Event Information:

• Thu

  12

  Apr

  2018

  UCSF to use predictive analytics to maintain imaging devices

  By Fred Bazzoli

  Healthcare organizations spend millions of dollars on imaging devices, so ensuring that they’re optimally maintained is essential in maximizing the return on that investment. Now, predictive analytics and machine learning are being used to do that.

  UCSF Medical Center in San Francisco is turning to an information services and analytics product from Glassbeam to power its clinical engineering analytics program.

  The hospital will work with the Santa Clara, Calif.-based company to use its CLEAN blueprint (Clinical Engineering Analytics) to manage components of its imaging equipment, with plans to expand its use to other modalities, such as ultrasound, cath lab and physiological monitoring equipment.

  “Investing in data systems and predictive analytics capabilities to help us facilitate service management, asset utilization and performance improvement of medical machines is critical to our success,” says Ramana Sastry, director of clinical engineering at UCSF Health. “Glassbeam’s unique analytics solution will help us as we scale our operations over next few years.”

  UCSF executives say that imaging medical equipment systems are based on complex technologies, and they increasingly are producing complex machine data that require more advanced data transformation solutions to enable root cause analysis, predictive analytics, machine learning and other high-value support applications.

  Also See: Machine learning analysis helps predict spinal injury prognosis

  The Glassbeam technology is intended to help organizations realize value from their machine data, and it can be used to optimize uptime on a variety of devices from different manufacturers, analyzing data to give a better view of operations and provide actionable intelligence.

  Using machine learning to improve imaging device performance is a crucial next step, says Frank Beltre, a service operations management consultant for UCSF. “This process traditionally has been done manually, and we’ve had to inject human behavior into the process of gathering data and looking at data. Using predictive analytics for lifecycle management of equipment is much easier—using manual processes doesn’t provide the predictive piece. It can take two to three weeks to analyze data from these devices, and so automating the gathering and analysis of this data can help you predict what to do and be ready for future events.”

  Glassbeam’s analytics and data collection runs on Amazon’s cloud services, says Puneet Pandit, the company’s CEO. Service logs from imaging devices are extensive but often result in vast quantities of unstructured data that contains a lot of semantic meaning. Digesting the output of these devices can help improve service and provide better care to patients, he says.

  Time savings in managing complex imaging devices can be significant, Beltre says. Predicting part failure or wise use of preventive maintenance can result in huge time savings. If a part fails in an imaging device, it can take 40 hours to obtain the replacement, install it and test it, he says. Getting ahead of part failure can increase device uptime and reduce costs for procuring replacement parts, he says.

  https://www.healthdatamanagement.com/news/ucsf-to-use-predictive-product-to-maintain-imaging-devices