Automatic Hand Hygiene Monitoring Systems for Infection Prevention in Healthcare Settings: A Short Review of Literature
Keywords:
Electronic monitoring, Hand hygiene compli- ance, Healthcare-associated infections, Infection prevention and controlAbstract
Healthcare-associated infections (HAIs) remain a
global challenge, with significant morbidity, mortality, and eco-
nomic implications. Improving Hand Hygiene (HH) compliance
is one of the most effective strategies for reducing HAIs. How-
ever, compliance rates remain suboptimal. Electronic Hand Hy-
giene Monitoring Systems (EHHMS) have emerged as a prom-
ising solution to address this challenge by providing real-time
feedback and promoting behavior change among healthcare
workers. This narrative review examines the methodologies
used in EHHMS, classifying them into four key categories: rule-
based systems, signal processing, machine learning, and data fu-
sion approaches. Rule-based systems, though widely used, are
limited by their static nature and inability to adapt to dynamic
healthcare environments. Signal processing methods focus on
localizing hand hygiene events, while machine learning (ML)
approaches mostly focused on HH quality. Data fusion tech-
niques improve monitoring by integrating inputs from multiple
sensors. Despite their potential, EHHMS face challenges in ac-
curacy, intrusiveness, and integration into clinical workflows.
This review highlights the potential role of ML in overcoming
these limitations. By addressing current barriers, EHHMS can
play a crucial role in enhancing HH practices and reducing HAI
rates, ultimately improving patient safety and healthcare qual-
ity.