Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship
Background: A correct approach to recurrent urinary tract infections (rUTIs) is an important pillar of antimicrobial stewardship. We aim to define an Artificial Neural Network (ANN) for predicting the clinical efficacy of the empiric antimicrobial treatment in women with rUTIs. Methods: We extracted...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Antibiotics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6382/12/2/375 |
| _version_ | 1797622789744623616 |
|---|---|
| author | Tommaso Cai Umberto Anceschi Francesco Prata Lucia Collini Anna Brugnolli Serena Migno Michele Rizzo Giovanni Liguori Luca Gallelli Florian M. E. Wagenlehner Truls E. Bjerklund Johansen Luca Montanari Alessandro Palmieri Carlo Tascini |
| author_facet | Tommaso Cai Umberto Anceschi Francesco Prata Lucia Collini Anna Brugnolli Serena Migno Michele Rizzo Giovanni Liguori Luca Gallelli Florian M. E. Wagenlehner Truls E. Bjerklund Johansen Luca Montanari Alessandro Palmieri Carlo Tascini |
| author_sort | Tommaso Cai |
| collection | DOAJ |
| description | Background: A correct approach to recurrent urinary tract infections (rUTIs) is an important pillar of antimicrobial stewardship. We aim to define an Artificial Neural Network (ANN) for predicting the clinical efficacy of the empiric antimicrobial treatment in women with rUTIs. Methods: We extracted clinical and microbiological data from 1043 women. We trained an ANN on 725 patients and validated it on 318. Results: The ANN showed a sensitivity of 87.8% and specificity of 97.3% in predicting the clinical efficacy of empirical therapy. The previous use of fluoroquinolones (HR = 4.23; <i>p</i> = 0.008) and cephalosporins (HR = 2.81; <i>p</i> = 0.003) as well as the presence of <i>Escherichia coli</i> with resistance against cotrimoxazole (HR = 3.54; <i>p</i> = 0.001) have been identified as the most important variables affecting the ANN output decision predicting the fluoroquinolones-based therapy failure. A previous isolation of <i>Escherichia coli</i> with resistance against fosfomycin (HR = 2.67; <i>p</i> = 0.001) and amoxicillin-clavulanic acid (HR = 1.94; <i>p</i> = 0.001) seems to be the most influential variable affecting the output decision predicting the cephalosporins- and cotrimoxazole-based therapy failure. The previously mentioned <i>Escherichia coli</i> with resistance against cotrimoxazole (HR = 2.35; <i>p</i> < 0.001) and amoxicillin-clavulanic acid (HR = 3.41; <i>p</i> = 0.007) seems to be the most influential variable affecting the output decision predicting the fosfomycin-based therapy failure. Conclusions: ANNs seem to be an interesting tool to guide the antimicrobial choice in the management of rUTIs at the point of care. |
| first_indexed | 2024-03-11T09:15:17Z |
| format | Article |
| id | doaj.art-b4e2046c3f1547cf8b78b1bb81331ab9 |
| institution | Directory Open Access Journal |
| issn | 2079-6382 |
| language | English |
| last_indexed | 2024-03-11T09:15:17Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Antibiotics |
| spelling | doaj.art-b4e2046c3f1547cf8b78b1bb81331ab92023-11-16T18:44:08ZengMDPI AGAntibiotics2079-63822023-02-0112237510.3390/antibiotics12020375Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial StewardshipTommaso Cai0Umberto Anceschi1Francesco Prata2Lucia Collini3Anna Brugnolli4Serena Migno5Michele Rizzo6Giovanni Liguori7Luca Gallelli8Florian M. E. Wagenlehner9Truls E. Bjerklund Johansen10Luca Montanari11Alessandro Palmieri12Carlo Tascini13Department of Urology, Santa Chiara Regional Hospital, 38123 Trento, ItalyIRCCS “Regina Elena” National Cancer Institute, 00144 Rome, ItalyDepartment of Urology, Campus Bio-Medico University of Rome, 00128 Rome, ItalyDepartment of Microbiology, Santa Chiara Regional Hospital, 38123 Trento, ItalyCentre of Higher Education for Health Sciences, 38122 Trento, ItalyDepartment of Gynecology and Obstetrics, Santa Chiara Regional Hospital, 38123 Trento, ItalyDepartment of Urology, University of Trieste, 34127 Trieste, ItalyDepartment of Urology, University of Trieste, 34127 Trieste, ItalyDepartment of Health Science, School of Medicine, University of Catanzaro, 88100 Catanzaro, ItalyClinic for Urology, Pediatric Urology and Andrology, Justus Liebig University, 35390 Giessen, GermanyInstitute of Clinical Medicine, University of Oslo, 0315 Oslo, NorwayDepartment of Medicine (DAME), Infectious Diseases Clinic, University of Udine, 33100 Udine, ItalyDepartment of Urology, University of Naples Federico II, 80138 Naples, ItalyDepartment of Medicine (DAME), Infectious Diseases Clinic, University of Udine, 33100 Udine, ItalyBackground: A correct approach to recurrent urinary tract infections (rUTIs) is an important pillar of antimicrobial stewardship. We aim to define an Artificial Neural Network (ANN) for predicting the clinical efficacy of the empiric antimicrobial treatment in women with rUTIs. Methods: We extracted clinical and microbiological data from 1043 women. We trained an ANN on 725 patients and validated it on 318. Results: The ANN showed a sensitivity of 87.8% and specificity of 97.3% in predicting the clinical efficacy of empirical therapy. The previous use of fluoroquinolones (HR = 4.23; <i>p</i> = 0.008) and cephalosporins (HR = 2.81; <i>p</i> = 0.003) as well as the presence of <i>Escherichia coli</i> with resistance against cotrimoxazole (HR = 3.54; <i>p</i> = 0.001) have been identified as the most important variables affecting the ANN output decision predicting the fluoroquinolones-based therapy failure. A previous isolation of <i>Escherichia coli</i> with resistance against fosfomycin (HR = 2.67; <i>p</i> = 0.001) and amoxicillin-clavulanic acid (HR = 1.94; <i>p</i> = 0.001) seems to be the most influential variable affecting the output decision predicting the cephalosporins- and cotrimoxazole-based therapy failure. The previously mentioned <i>Escherichia coli</i> with resistance against cotrimoxazole (HR = 2.35; <i>p</i> < 0.001) and amoxicillin-clavulanic acid (HR = 3.41; <i>p</i> = 0.007) seems to be the most influential variable affecting the output decision predicting the fosfomycin-based therapy failure. Conclusions: ANNs seem to be an interesting tool to guide the antimicrobial choice in the management of rUTIs at the point of care.https://www.mdpi.com/2079-6382/12/2/375urinary tract infectionrecurrenceartificial intelligenceantibiotic resistance |
| spellingShingle | Tommaso Cai Umberto Anceschi Francesco Prata Lucia Collini Anna Brugnolli Serena Migno Michele Rizzo Giovanni Liguori Luca Gallelli Florian M. E. Wagenlehner Truls E. Bjerklund Johansen Luca Montanari Alessandro Palmieri Carlo Tascini Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship Antibiotics urinary tract infection recurrence artificial intelligence antibiotic resistance |
| title | Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship |
| title_full | Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship |
| title_fullStr | Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship |
| title_full_unstemmed | Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship |
| title_short | Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship |
| title_sort | artificial intelligence can guide antibiotic choice in recurrent utis and become an important aid to improve antimicrobial stewardship |
| topic | urinary tract infection recurrence artificial intelligence antibiotic resistance |
| url | https://www.mdpi.com/2079-6382/12/2/375 |
| work_keys_str_mv | AT tommasocai artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT umbertoanceschi artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT francescoprata artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT luciacollini artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT annabrugnolli artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT serenamigno artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT michelerizzo artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT giovanniliguori artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT lucagallelli artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT florianmewagenlehner artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT trulsebjerklundjohansen artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT lucamontanari artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT alessandropalmieri artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship AT carlotascini artificialintelligencecanguideantibioticchoiceinrecurrentutisandbecomeanimportantaidtoimproveantimicrobialstewardship |