Artificial intelligence–enabled penicillin allergy delabelling: an implementation study

Brandon Stretton; Melinda Jiang; Joshua Kovoor; Joshua M. Inglis; Lydia Lam; Sheryn Tan; Chino Yuson; William Smith; Sepehr Shakib; Stephen Bacchi

doi:10.1111/imj.16266

Artificial intelligence–enabled penicillin allergy delabelling: an implementation study

Brandon Stretton, Melinda Jiang, Joshua Kovoor, Joshua M. Inglis, Lydia Lam, Sheryn Tan, Chino Yuson, William Smith, Sepehr Shakib, Stephen Bacchi

College of Medicine and Public Health

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

3 Citations (Scopus)

Abstract

Inaccurate penicillin allergy labels may be delabelled following evaluation. The intervention in this study was an email-based notification system regarding the appropriateness for penicillin allergy evaluation, with a view to delabelling, as identified by a deep learning artificial intelligence algorithm. Of the intervention group (n = 59), three (5.1%) individuals had their penicillin allergies delabelled, which was significantly more than the control group (0%, P = 0.002). Further research to optimise such approaches is required.

Original language	English
Pages (from-to)	2119-2122
Number of pages	4
Journal	Internal Medicine Journal
Volume	53
Issue number	11
DOIs	https://doi.org/10.1111/imj.16266
Publication status	Published - Nov 2023

Keywords

antibiotic
efficiency
intolerance
machine learning
outcomes

Access to Document

10.1111/imj.16266Licence: In Copyright

Cite this

@article{0f28a7cbd2af45a8825c0a30632a872e,

title = "Artificial intelligence–enabled penicillin allergy delabelling: an implementation study",

abstract = "Inaccurate penicillin allergy labels may be delabelled following evaluation. The intervention in this study was an email-based notification system regarding the appropriateness for penicillin allergy evaluation, with a view to delabelling, as identified by a deep learning artificial intelligence algorithm. Of the intervention group (n = 59), three (5.1%) individuals had their penicillin allergies delabelled, which was significantly more than the control group (0%, P = 0.002). Further research to optimise such approaches is required.",

keywords = "antibiotic, efficiency, intolerance, machine learning, outcomes",

author = "Brandon Stretton and Melinda Jiang and Joshua Kovoor and Inglis, {Joshua M.} and Lydia Lam and Sheryn Tan and Chino Yuson and William Smith and Sepehr Shakib and Stephen Bacchi",

year = "2023",

month = nov,

doi = "10.1111/imj.16266",

language = "English",

volume = "53",

pages = "2119--2122",

journal = "Internal Medicine Journal",

issn = "1444-0903",

publisher = "John Wiley & Sons, Inc",

number = "11",

}

TY - JOUR

T1 - Artificial intelligence–enabled penicillin allergy delabelling

T2 - an implementation study

AU - Stretton, Brandon

AU - Jiang, Melinda

AU - Kovoor, Joshua

AU - Inglis, Joshua M.

AU - Lam, Lydia

AU - Tan, Sheryn

AU - Yuson, Chino

AU - Smith, William

AU - Shakib, Sepehr

AU - Bacchi, Stephen

PY - 2023/11

Y1 - 2023/11

N2 - Inaccurate penicillin allergy labels may be delabelled following evaluation. The intervention in this study was an email-based notification system regarding the appropriateness for penicillin allergy evaluation, with a view to delabelling, as identified by a deep learning artificial intelligence algorithm. Of the intervention group (n = 59), three (5.1%) individuals had their penicillin allergies delabelled, which was significantly more than the control group (0%, P = 0.002). Further research to optimise such approaches is required.

AB - Inaccurate penicillin allergy labels may be delabelled following evaluation. The intervention in this study was an email-based notification system regarding the appropriateness for penicillin allergy evaluation, with a view to delabelling, as identified by a deep learning artificial intelligence algorithm. Of the intervention group (n = 59), three (5.1%) individuals had their penicillin allergies delabelled, which was significantly more than the control group (0%, P = 0.002). Further research to optimise such approaches is required.

KW - antibiotic

KW - efficiency

KW - intolerance

KW - machine learning

KW - outcomes

UR - http://www.scopus.com/inward/record.url?scp=85177694964&partnerID=8YFLogxK

U2 - 10.1111/imj.16266

DO - 10.1111/imj.16266

M3 - Article

C2 - 37997266

AN - SCOPUS:85177694964

SN - 1444-0903

VL - 53

SP - 2119

EP - 2122

JO - Internal Medicine Journal

JF - Internal Medicine Journal

IS - 11

ER -

Artificial intelligence–enabled penicillin allergy delabelling: an implementation study

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this