A Novel Approach to Antimicrobial Resistance: Machine Learning Predictions for Carbapenem-Resistant Klebsiella in ICUs

NCT05985057 | Completed

• 1 other identifier: GOKAEK-2023/12.32
• Study Type: observational
• Target: 289
• Locations: 1 country
• Sites: 1

Brief Summary

The aim of this study to predict carbapenem resistant Klebsiella spp. earlier in our patients monitored in our Intensive Care Unit in the future, using artificial intelligence. Patients with bloodstream infection and pneumonia caused by Klebsiella spp. will be comparatively examined in two groups, as sensitive and resistant. Resistance will be attempted to be predicted with deep machine learning.

Conditions

Carbapenem Resistant Enterobacteriaceae Infection; Artificial Intelligence; Intensive Care Unit

Outcome Measures

Primary Outcomes (1)

• Risk of Carbapenem Resistant Klebsiella Infection

  The sensitivity and specificity of a diagnostic method based on machine learning will be measured with the AUC-ROC curve (Area Under the Receiver Operating Characteristic curve)

  3 months

Study Arms (2)

Patients with carbapenem resistant Klebsiella spp. infection

Other: Artificial intelligence

Patients with carbapenem sensitive Klebsiella spp. infection

Other: Artificial intelligence

Interventions

Artificial intelligence OTHER

Prediction of carbapenem resistance via deep machine learning model

Patients with carbapenem resistant Klebsiella spp. infection; Patients with carbapenem sensitive Klebsiella spp. infection

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Patients monitored in our third-level intensive care unit between June 2017 and June 2023 will be evaluated retrospectively. Patients with pneumonia and bloodstream infection developed with Klebsiella spp. will be included in the study.

You may qualify if:

• Patients monitored in our third-level intensive care unit between June 2017 and June 2023 will be evaluated retrospectively. Patients with pneumonia and bloodstream infection developed with Klebsiella spp. will be included in the study.

You may not qualify if:

• Patients under the age of 18 have not been included in the study.
• Infections outside of the respiratory tract and bloodstream have not been included in the study.
• Patients with respiratory tract colonization and without active inflammation have also not been included.

Sponsors & Collaborators

• Kocaeli University: lead

Study Sites (1)

Kocaeli University

Kocaeli, Turkey (Türkiye)

Location

Related Publications (1)

• Alparslan V, Guler O, Inner B, Duzgun A, Baykara N, Kus A. A novel approach to antimicrobial resistance: Machine learning predictions for carbapenem-resistant Klebsiella in intensive care units. Int J Med Inform. 2025 Mar;195:105751. doi: 10.1016/j.ijmedinf.2024.105751. Epub 2024 Dec 7.

  PMID: 39674007 DERIVED

Related Links

• Using Machine Learning to Predict Antimicrobial Resistance of Acinetobacter Baumannii, Klebsiella Pneumoniae and Pseudomonas Aeruginosa Strains

MeSH Terms

Interventions

Artificial Intelligence

Intervention Hierarchy (Ancestors)

Algorithms; Mathematical Concepts

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Medical Doctor

Study Record Dates

• First Submitted: August 2, 2023
• First Posted: August 14, 2023
• Study Start: December 1, 2023
• Primary Completion: June 22, 2024
• Study Completion: June 30, 2024
• Last Updated: April 9, 2025

Record last verified: 2025-04

Locations

TU (1)