Document Type

Dissertation

Date of Degree

Summer 2015

Degree Name

PhD (Doctor of Philosophy)

Degree In

Computer Science

First Advisor

Ted Herman

Abstract

Hand hygiene is an important part of preventing disease transmission in the hospital. Due to this importance, electronic systems have been proposed for automatically monitoring healthcare worker adherence to hand hygiene guidelines. However, these systems can miss certain hand hygiene events and do not include quality metrics such as duration or technique. We propose that hand hygiene duration and technique can be automatically inferred using the motion of the wrist. This work presents a system utilizing wrist-based 3-dimensional accelerometers and orientation sensors, signal processing (including novel features), and machine learning to detect healthcare worker hand hygiene and report quality metrics such as duration and whether the healthcare worker used recommended rubbing technique. We validated the system using several different types of data sets with up to 116 healthcare workers and activities ranging from synthetically generated hand hygiene movements to observation of healthcare worker hand hygiene on the hospital floor. In these experiments our system detects up to 98.4% of hand hygiene events, detects hand hygiene technique with up to 92.1% accuracy, and accurately estimates hand hygiene duration.

Keywords

Activity Recognition, Hand Hygiene, Healthcare, Machine Learning, Sensors, Signal Processing

Pages

xiii, 83 pages

Bibliography

Includes bibliographical references (pages 79-83).

Copyright

Copyright 2015 Valerie Galluzzi

Share

COinS