This paper presents an implementation work on the digitization of hospital facilities leveraging Internet of Things (IoT) and machine learning algorithms. The objective of the study is to augment healthcare service delivery and facilitate robust patient care. The application of IoT devices in healthcare has provided a platform for continuous monitoring, resulting in significant improvements in patient outcomes. We present a dual-pronged approach using two machine learning algorithms - Random Forests and Support Vector Machines (SVM) - to develop predictive models based on the data acquired from IoT devices. Random Forests is applied to predict patient health deterioration, enabling early intervention by clinicians, while SVM is employed to identify potential equipment malfunctions or requirements for preventative maintenance. The research establishes an IoT infrastructure within a hospital environment, integrating numerous IoT devices to digitize patient health records, vital signs monitoring, and hospital equipment status. The data from these IoT devices are fed into the machine learning models to provide actionable insights. Our results demonstrate an improved efficiency in healthcare service delivery, increased predictive accuracy for potential health issues and equipment failure, as well as enhanced overall patient experience. The study thus provides a pioneering perspective on digitizing hospital facilities, setting a concrete foundation for future research in this domain.
Key words: Digitization , Hospital , Facilities
|
