasteful.
Big Data and Lean
Lean Six Sigma can define many of the above problems and provides a systematic method for developing solutions. It also accounts for tracking those solutions to see if they work and then making adjustments as deemed necessary.
A big part of Lean is collecting data on a process and getting into the details of everything that goes into that process. With those types of details, teams can then begin to find the root causes of factors that are impeding the delivery of a service or product and determine wasted or unnecessary steps in the process.
Strategies associated with big data can prove beneficial in this area, especially predictive analytics.
Those working in predictive analytics work with large volumes of past data, searching for trends and also the relationship between two factors. In some cases, machine learning is employed to search for these often-hidden trends.
For an example from the healthcare setting, data analysts could collect data on the number of people who visit a diagnostic clinic every day, the type of treatment they seek and their average wait time.
The Winship Cancer Institute of Emory University in Georgia did exactly that, using a predictive model developed by iQueue Labs that predicted both the volume of patients and the mix of treatment they sought when coming to the institute – getting blood drawn, for example, versus a more complicated diagnostic treatment.
Using this information, the institute then took a very Lean approach, analyzing the challenges and finding solutions. By looking at the predictive model in 15-minute increments, they were able to staff the needed number of nurses and phlebotomists at the right times.
The result? They cut wait times from about one hour to less than 15 minutes.
Lean and Healthcare Integration
The above example shows how predictive analytics can be used as yet another tool in implementing Lean methodology.
And Lean is certainly worth using in healthcare, a mature industry that faces many challenges in improving both operational efficiencies and patient experience. But there is cause for optimism. Recently, success has been shown in a number of cases, including:
- A 2017 healthcare survey that found 87% of healthcare organizations that implemented process improvements saw scores from patients improve
- In Nebraska, the application process time for nurses to receive a license from the state was cut by more than a month when Lean practices were put into place
- In Dallas, a children’s hospital used Six Sigma methodologies used by Toyota to improve patient outcomes by 75%.
Even with the emergence of technology innovations, the core principles of Lean Six Sigma continue to make a difference for businesses across many industries, including healthcare. Big data and predictive analytics provide an extremely valuable tool that, in combination with Lean, can produce even better results.