04 February 2025

Patients and health systems across Australia are set to save time and resources through the rollout of an artificial intelligence-powered penicillin allergy de-labelling system.

The system examines patients’ electronic medical records (EMRs) and cross-references them against evidence-based data, to determine if they have been incorrectly labelled as allergic to penicillin.

The system was developed using research recently recognised by the Royal Australasian College of Physicians (RACP) Foundation and won a Trainee Research Award.

The de-labelling system is currently being rolled out across the public health system in South Australia, with full implementation expected to be completed by early 2025. Over the coming years, the system is expected to be implemented across Australia.

Approximately 18 to 25 per cent of Australian patients report penicillin allergies^[1], around 90 per cent of them are incorrectly labelled ^[2].

Lead project researcher Associate Professor Stephen Bacchi said that incorrect penicillin allergy labels result in increased costs and delays in treatment for patients and increase pressure on health systems.

“Adding the penicillin allergy label to a patient’s medical records can lead to several knock-on effects.

“Since penicillin may be contraindicated in some patients with allergy labels, healthcare workers must spend time sourcing alternative antibiotics.

“This can lead to patients having to spend longer at the doctor or hospital, and increased costs for both the health system and the patients.”

Incorrect penicillin allergy labels can also cause patients to develop antimicrobial resistance and receive lower-quality care ^[3].

“The current allergy labelling process relies heavily on self-reporting and assessing patients’ immediate response to the antibiotic.

“These measures aren’t always accurate. Many patients labelled as allergic to penicillin are intolerant to the antibiotic.

“While allergies and intolerances may both present unpleasant symptoms, they are very different.

“If a patient is intolerant to penicillin, they can typically still receive the antibiotic. This is not true for allergies.

“The artificial intelligence algorithm has been trained to read descriptions of allergies and intolerances and classify individual interactions based on these previous examples. It can then determine if patients may be incorrectly labelled as allergic to penicillin.

“We flag this with the patient’s hospital doctors. Following discussion with the patient, in many cases, the label is then able to be removed.

“By de-labelling incorrect penicillin allergy labels, we can help save time and resources for patients and for health systems.

“Many healthcare systems across the country are already strained, and processes like these can go a long way in ensuring that some of that burden is eased,” A/Prof Bacchi said.

[1] Trubiano, J.A., Cairns, K.A., Evans, J.A. et al. The prevalence and impact of antimicrobial allergies and adverse drug reactions at an Australian tertiary centre. BMC Infect Dis 15, 572 (2015).

[2] Marwood, J., Aguirrebarrena, G., Kerr, S., Welch, S. A., & Rimmer, J. (2017). De‐labelling self‐reported penicillin allergy within the emergency department through the use of skin tests and oral drug provocation testing. Emergency Medicine Australasia

[3] Devchand M, Trubiano JA. Penicillin allergy: a practical approach to assessment and prescribing. Aust Prescr 2019;42:192–9.