Smart versus big: how data can assist in the OR

The OR is the centerpiece of every hospital and also the most expensive resource that should be used efficiently. Yet in reality, there are often delays when interventions are not intelligently scheduled and take place back-to-back. This is why the InnOPlan Research Consortium wants to make surgical device data usable and useful to improve the operating room planning process.

In this interview with MEDICA-tradefair.com, Dr. Lars Mündermann talks about operating room processes, their phases and obstacles and how smart data can support OR coordinators and OR teams.

Dr. Mündermann, what is the goal of the InnOPlan project?

Dr. Lars Mündermann: KARL STORZ and the University Hospital Heidelberg as well as several other partners from the university and industry sectors, collaborate in the InnOPlan joint research project that is funded by the German Ministry of Economic Affairs and Energy (BMWi), to turn operating room devices into intelligent data sources. The goal is to make clinical processes more efficient, with an emphasis on the OR and its environment.

The project goes beyond mere networking of medical devices and their interfaces. Let’s take OR management for example: If we provide information to the OR coordinator about the various phases of the surgical procedure, he has entirely different options to improve the planning and cleaning process as well as the transition from one patient to another.

What types of data do you access and what role does big data play?

Mündermann: Among other things, the field of big data includes management, retrieval, and analysis of large data volumes. However, the InnOPlan project primarily aims to generate smart data using big data, which is why analysis is particularly important. We access very heterogeneous OR data sources such as endoscopic cameras, light sources, insufflators or HF systems. In addition, there are potential data sources in patient monitoring and respiration that can also provide information on the patient’s condition. We want to generate an added benefit by combining, linking and analyzing this data while complying with data protection aspects. The management and consolidation and especially analysis of data from multiple sources are classic aspects of big data technologies this project ultimately wants to utilize to contribute to clinical process optimization.

Can you give us an example?

Mündermann: One example we are presently reviewing pertains to the transport of patients from the hospital ward to the OR. Since OR minutes are a very precious resource, the patient handoff needs to be as smooth and seamless as possible, so the OR is not left unused. This means that ideally, the next patient has to be transported from the ward and is ready to enter the OR at the end of the cleaning phase.

This is where correctly processed data from surgical equipment could help in predicting the estimated end of surgery with a certain probability. The OR coordinator could use this information to expedite the next patient’s transport.

The approach, in this case, is to optimally put all OR processes in place and make handoffs and transitions as smooth and seamless as possible. The operating room team should be able to focus on their medical tasks and not be bogged down by administrative or similar processes.

Another example for the systematic utilization of data would be “predictive maintenance“, meaning to predict when maintenance should be performed on equipment. If data can indicate where devices show wear and tear, the hospital is able to take action before any equipment failure actually occurs. In the case of an endoscope, for example, light source failure causes a major delay in the operating room process. Work, in this case, could be even more efficient if equipment data would be continuously collected and analyzed, allowing the determination when and where the light source loses intensity – possibly even before the loss can be visually noticed.

If you think about the future: how could hospitals utilize these types of data?

Mündermann: In this instance, I envision applications that use the data stream from surgical equipment to record OR processes and automatically identify OR progress. This smart data can subsequently support the OR coordinator in OR management or surgeons in preparing surgical case reports for example.

As already indicated, in the area of process support, there could be a conceivable tool that supports the OR coordinator with the visualization of the current OR status. The next patient could be transitioned more effectively, allowing for better OR process control. You can also take this idea one step further towards an “observant OR” that is able to support the team in its work in the future.