Performance of clinical decision aids (CDA) for the care of young febrile infants: a multicentre prospective cohort study conducted in the UK and Ireland

Abstract

Background: Between 1% and 4% of febrile infants, aged from birth to 90 days of age, presenting to hospital will be diagnosed with an invasive bacterial infection (IBI). Traditional teaching has advocated a treat all approach but more recently a number of clinical decision aids (CDA) have been developed to classify febrile infants into lower and higher risk cohorts, with lower risk infants suitable for management without immediate parenteral antibiotics and lumbar puncture. The aim of this study was to apply these CDA to a UK and Irish cohort.

Methods: This was a prospective multicentre cohort study of febrile infants presenting to 35 Paediatric Emergency Research in the UK and Ireland (PERUKI) sites between the 6th July 2022 and the 31st August 2023. All infants received standard care as per local policy. IBI was defined as growth of bacterial pathogen in blood or cerebrospinal fluid. The performance of the following CDAs were assessed, National Institute for Health and Care Excellence (NICE) guidelines NG143 (Fever under 5 years), British Society Antimicrobial Chemotherapy (BSAC), Aronson rule and American Academy of Pediatrics (AAP) CDA. A cost comparison of each CDA against a treat all approach was conducted. Trial registration: NCT05259683.

Findings: 1821 were included in the final analysis. The median age was 46 days (IQR: 30-64 days), with 1108 (61%) being male. Of the 1821 infants, 67 (3.7%) had IBI. The AAP and BSAC CDAs were the most sensitive at 0.99 (95% CI 0.92-1.0) for both with specificities of 0.23 (95% CI 0.21-0.25) and 0.20 (95% CI 0.18-0.22) respectively. The NICE NG143 and Aronson CDA were the most specific CDAs with values of 0.27 (95% CI 0.25-0.30) and 0.30 (95% CI 0.28-0.32) respectively, but their sensitivity was lower. The AAP CDA performed equally well with either procalcitonin (PCT) or C-reactive protein (CRP) as the biomarker of choice. Of the 1821 infants, 77% were admitted, 14% were discharged and 9% were ambulated. All CDAs were cost saving for hospital services when compared to a treat all approach, with the lowest mean cost per patient estimated for Aronson (£1171; bootstrap 95% CI £1129-£1214) and NICE NG143 CDA (£1218; bootstrap 95% CI £1174-£1263).

Interpretation: The AAP and BSAC CDAs are highly sensitive at excluding IBI, with a cost saving to hospital services when compared to a treat all approach. The substitution of CRP for PCT made no difference to the performance of the AAP CDA in this cohort and was more costly.

Funding: The Febrile Infant Diagnostic Assessment and Outcome (FIDO) study is funded by Royal College of Emergency Medicine Doctoral Fellowship (RCEM 02/03/2021). Procalcitonin analysis was supported by the Public Health Agency Northen Ireland Grant (HSC R&D-COM/5745/22). The funders played no part in the conception or design of this study.

Keywords: Clinical decision aid; Febrile infant; Invasive bacterial infection.

Fig. 1

Flow chart of participant inclusion in the FIDO study. CDA, Clinical decision aid; ED, Emergency department; FIDO, Febrile Infant Diagnostic Assessment and Outcome; IBI, Invasive bacterial infection; LOS, Length of stay; PCT, Procalcitonin; SBI, Serious bacterial infection.

Fig. 2

Cost profile of each CDA versus a treat all approach. AAP, American Academy of Pediatrics; BSAC, British Society for Antimicrobial Chemotherapy; CDA, Clinical decision aid; CRP, C-reactive protein; ED, Emergency department; NICE, National Institute for Health and Care Excellence; NICE NG143, Fever under 5 guideline; Treat all, NICE NG51 (Sepsis guideline).