Latest / The Operator's Manual with Fexingo: Daily Decisions, Tactical Wins, and Business Execution / How One Hospital Cut OR Turnover Time 25 Percent With One Camera
Transcript
- Lucas: So there is this mid-sized teaching hospital in the Midwest that cut operating room turnover time by 25 percent. And the entire intervention was one ceiling-mounted camera and a machine-vision model. Luna: A camera? That feels almost too simple. What were they catching with it? Lucas: They were catching every single minute between one patient leaving the OR and the next one rolling in. Before that, they were using manual logs and a clipboard. Nurses would jot down timestamps, but you know how that goes — sometimes you're in the middle of something and you forget, or you estimate, and the data ends up fuzzy. So they had a vague sense that turnover was taking around forty minutes, but the camera showed them it was actually closer to fifty-five. Luna: So the data was just wrong. And that misled everyone about where the time was actually going. Lucas: Exactly. The camera didn't just give them better numbers — it gave them a second-by-second timeline of every turnover. They could see when the room was empty, when the cleaning crew came in, when they left, when the next patient's anesthesia team showed up. And what they found was surprising: cleaning was not the bottleneck. The longest gap was between the room being clean and the next patient being ready for anesthesia. Luna: So the room was sitting empty, clean and ready, but nobody was bringing the patient in. Lucas: Right. The anesthesia team was still prepping the previous patient's discharge paperwork or finishing up in the holding area. And because the OR team assumed the cleaning was the slow part, they never questioned it. They just waited. The camera made that invisible wait visible. Luna: So what did they actually change? Did they hire more people? Lucas: No new staff, no new equipment. They changed the workflow. They moved the responsibility for calling the holding area from the circulating nurse to the cleaning team. So the moment the room passed inspection, the cleaning lead would call the holding area and say, 'The room is ready, bring the patient now.' That one action, that clear trigger, cut the average turnover from fifty-five minutes down to about forty-one. Luna: It's like a baton pass. Previously, the person handing off wasn't paying attention to when the baton was ready. Lucas: Precisely. And the beauty is the camera didn't just help identify the fix — it also verified the improvement. The same system that measured the before was measuring the after. So the hospital could see, week over week, that the gains were real and sustained. They even caught a few times when the new process slipped and the old delay crept back in, which let them course-correct quickly. Luna: I love that it's not a one-time fix but an ongoing monitoring loop. So is this something any hospital could do? I imagine installing cameras in ORs isn't exactly cheap or easy. Lucas: That's the interesting part. The hardware was actually off-the-shelf — a standard IP camera with a wide-angle lens, mounted in the corner of the room, roughly three hundred dollars. The software was the clever bit. They used a simple machine-vision model that was trained to detect when the room was empty and when there was a person in the bed. It didn't need to recognize faces or anything sensitive — it just needed to count people and detect the state of the bed. Luna: So no privacy nightmare? That's a relief, because I was about to ask — patients and staff might not love being filmed. Lucas: Right, and that was a big consideration. They worked with the hospital's ethics committee and the nurses' union from the start. The camera only captured a wide view of the room, and the model processed the video locally, on a small computer in the corner — it never streamed to the cloud. The only output was a timestamped log of the room state: empty, occupied, cleaning in progress. No video was stored. That transparency was key to getting buy-in. Luna: So the staff knew exactly what was being measured and why. That probably made them more willing to trust the data. Lucas: Absolutely. And there's a broader lesson here that goes beyond hospitals. Any operation that involves handoffs — a factory line, a kitchen, even a software deployment pipeline — can benefit from measuring the actual flow instead of relying on assumptions. The camera is just a tool to give you ground truth. The real insight was that the bottleneck wasn't where everyone thought it was. Luna: Yeah, it reminds me of that old saying: you can't improve what you don't measure. But sometimes you're measuring the wrong thing. Lucas: Exactly. And that's the thing — they weren't measuring the right thing before. They were measuring 'time from patient out to patient in,' but they weren't breaking down that interval into its components. Once they did, the fix was almost obvious. And it was a change that cost them nothing but a shift in responsibility. Luna: So what's the takeaway for our listeners who aren't running an OR? If they want to apply this in their own context, what's the first step? Lucas: The first step is to map the process at a granular level. Break down the handoff into its component steps and find a way to measure each one — even if it's just a stopwatch for a week. You don't need a camera to start. In fact, the hospital initially used a manual observation sheet for two weeks, and even that data was enough to suggest where the bottleneck might be. The camera just made it permanent and continuous. Luna: So start small, get the data, and then question your assumptions. That's a solid methodology. Lucas: And one more thing — they also found that the gains translated into real financial impact. Twenty-five percent faster turnover means they could schedule more surgeries in a day, which increases revenue and reduces patient wait times. The hospital estimated that the improvement added roughly two extra surgical slots per week, which over the course of a year can be significant. Luna: Two extra surgeries a week — that could be hundreds more patients a year who get treated sooner. That's a meaningful outcome. Lucas: And it all came from a three-hundred-dollar camera and a willingness to question a process everyone had accepted for years. There's a lesson there about the power of observation. Luna: Speaking of things we appreciate — if today's episode gave you a useful lens on your own operations, that kind of value is exactly why we keep doing this. And these conversations stay ad-free because of listener support. Lucas: Yeah, if you found this useful, you can help keep the show independent by supporting us at buy me a coffee dot com slash fexingo. No pressure, it just helps us keep digging into stories like this. Luna: And if you do, thank you. Now, back to the hospital — one more detail that stuck with me. They also used the camera data to improve scheduling. They found that the first turnover of the day was always the fastest because everyone was fresh. So they started scheduling the most complex surgeries later in the day when the team had more time, and the simpler ones earlier. That alone shaved off another five minutes on average. Lucas: That's a great example of using the data not just to fix a bottleneck but to optimize the whole flow. And it shows that these insights compound. Once you have good data, you start seeing opportunities everywhere. Luna: So it's not just about the one fix — it's about building a culture of continuous improvement. Lucas: Exactly. And that's the real takeaway from this story. The camera was the catalyst, but the mindset shift — moving from assumption to measurement — is what actually drove the improvement. That's something any team can adopt, regardless of industry. Luna: Well, I'm definitely going to look at my own team's handoffs differently now. Thanks for breaking this down, Lucas. Lucas: Sure thing. And if you want to try this in your own organization, start with a notepad and a stopwatch. You might be surprised by what you find.