Clinical Activity Monitoring System (CATS): An automatic system to quantify bedside clinical activities in the intensive care unit

Guo P 1 , Chiew YS 2 , Shaw GM 3 , Shao L 4 , Green R 5 , Clark A 6 Show all authors , Chase JG 7

Affiliations 

  • 1 Department of Mechanical Engineering, University of Canterbury, New Zealand; Auckland Bioengineering Institute, the University of Auckland, New Zealand. Electronic address: [email protected]
  • 2 Department of Mechanical Engineering, University of Canterbury, New Zealand; School Of Engineering, Monash University Malaysia, Malaysia. Electronic address: [email protected]
  • 3 Department of Intensive Care Medicine, Christchurch Hospital, Christchurch, New Zealand. Electronic address: [email protected]
  • 4 Department of Mechanical Engineering, University of Canterbury, New Zealand; School of Electrical Engineering, Tianjin University of Technology, China. Electronic address: [email protected]
  • 5 Department of Computer Science and Software Engineering, University of Canterbury, New Zealand. Electronic address: [email protected]
  • 6 HIT Lab NZ, University of Canterbury, New Zealand. Electronic address: [email protected]
  • 7 Department of Mechanical Engineering, University of Canterbury, New Zealand. Electronic address: [email protected]
Intensive Crit Care Nurs, 2016 Dec;37:52-61.
PMID: 27401048 DOI: 10.1016/j.iccn.2016.05.003

Abstract

Monitoring clinical activity at the bedside in the intensive care unit (ICU) can provide useful information to evaluate nursing care and patient recovery. However, it is labour intensive to quantify these activities and there is a need for an automated method to record and quantify these activities. This paper presents an automated system, Clinical Activity Tracking System (CATS), to monitor and evaluate clinical activity at the patient's bedside. The CATS uses four Microsoft Kinect infrared sensors to track bedside nursing interventions. The system was tested in a simulated environment where test candidates performed different motion paths in the detection area. Two metrics, 'Distance' and 'Dwell time', were developed to evaluate interventions or workload in the detection area. Results showed that the system can accurately track the intervention performed by individual or multiple subjects. The results of a 30-day, 24-hour preliminary study in an ICU bed space matched clinical expectations. It was found that the average 24-hour intervention is 22.0minutes/hour. The average intervention during the day time (7am-11pm) is 23.6minutes/hour, 1.4 times higher than 11pm-7am, 16.8minutes/hour. This system provides a unique approach to automatically collect and evaluate nursing interventions that can be used to evaluate patient acuity and workload demand.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.

MeSH terms
Similar publications