At Tampa General Hospital (TGH), every minute in the operating room is crucial. This is especially true in cardiovascular thoracic operating rooms (CVTORs), where transplant surgeries and complex vascular procedures are routine. Precision is essential, not only during the actual surgeries, but also during the transitions between them.
Like many leading health systems, TGH’s efforts to reduce turnover times in CVTORs had reached a plateau. Despite years of process improvement, the reasons for turnover delays remained unclear. Leaders recognized they were wasting time, but couldn't answer the critical question of where the operational cracks were.
Delays without answers
Before Apella, turnover tracking relied on two basic EHR timestamps: wheels out and wheels in. Everything in between was a mystery. Delays were visible, but the causes were not. That lack of objective data created friction across the team:
- Surgeons finished long, complex cases only to wait 45 minutes for the next one, often assuming the environmental services team was causing the hold up.
- Charge nurses fielded constant “Why aren’t we in yet?” calls with no way to verify in real-time where the delays were happening.
- Staff absorbed the downstream impact: late finishes, missed breaks, and the cumulative stress that fuels burnout.
Learn how Tampa General Reduced Turnover Cleaning Time by 12%.
Read the case study
Objective data, captured automatically
In early 2024, TGH implemented Apella’s ambient AI to replace speculation with real, actionable insights.
Apella passively captured activity in the OR and automatically identified the start and end of key turnover sub-phases, such as when cleaning truly ended or when setup began. This gave TGH two things they’d never had before: real-time visibility and precise, objective data. With it, teams could:
- Pinpoint bottlenecks by sub-phase: cleaning, setup, anesthesia
- Act in the moment using live dashboards at the nursing station
- Benchmark fairly across rooms and shifts using the same source of truth
38 more cases per year
By breaking turnovers into measurable components, TGH uncovered a critical insight: cleaning wasn’t slow due to lack of effort; it was slow because of miscoordination. With that visibility:
- Cleaning times improved by 12%
- Each case averaged five minutes of wasted time saved
- That translated into 38 additional cases per year
For a high-acuity CVTOR, that’s nearly a full month of added surgical capacity without hiring staff or building new ORs.
Efficiency that scales
The CVTOR success created a repeatable model for improvement at TGH. The same AI-driven approach is now being applied across anesthesia prep, case wrap-up, and other high-variability phases of the surgical day.
What changed wasn’t just performance; it was decision-making. Leaders moved from reacting to delays after the fact to managing flow in real time, using a single, trusted source of truth.
Learn how Tampa General Reduced Turnover Cleaning Time by 12%.
Read the case study