Predictive maintenance of medical devices based on years of experience and advan
- Analytics & Modeling - Machine Learning
- Analytics & Modeling - Predictive Analytics
- Healthcare & Hospitals
- Predictive Maintenance
Failure prediction by human operators requires advanced skills, and the limited number of experts cannot monitor all MRI systems around the world. "Corrective maintenance" for repairs after breakdowns has also become inevitable.
Hitachi analyzed three years’ worth of sensor data from 100 MRI systems and created a mechanism to investigate the cause patterns that lead to device failures. Then machine learning was used to define a normal operational state to achieve successful early detection of abnormalities and changes in status that lead to failures.