Appropriate Use of Blood Cultures in the Emergency Department Through Machine Learning (ABC)

Appropriate Use of Blood Cultures in the Emergency Department Through Machine Learning: a Randomized Controlled Trial

The goal of this clinical trial is to study whether the use of our blood culture prediction tool is non-inferior to current practice and if it can improve certain outcomes in all adult patients presenting to the emergency department with a clinical indication for a blood culture analysis (according to the treating physician). The primary endpoint is 30-day mortality. Key secondary outcomes are:

• hospital admission rates
• in-hospital mortality
• hospital length-of-stay. In the intervention group, the physician will follow the advice of our blood culture prediction tool.

In the comparison group all patients will undergo a blood culture analysis.

Study Overview

• Status: Not yet recruiting
• Conditions: Artificial Intelligence; Machine Learning; Randomized Controlled Trial; Emergency Service, Hospital; Microbiology
• Intervention / Treatment: Device: Blood culture prediction tool

Detailed Description

Rationale: The overuse of blood cultures in emergency departments leads to low yields and high numbers of contaminated cultures, which is associated with increased diagnostics, antibiotic usage, prolonged hospitalisation, and mortality. Ideally, blood cultures would only be performed in patients with a high risk for a positive culture. The investigators have developed a machine learning model to predict the outcome of blood cultures in the ED. Retrospective and prospective validation of the tool in various settings show that it can be used to reduce the number of blood culture analyses by at least 30% and help avoid the hidden costs of contaminated cultures.

Objective: This study aims to investigate whether the use of our blood culture prediction tool is non-inferior to current practice and if it can improve certain outcomes.

Study design: A randomized controlled non-inferiority trial. Study population: All adult patients presenting to the emergency department with a clinical indication for a blood culture analysis (according to the treating physician).

Intervention: In the control group, all patients will undergo a blood culture analysis. In the intervention group, the physician will follow the advice of our blood culture prediction tool. If the chance of a positive blood culture is < 5%, the blood culture analysis will be cancelled and the sample destroyed. If the change of a positive blood culture is > 5%, the blood culture analysis will be performed as usual.

Main study parameters/endpoints: The primary endpoint is 30-day mortality, for which the investigators aim to show non-inferiority. Key secondary outcomes, for which the investigators also aim to show non-inferiority, are hospital admission rates, in-hospital mortality, and hospital length-of-stay.

• Study Type: Interventional
• Enrollment (Estimated): 7584
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Prabath WB Nanayakkara, MD, PhD; Phone Number: +31204444444; Email: p.nanayakkara@amsterdamumc.nl
• Study Contact Backup: Name: Sheena C Bhagirath, MD; Phone Number: +31204444444; Email: s.bhagirath@amsterdamumc.nl

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Age >= 18 years
• Have a clinical indication for a blood culture analysis (according to the treating physician)
• Have sufficient data recorded (laboratory results and vital sign measurements) for a prediction to be made (at least 20% of the needed parameters)

Exclusion Criteria:

• Central Venous Line (CVL) or Peripherally Inserted Central Catheter (PICC) in situ
• Neutrophil count < 0.5 * 109/L
• Candidemia or S. aureus bacteraemia in the past 3 months.
• Most likely diagnosis of endocarditis/spondylodiscitis/infected prosthetic material

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Blood culture taken based on machine learning tool	Device: Blood culture prediction tool; Machine learning based predicition tool
No Intervention: Blood culture taken based on the treating physician

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
30-day mortality	30 days

Secondary Outcome Measures

Outcome Measure	Time Frame
hospital admission rates	1 day
in-hospital mortality	90 days
hospital length-of-stay	90 days

Other Outcome Measures

Outcome Measure	Time Frame
30-day readmission rates	30 days
90 day mortality	90 days
Length of stay in the ED in hours	2 days
Percentage of blood cultures avoided in the intervention group	90 days
Number of blood cultures on each day of hospital stay (in admitted patients)	90 days
Percentage of positive blood cultures in each group	90 days
Total number of laboratory- and microbiology tests in the ED	2 days
Total number of laboratory- and microbiology test on each day of hospital stay (in admitted patients)	90 days
Percentage of patients receiving antibiotics in the ED	2 days
Duration of antibiotic therapy	90 days
Types of antibiotics given in the ED	2 days
Model performance (AUC) during the trial	3 years
Model performance in subgroup of Immunocompromised patients (triple immunosuppressive therapy)	3 years
Model performance in subgroup of transplanted patients	3 years

Collaborators and Investigators

• Sponsor: Amsterdam UMC, location VUmc

Publications and helpful links

General Publications

• Boerman AW, Schinkel M, Meijerink L, van den Ende ES, Pladet LC, Scholtemeijer MG, Zeeuw J, van der Zaag AY, Minderhoud TC, Elbers PWG, Wiersinga WJ, de Jonge R, Kramer MH, Nanayakkara PWB. Using machine learning to predict blood culture outcomes in the emergency department: a single-centre, retrospective, observational study. BMJ Open. 2022 Jan 4;12(1):e053332. doi: 10.1136/bmjopen-2021-053332.
• Schinkel M, Boerman AW, Bennis FC, Minderhoud TC, Lie M, Peters-Sengers H, Holleman F, Schade RP, de Jonge R, Wiersinga WJ, Nanayakkara PWB. Diagnostic stewardship for blood cultures in the emergency department: A multicenter validation and prospective evaluation of a machine learning prediction tool. EBioMedicine. 2022 Aug;82:104176. doi: 10.1016/j.ebiom.2022.104176. Epub 2022 Jul 16.

Study record dates

Study Major Dates

• Study Start (Estimated): January 1, 2024
• Primary Completion (Estimated): January 1, 2027
• Study Completion (Estimated): July 1, 2027

Study Registration Dates

• First Submitted: October 12, 2023
• First Submitted That Met QC Criteria: November 30, 2023
• First Posted (Actual): December 11, 2023

Study Record Updates

• Last Update Posted (Actual): December 11, 2023
• Last Update Submitted That Met QC Criteria: November 30, 2023
• Last Verified: November 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Pathologic Processes; Disease Attributes; Emergencies
• Other Study ID Numbers: NL81971.000.22

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: : Participant data underlying the results of this study can be shared. The data can be requested following publication of this work. The data can be shared with researchers who provide a methodologically sound proposal, which is allowed under our local privacy regulations. Proposals should be directed to the corresponding author and requestors will need to sign a data access agreement.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No