Prediction of Antibiotic Resistance in Patients With a Urinary Tract Infection : Algorithm Development and Validation
©Nevruz İlhanlı, Se Yoon Park, Jaewoong Kim, Jee An Ryu, Ahmet Yardımcı, Dukyong Yoon. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 29.02.2024..
BACKGROUND: The early prediction of antibiotic resistance in patients with a urinary tract infection (UTI) is important to guide appropriate antibiotic therapy selection.
OBJECTIVE: In this study, we aimed to predict antibiotic resistance in patients with a UTI. Additionally, we aimed to interpret the machine learning models we developed.
METHODS: The electronic medical records of patients who were admitted to Yongin Severance Hospital, South Korea were used. A total of 71 features extracted from patients' admission, diagnosis, prescription, and microbiology records were used for classification. UTI pathogens were classified as either sensitive or resistant to cephalosporin, piperacillin-tazobactam (TZP), carbapenem, trimethoprim-sulfamethoxazole (TMP-SMX), and fluoroquinolone. To analyze how each variable contributed to the machine learning model's predictions of antibiotic resistance, we used the Shapley Additive Explanations method. Finally, a prototype machine learning-based clinical decision support system was proposed to provide clinicians the resistance probabilities for each antibiotic.
RESULTS: The data set included 3535, 737, 708, 1582, and 1365 samples for cephalosporin, TZP, TMP-SMX, fluoroquinolone, and carbapenem resistance prediction models, respectively. The area under the receiver operating characteristic curve values of the random forest models were 0.777 (95% CI 0.775-0.779), 0.864 (95% CI 0.862-0.867), 0.877 (95% CI 0.874-0.880), 0.881 (95% CI 0.879-0.882), and 0.884 (95% CI 0.884-0.885) in the training set and 0.638 (95% CI 0.635-0.642), 0.630 (95% CI 0.626-0.634), 0.665 (95% CI 0.659-0.671), 0.670 (95% CI 0.666-0.673), and 0.721 (95% CI 0.718-0.724) in the test set for predicting resistance to cephalosporin, TZP, carbapenem, TMP-SMX, and fluoroquinolone, respectively. The number of previous visits, first culture after admission, chronic lower respiratory diseases, administration of drugs before infection, and exposure time to these drugs were found to be important variables for predicting antibiotic resistance.
CONCLUSIONS: The study results demonstrated the potential of machine learning to predict antibiotic resistance in patients with a UTI. Machine learning can assist clinicians in making decisions regarding the selection of appropriate antibiotic therapy in patients with a UTI.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:12 |
---|---|
Enthalten in: |
JMIR medical informatics - 12(2024) vom: 29. Feb., Seite e51326 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
İlhanlı, Nevruz [VerfasserIn] |
---|
Links: |
---|
Themen: |
Antibiotic resistance |
---|
Anmerkungen: |
Date Revised 17.03.2024 published: Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.2196/51326 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM369116372 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM369116372 | ||
003 | DE-627 | ||
005 | 20240317233125.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240301s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.2196/51326 |2 doi | |
028 | 5 | 2 | |a pubmed24n1333.xml |
035 | |a (DE-627)NLM369116372 | ||
035 | |a (NLM)38421718 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a İlhanlı, Nevruz |e verfasserin |4 aut | |
245 | 1 | 0 | |a Prediction of Antibiotic Resistance in Patients With a Urinary Tract Infection |b Algorithm Development and Validation |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 17.03.2024 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a ©Nevruz İlhanlı, Se Yoon Park, Jaewoong Kim, Jee An Ryu, Ahmet Yardımcı, Dukyong Yoon. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 29.02.2024. | ||
520 | |a BACKGROUND: The early prediction of antibiotic resistance in patients with a urinary tract infection (UTI) is important to guide appropriate antibiotic therapy selection | ||
520 | |a OBJECTIVE: In this study, we aimed to predict antibiotic resistance in patients with a UTI. Additionally, we aimed to interpret the machine learning models we developed | ||
520 | |a METHODS: The electronic medical records of patients who were admitted to Yongin Severance Hospital, South Korea were used. A total of 71 features extracted from patients' admission, diagnosis, prescription, and microbiology records were used for classification. UTI pathogens were classified as either sensitive or resistant to cephalosporin, piperacillin-tazobactam (TZP), carbapenem, trimethoprim-sulfamethoxazole (TMP-SMX), and fluoroquinolone. To analyze how each variable contributed to the machine learning model's predictions of antibiotic resistance, we used the Shapley Additive Explanations method. Finally, a prototype machine learning-based clinical decision support system was proposed to provide clinicians the resistance probabilities for each antibiotic | ||
520 | |a RESULTS: The data set included 3535, 737, 708, 1582, and 1365 samples for cephalosporin, TZP, TMP-SMX, fluoroquinolone, and carbapenem resistance prediction models, respectively. The area under the receiver operating characteristic curve values of the random forest models were 0.777 (95% CI 0.775-0.779), 0.864 (95% CI 0.862-0.867), 0.877 (95% CI 0.874-0.880), 0.881 (95% CI 0.879-0.882), and 0.884 (95% CI 0.884-0.885) in the training set and 0.638 (95% CI 0.635-0.642), 0.630 (95% CI 0.626-0.634), 0.665 (95% CI 0.659-0.671), 0.670 (95% CI 0.666-0.673), and 0.721 (95% CI 0.718-0.724) in the test set for predicting resistance to cephalosporin, TZP, carbapenem, TMP-SMX, and fluoroquinolone, respectively. The number of previous visits, first culture after admission, chronic lower respiratory diseases, administration of drugs before infection, and exposure time to these drugs were found to be important variables for predicting antibiotic resistance | ||
520 | |a CONCLUSIONS: The study results demonstrated the potential of machine learning to predict antibiotic resistance in patients with a UTI. Machine learning can assist clinicians in making decisions regarding the selection of appropriate antibiotic therapy in patients with a UTI | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a UTI | |
650 | 4 | |a antibiotic resistance | |
650 | 4 | |a decision support | |
650 | 4 | |a machine learning | |
650 | 4 | |a urinary tract infections | |
700 | 1 | |a Park, Se Yoon |e verfasserin |4 aut | |
700 | 1 | |a Kim, Jaewoong |e verfasserin |4 aut | |
700 | 1 | |a Ryu, Jee An |e verfasserin |4 aut | |
700 | 1 | |a Yardımcı, Ahmet |e verfasserin |4 aut | |
700 | 1 | |a Yoon, Dukyong |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t JMIR medical informatics |d 2013 |g 12(2024) vom: 29. Feb., Seite e51326 |w (DE-627)NLM245263071 |x 2291-9694 |7 nnns |
773 | 1 | 8 | |g volume:12 |g year:2024 |g day:29 |g month:02 |g pages:e51326 |
856 | 4 | 0 | |u http://dx.doi.org/10.2196/51326 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 12 |j 2024 |b 29 |c 02 |h e51326 |