Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections

Abstract Artificial intelligence (AI) models are promising tools for predicting antimicrobial susceptibility in gram-negative bloodstream infections (GN-BSI). Single-center study on hospitalized patients with GN-BSI, over 7-year period, aimed to predict resistance to fluoroquinolones (FQ-R), third g...

Full description

Saved in:
Bibliographic Details
Main Authors: Cecilia Bonazzetti, Ettore Rocchi, Alice Toschi, Nicolas Riccardo Derus, Claudia Sala, Renato Pascale, Matteo Rinaldi, Caterina Campoli, Zeno Adrien Igor Pasquini, Beatrice Tazza, Armando Amicucci, Milo Gatti, Simone Ambretti, Pierluigi Viale, Gastone Castellani, Maddalena Giannella
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01696-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704292325261312
author Cecilia Bonazzetti
Ettore Rocchi
Alice Toschi
Nicolas Riccardo Derus
Claudia Sala
Renato Pascale
Matteo Rinaldi
Caterina Campoli
Zeno Adrien Igor Pasquini
Beatrice Tazza
Armando Amicucci
Milo Gatti
Simone Ambretti
Pierluigi Viale
Gastone Castellani
Maddalena Giannella
author_facet Cecilia Bonazzetti
Ettore Rocchi
Alice Toschi
Nicolas Riccardo Derus
Claudia Sala
Renato Pascale
Matteo Rinaldi
Caterina Campoli
Zeno Adrien Igor Pasquini
Beatrice Tazza
Armando Amicucci
Milo Gatti
Simone Ambretti
Pierluigi Viale
Gastone Castellani
Maddalena Giannella
author_sort Cecilia Bonazzetti
collection DOAJ
description Abstract Artificial intelligence (AI) models are promising tools for predicting antimicrobial susceptibility in gram-negative bloodstream infections (GN-BSI). Single-center study on hospitalized patients with GN-BSI, over 7-year period, aimed to predict resistance to fluoroquinolones (FQ-R), third generation cephalosporins (3GC-R), beta-lactam/beta-lactamase inhibitors (BL/BLI-R) and carbapenems (C-R) was performed. Analyses were carried out within a machine learning framework, developed using the scikit-learn Python package. Overall, 2552 patients were included. Enterobacterales accounted for 85.5% of isolates, with E. coli, Klebsiella spp, and Proteus spp being most common. Distribution of resistance was FQ-R 48.6%, 3GC-R 40.1%, BL/BLI-R 29.9%, and C-R 16.9%. Models’ validation showed good performance predicting antibiotic resistance for all four resistance classes, with the best performance for C-R (AUC-ROC 0.921 ± 0.013). The developed pipeline has been made available ( https://github.com/EttoreRocchi/ResPredAI ), along with documentation for running the same workflow on a different dataset, to account for local epidemiology and clinical features.
format Article
id doaj-art-a40159d052524c8aaf547e48156635be
institution DOAJ
issn 2398-6352
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-a40159d052524c8aaf547e48156635be2025-08-20T03:16:47ZengNature Portfolionpj Digital Medicine2398-63522025-05-01811610.1038/s41746-025-01696-xArtificial Intelligence model to predict resistances in Gram-negative bloodstream infectionsCecilia Bonazzetti0Ettore Rocchi1Alice Toschi2Nicolas Riccardo Derus3Claudia Sala4Renato Pascale5Matteo Rinaldi6Caterina Campoli7Zeno Adrien Igor Pasquini8Beatrice Tazza9Armando Amicucci10Milo Gatti11Simone Ambretti12Pierluigi Viale13Gastone Castellani14Maddalena Giannella15Department of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaInfectious Diseases Unit, Department of Integrated Infectious Risk Management, IRCCS Azienda Ospedaliero-Universitaria di BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaInfectious Diseases Unit, Department of Integrated Infectious Risk Management, IRCCS Azienda Ospedaliero-Universitaria di BolognaInfectious Diseases Unit, Department of Integrated Infectious Risk Management, IRCCS Azienda Ospedaliero-Universitaria di BolognaInfectious Diseases Unit, Department of Integrated Infectious Risk Management, IRCCS Azienda Ospedaliero-Universitaria di BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaSection of Microbiology, Department of Medical and Surgical Sciences, Alma Mater Studiorum - University of BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum, University of BolognaAbstract Artificial intelligence (AI) models are promising tools for predicting antimicrobial susceptibility in gram-negative bloodstream infections (GN-BSI). Single-center study on hospitalized patients with GN-BSI, over 7-year period, aimed to predict resistance to fluoroquinolones (FQ-R), third generation cephalosporins (3GC-R), beta-lactam/beta-lactamase inhibitors (BL/BLI-R) and carbapenems (C-R) was performed. Analyses were carried out within a machine learning framework, developed using the scikit-learn Python package. Overall, 2552 patients were included. Enterobacterales accounted for 85.5% of isolates, with E. coli, Klebsiella spp, and Proteus spp being most common. Distribution of resistance was FQ-R 48.6%, 3GC-R 40.1%, BL/BLI-R 29.9%, and C-R 16.9%. Models’ validation showed good performance predicting antibiotic resistance for all four resistance classes, with the best performance for C-R (AUC-ROC 0.921 ± 0.013). The developed pipeline has been made available ( https://github.com/EttoreRocchi/ResPredAI ), along with documentation for running the same workflow on a different dataset, to account for local epidemiology and clinical features.https://doi.org/10.1038/s41746-025-01696-x
spellingShingle Cecilia Bonazzetti
Ettore Rocchi
Alice Toschi
Nicolas Riccardo Derus
Claudia Sala
Renato Pascale
Matteo Rinaldi
Caterina Campoli
Zeno Adrien Igor Pasquini
Beatrice Tazza
Armando Amicucci
Milo Gatti
Simone Ambretti
Pierluigi Viale
Gastone Castellani
Maddalena Giannella
Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections
npj Digital Medicine
title Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections
title_full Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections
title_fullStr Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections
title_full_unstemmed Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections
title_short Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections
title_sort artificial intelligence model to predict resistances in gram negative bloodstream infections
url https://doi.org/10.1038/s41746-025-01696-x
work_keys_str_mv AT ceciliabonazzetti artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT ettorerocchi artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT alicetoschi artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT nicolasriccardoderus artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT claudiasala artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT renatopascale artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT matteorinaldi artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT caterinacampoli artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT zenoadrienigorpasquini artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT beatricetazza artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT armandoamicucci artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT milogatti artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT simoneambretti artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT pierluigiviale artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT gastonecastellani artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections
AT maddalenagiannella artificialintelligencemodeltopredictresistancesingramnegativebloodstreaminfections