Predictive Maintenance in Healthcare Services with Big Data Technologies


11th IEEE International Conference on Service-Oriented Computing and Applications, SOCA 2018, Paris, France, 20 - 22 November 2018, pp.93-98 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/soca.2018.00021
  • City: Paris
  • Country: France
  • Page Numbers: pp.93-98
  • Keywords: Big data, Biomedical devices, Cloud computing, Internet of things, Predictive maintenance
  • Hacettepe University Affiliated: No


Advances in medical technology is not sufficient alone to satisfy the growing and emerging needs such as improving quality of life, providing healthcare services tailored to each individual, ensuring efficient management of care and creating sustainable social healthcare. There is a potential for substantially enhancing healthcare services by integrating information technologies, social networking technologies, digitization and control of biomedical devices, and utilization of big data technologies as well as machine learning techniques. Today, data has become more ubiquitous and accessible by virtue of advancements in smart sensor and actuator technologies. This in turn allow us to collect significant amount of data from biomedical devices and automate certain healthcare functions. In order to get maximum benefit from the generated data, there is a need to develop new models and distributed data analytics approaches for health industry. Big data has the potential to improve the quality and efficiency of health care services as well as reducing the maintenance costs by minimizing the risks related with malfunctions of biomedical devices. Hospitals grasp this noteworthy potential and convert collected data into valuable information that can be used for several purposes including management of biomedical device maintenance. To this end, in this study, by leveraging the latest advancements in big data analytics technologies, we propose a scalable predictive maintenance architecture for healthcare domain. We also discussed the opportunities and challenges of utilizing the proposed architecture in the healthcare domain.