A step forward in the diagnosis of urinary tract infections: from machine learning to clinical practice
Computational and Structural Biotechnology Journal · 2024-12 · 24 · 533-541
DOI: 10.1016/j.csbj.2024.07.018 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 07.08.2024. Verfasst von Emilio Flores und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Laboratory, Hospital Universitario San Juan de Alicante, Carretera de Valencia, 03550 San Juan de Alicante, Alicante, Spain. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Abbott Germany.
Abstract (Originalsprache)
Objectives
Urinary tract infections (UTIs) are common infections within the Emergency Department (ED), causing increased laboratory workloads and unnecessary antibiotics prescriptions. The aim of this study was to improve UTI diagnostics in clinical practice by application of machine learning (ML) models for real-time UTI prediction.
Methods
In a retrospective study, patient information and outcomes from Emergency Department patients, with positive and negative culture results, were used to design models – ‘Random Forest’ and ‘Neural Network’ – for the prediction of UTIs. The performance of these predictive models was validated in a cross-sectional study. In a quasi-experimental study, the impact of UTI risk assessment was investigated by evaluating changes in the behaviour of clinicians, measuring changes in antibiotic prescriptions and urine culture requests.
Results
First, we trained and tested two different predictive models with 8692 cases. Second, we investigated the performance of the predictive models in clinical practice with 962 cases (Area under the curve was between 0.81 to 0.88). The best performance was the combination of both models. Finally, the assessment of the risk for UTIs was implemented into clinical practice and allowed for the reduction of unnecessary urine cultures and antibiotic prescriptions for patients with a low risk of UTI, as well as targeted diagnostics and treatment for patients with a high risk of UTI.
Conclusion
The combination of modern urinalysis diagnostic technologies with digital health solutions can help to further improve UTI diagnostics with positive impact on laboratory workloads and antimicrobial stewardship.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Laboratory, Hospital Universitario San Juan de Alicante, Carretera de Valencia, 03550 San Juan de Alicante, Alicante, Spain.
- Department of Clinical Medicine, Universidad Miguel Hernandez, Elche, Spain.
- Department of Emergency, Hospital Universitario San Juan de Alicante, Carretera de Valencia, 03550 San Juan de Alicante, Alicante, Spain.
Förderung
- Abbott Germany
Zitieren
APA
Flores, E., Martínez-Racaj, L., Blasco, Á., Diaz, E., Esteban, P., López-Garrigós, M., & Salinas, M. (2024). A step forward in the diagnosis of urinary tract infections: from machine learning to clinical practice. Computational and Structural Biotechnology Journal, 24, 533-541. https://doi.org/10.1016/j.csbj.2024.07.018
Vancouver
Flores E, Martínez-Racaj L, Blasco Á, Diaz E, Esteban P, López-Garrigós M, et al. A step forward in the diagnosis of urinary tract infections: from machine learning to clinical practice. Computational and Structural Biotechnology Journal. 2024;24:533-541. doi:10.1016/j.csbj.2024.07.018
BibTeX
@article{Flores2024,
author = {Flores, Emilio and Martínez-Racaj, Laura and Blasco, Álvaro and Diaz, Elena and Esteban, Patricia and López-Garrigós, Maite and Salinas, María},
title = {A step forward in the diagnosis of urinary tract infections: from machine learning to clinical practice},
journal = {Computational and Structural Biotechnology Journal},
year = {2024},
volume = {24},
pages = {533--541},
doi = {10.1016/j.csbj.2024.07.018}
}
EUVIMED