In healthcare, service can be a factor in driving revenue. That’s one reason why patient throughput may be a main concern for many hospitals today. In fact, a recent Vizient survey reports that 52.8% of hospital and health system leaders see patient access, throughput and capacity as their top areas of focus for 2025.¹
This focus on access, throughput and capacity emphasizes the importance of reducing unplanned downtime related to equipment failures — especially when you consider that a tube failure or X-ray chain failure generates an average of 2-3 days of downtime.2,3,4
Enabling you to say goodbye to the three-day fix
Using predictive models may be useful to anticipate events, and it is becoming increasingly popular in hospitals. A study published in Health
Affairs in January 2025 found that 65% of U.S. hospitals reported using AI- powered predictive models, with much of the focus on identifying individuals at higher risk of complications and for patient scheduling.5
Predictive models may also be incredibly useful in equipment management. The goal here is often focused on using data analysis to anticipate when equipment or systems are likely to fail, potentially allowing for maintenance to be scheduled before a breakdown occurs.
Planned maintenance still requires downtime. In fact, the planned downtime to proactively repair a Computed Tomography (CT) system is approximately 12-16 hours.3,6,7 While that may seem like a lot, consider this: It’s up to 75% less downtime4,7 when compared to the average three-day turnaround, and it may be able to be scheduled for when the hospital is likely to be less busy.
What are the real-world benefits of predictive maintenance?
To understand the potential benefits of predictive maintenance, it’s helpful to look at a real-world application. One large healthcare facility in the U.S. operates several hundred inpatient beds and multiple diagnostic imaging systems. Among these systems are three CT scanners, which together support a high daily volume of patient scans. One scanner is used primarily for specialized procedures, while the others handle cardiac and outpatient imaging.
Regarding Health Care Technology Management (HTM), the hospital contracts with GE HealthCare as its full-service provider for imaging but has an in- house team for biomed, making it a mixed-model hospital.
The hospital added Tube Watch – a form of predictive monitoring designed to anticipate impending tube component and X-ray generation chain failure before it occurs so customers can proactively manage replacement to potentially avoid service disruption. Since adding Tube Watch, the hospital has been able to avoid major disruptions in patient care by performing services before system failure.
The Director of Imaging at the facility notes that Tube Watch has been a game changer because the high use of their systems can affect predicted lifespan. Their oldest CT scanner is over five years old, and while most scanners have a 10-year lifespan, this particular scanner is much older than its chronological age because of the work it does daily. In the case of this scanner, usage, not age, is a better indicator of parts wear, so predictive maintenance becomes all the more important.
How big of an impact can predictive maintenance have? The imaging director explained that when they first joined the hospital, replacing a tube could take up to three days due to delivery times. Today, they keep a spare tube on site and closely monitor service timelines to minimize delays.
They also emphasized that gaining approval for predictive services is generally straightforward. Imaging directors may hesitate to adopt new approaches without proven success, so demonstrating reduced downtime with solutions like Tube Watch helps reinforce the value of these services during business reviews.
What are possible additional applications of predictive maintenance?
While predictive maintenance may be impactful in high-use facilities, it also may have broader applications. Consider healthcare organizations with high daily imaging volumes that are tightly scheduled in advance because they serve a large geographic area. In these types of facilities, avoiding extended periods of downtime is important to help avoid costly disruptions and to better serve the patient population.
Learn more about Tube Watch and OnWatch™ Predict
Whether your imaging equipment utilization is high and scheduled well into the future or you’re prioritizing patient throughput as an initiative, Tube Watch and OnWatch Predict may be beneficial. By predicting when potential tube and X-ray chain failures may happen, this service allows proactive parts replacement and service scheduling at more convenient times, potentially minimizing patient care disruption.
References:
1. 2025 Trends Report: Strategy Is Finally Back in the Driver's Seat | Vizient/KaufmanHall
https://www.healthaffairs.org/doi/10.1377/hlthaff.2024.00842
2. Average downtime is calculated based on 88 systems globally for which we observed an X-ray tube failure and calculated on a 24x7 on a 12 month rolling period
3. Estimated planned downtime is based on the average labor time of 138 events related to the x-ray chain generation. Recommended labor time to replace an X-ray tube as per the svc manual.
4. Calculation is based on the avg downtime generated by a CT Revolution APEX for a tube failure or x-ray generation chain failure vs the average planned labor time.
5. Current use and evaluation of artificial intelligence and predictive models in U.S. Hospitals
| Health Affairs Journal. Accessed August 28, 2025. https://www.healthaffairs.org/doi/10.1377/hlthaff.2024.00842
6. Recommended labor time to replace an X-ray tube as per the svc manual
7. As each hospital is unique, results may vary. GE HealthCare does not guarantee the results
identified herein.
