Artificial intelligence (AI) use for personal protective equipment training, remediation and education in healthcare

Veronica Preda; Zehurn Ong; Chandana Wijeweera; Terry Carney; Robyn Clay-Williams; Denuka Kankanamge; Tamara Preda; Ionides Kopsidas; Michael Keith Wilson

doi:10.1016/j.ajic.2025.03.020

Artificial intelligence (AI) use for personal protective equipment training, remediation and education in healthcare

Veronica Preda, Zehurn Ong, Chandana Wijeweera, Terry Carney, Robyn Clay-Williams, Denuka Kankanamge, Tamara Preda, Ionides Kopsidas, Michael Keith Wilson

Research output: Contribution to journal › Article › peer-review

Abstract

BACKGROUND: Personal protective equipment (PPE) is a first-line transmission-based precaution for reducing the spread of nosocomial infections between health care workers (HCWs), patients, and staff. The COVID-19 pandemic highlighted a problematic skill gap in effective PPE donning/doffing.

METHODS: We performed a single-center, mixed-methods, prospective cohort study of 293 HCWs in Sydney, Australia. Participants were assessed using SXR AI-PPE, an artificial intelligence (AI) system that autonomously evaluates donning/doffing of PPE while providing real-time feedback on user technique.

RESULTS: Longitudinal results showed improved accuracy rates for correct donning/doffing after each guided session conducted at 3-monthly intervals, with a 100% accuracy rate for correct use of PPE after 2 guided sessions. These improvements were maintained with 3-monthly training sessions.

CONCLUSIONS: The SXR AI-PPE platform is a comprehensive tool capable of training PPE donning/doffing by HCWs in real time with implications for reducing PPE contamination and risk of nosocomial infections.

Original language	English
Number of pages	7
Journal	American Journal of Infection Control
DOIs	https://doi.org/10.1016/j.ajic.2025.03.020
Publication status	Accepted/In press - 25 Mar 2025

Bibliographical note

Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

Infection prevention
Nosocomial infections
Personal Protective Equipment
Personal protective equipment

Access to Document

10.1016/j.ajic.2025.03.020Licence: CC BY

Cite this

@article{9e152013eb1f4e71beb9fe511b9ea24c,

title = "Artificial intelligence (AI) use for personal protective equipment training, remediation and education in healthcare",

abstract = "BACKGROUND: Personal protective equipment (PPE) is a first-line transmission-based precaution for reducing the spread of nosocomial infections between health care workers (HCWs), patients, and staff. The COVID-19 pandemic highlighted a problematic skill gap in effective PPE donning/doffing.METHODS: We performed a single-center, mixed-methods, prospective cohort study of 293 HCWs in Sydney, Australia. Participants were assessed using SXR AI-PPE, an artificial intelligence (AI) system that autonomously evaluates donning/doffing of PPE while providing real-time feedback on user technique.RESULTS: Longitudinal results showed improved accuracy rates for correct donning/doffing after each guided session conducted at 3-monthly intervals, with a 100% accuracy rate for correct use of PPE after 2 guided sessions. These improvements were maintained with 3-monthly training sessions.CONCLUSIONS: The SXR AI-PPE platform is a comprehensive tool capable of training PPE donning/doffing by HCWs in real time with implications for reducing PPE contamination and risk of nosocomial infections.",

keywords = "Infection prevention, Nosocomial infections, Personal Protective Equipment, Personal protective equipment",

author = "Veronica Preda and Zehurn Ong and Chandana Wijeweera and Terry Carney and Robyn Clay-Williams and Denuka Kankanamge and Tamara Preda and Ionides Kopsidas and Wilson, {Michael Keith}",

note = "Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",

year = "2025",

month = mar,

day = "25",

doi = "10.1016/j.ajic.2025.03.020",

language = "English",

journal = "American Journal of Infection Control",

issn = "0196-6553",

publisher = "Mosby Elsevier",

}

TY - JOUR

T1 - Artificial intelligence (AI) use for personal protective equipment training, remediation and education in healthcare

AU - Preda, Veronica

AU - Ong, Zehurn

AU - Wijeweera, Chandana

AU - Carney, Terry

AU - Clay-Williams, Robyn

AU - Kankanamge, Denuka

AU - Preda, Tamara

AU - Kopsidas, Ionides

AU - Wilson, Michael Keith

N1 - Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2025/3/25

Y1 - 2025/3/25

N2 - BACKGROUND: Personal protective equipment (PPE) is a first-line transmission-based precaution for reducing the spread of nosocomial infections between health care workers (HCWs), patients, and staff. The COVID-19 pandemic highlighted a problematic skill gap in effective PPE donning/doffing.METHODS: We performed a single-center, mixed-methods, prospective cohort study of 293 HCWs in Sydney, Australia. Participants were assessed using SXR AI-PPE, an artificial intelligence (AI) system that autonomously evaluates donning/doffing of PPE while providing real-time feedback on user technique.RESULTS: Longitudinal results showed improved accuracy rates for correct donning/doffing after each guided session conducted at 3-monthly intervals, with a 100% accuracy rate for correct use of PPE after 2 guided sessions. These improvements were maintained with 3-monthly training sessions.CONCLUSIONS: The SXR AI-PPE platform is a comprehensive tool capable of training PPE donning/doffing by HCWs in real time with implications for reducing PPE contamination and risk of nosocomial infections.

AB - BACKGROUND: Personal protective equipment (PPE) is a first-line transmission-based precaution for reducing the spread of nosocomial infections between health care workers (HCWs), patients, and staff. The COVID-19 pandemic highlighted a problematic skill gap in effective PPE donning/doffing.METHODS: We performed a single-center, mixed-methods, prospective cohort study of 293 HCWs in Sydney, Australia. Participants were assessed using SXR AI-PPE, an artificial intelligence (AI) system that autonomously evaluates donning/doffing of PPE while providing real-time feedback on user technique.RESULTS: Longitudinal results showed improved accuracy rates for correct donning/doffing after each guided session conducted at 3-monthly intervals, with a 100% accuracy rate for correct use of PPE after 2 guided sessions. These improvements were maintained with 3-monthly training sessions.CONCLUSIONS: The SXR AI-PPE platform is a comprehensive tool capable of training PPE donning/doffing by HCWs in real time with implications for reducing PPE contamination and risk of nosocomial infections.

KW - Infection prevention

KW - Nosocomial infections

KW - Personal Protective Equipment

KW - Personal protective equipment

UR - http://www.scopus.com/inward/record.url?scp=105002305969&partnerID=8YFLogxK

U2 - 10.1016/j.ajic.2025.03.020

DO - 10.1016/j.ajic.2025.03.020

M3 - Article

C2 - 40147733

SN - 0196-6553

JO - American Journal of Infection Control

JF - American Journal of Infection Control

ER -

Artificial intelligence (AI) use for personal protective equipment training, remediation and education in healthcare

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Cite this