Earlier this year, Mohan Giridharadas, CEO & Co-founder of LeanTaaS, sat down with Steve Hess, Chief Information Officer of The University of Colorado Health (UCHealth), to discuss why the EHR alone cannot solve capacity management challenges. The iQueue platform, which relies on machine learning and predictive analytics, has helped UCHealth improve capacity in their ORs, infusions centers, and now, even their inpatient beds. Missed the event? We’ve got the details below, plus the full webinar recording and transcript.
Optimizing capacity in health systems has always been a complex process. With the unprecedented demand on healthcare organizations during COVID, it’s become exponentially more challenging.
Infusion center directors, OR nurse managers, and senior leaders do the best they can to navigate the daily chaos of capacity management by estimating what will happen over the course of the day. They know EHRs are not built to optimize asset utilization or patient access. EHRs serve many important purposes, not the least of which is supplying the data needed to create reporting on past performance. But to use that data to predict tomorrow’s capacity needs is a different task altogether. Optimizing capacity is a difficult math problem that can never be solved by an EHR by itself
EHRs do not use probability theory or simulation algorithms to account for delays, overbooking, cancellations, and add-ons. The dashboards and reports EHRs are designed to produce can’t fully address these variables as analytics software can. It takes constraint-based optimization methods, machine learning, artificial intelligence, and simulation algorithms to solve the problem.
Steve Hess, Chief Information Officer of The University of Colorado Health (UCHealth), realized the system’s EHR alone would not solve capacity management challenges. After launching Epic enterprise-wide in 2011, the organization began implementing LeanTaaS’ suite of iQueue software solutions in 2015. LeanTaaS tapped into the data provided by the Epic EHR, applying machine learning and AI to better predict supply and demand for their system’s capacity management needs.
UCHealth layered AI onto the EHR to leverage its value
UCHealth is an integrated healthcare system, located across Colorado from the northern part of the state down to Colorado Springs. The 12 hospital system generates $5 billion in revenue, operates 2,000 inpatient beds, and receives 4 million annual ambulatory visits.
Hess explained, “From an IT perspective, we are on a single enterprise Epic electronic health record with about 7 million unique patients in our integrated platform.”
The natural evolution of an EHR rollout entails a lot of optimization, change management, and staff getting familiar with the tools. In 2015, UCHealth looked at its oncology infusion scheduling and saw a bolus of activity between the hours of 10am and 2pm. The bottleneck was creating significant patient delays and causing nursing overtime.
Schedulers and managers already utilized all the tools Epic provided, using scheduling templates for two-hour, four-hour, and eight-hour infusion schedules. While the Epic templates were useful, they did not provide the forward-looking analytics needed to actively anticipate demand.
Hess shared, “We turned to LeanTaaS as an innovation partner to help us think through the problem from a mathematical calculation perspective. We’re trying to figure out how to schedule different lengths of infusions to flatten that peak from 10am to 2pm and create a much better patient experience, get patients through, and reduce overtime.”
UCHealth exported deidentified data out of Epic to the LeanTaaS cloud, and then ran it through their machine learning algorithms in iQueue for Infusion Centers. The process provided them with the information necessary to adjust their Epic templates to flatten that peak.
Immediate results fueled new opportunities
The results were almost immediate. Hess explained, “Within 90 days, what we saw in our first and largest academic medical infusion center was a 7% patient volume increase with no other variables that changed. So just by applying this machine learning math on top of our existing EHR scheduling capability, we flattened that curve, and saw 7% more patients, without adding staff or chairs.”
Based on that success, UCHealth looked for other opportunities throughout their system where there was what Hess described as “expensive real estate with unpredictable scheduling patterns.” LeanTaaS solutions were rolled out across the system’s other infusion centers, then to their ORs.
“We’re playing this game of Tetris, in a way that actually improves surgeon and nursing efficiency, increases our patients’ satisfaction while reducing our costs. We turned to LeanTaaS and said, ’Okay let’s figure out this problem with the OR.’ The ORs are infinitely more complex so it was not an easy nut to crack, but we did crack it with LeanTaaS’ help. Then we rolled out iQueue for Operating Rooms as well. It’s been a wonderful partnership to really leverage that investment in the EHR that we’ve made and layer intelligence on top of it.”
Hess shared that their journey with LeanTaaS continues and that they are in the earliest stages of implementing iQueue for Inpatient Beds. He predicts they will see a similar ROI. Layering analytics sofware, with the power of machine learning and AI, on their enterprise-wide EHR has opened the door to improved capacity across their system.