Rapid extended-spectrum beta-lactamase-confirmation by using a machine learning model directly on routine automated susceptibility testing results
ObjectivesPhenotypical Extended Spectrum β-Lactamase (ESBL)-production is commonly determined using the combination disk diffusion test or gradient test. This requires overnight incubation, prolonging time-to-detection and increasing duration of empirical treatment for patients with infections cause...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-04-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2025.1582703/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850142839519838208 |
|---|---|
| author | Y. El Ghouch Y. El Ghouch M. C. Schut K. C. E. Sigaloff W. Altorf-Van Der Kuil J. M. Prins R. P. Schade R. P. Schade the ISIS-AR study group J.W.T. Cohen Stuart D.C. Melles K. van Dijk A. Alzubaidy M. Scholing S.D. Kuil G.J. Blaauw W. Altorf van der Kuil S.M. Bierman S.C. de Greeff S.R. Groenendijk R. Hertroys L. Kruithof I.M. Nauta D.W. Notermans J. Polman W.J. van den Reek A.F. Schoffelen F. Velthuis C.C.H. Wielders B.J. de Wit R.E. Zoetigheid W. van den Bijllaardt E.M. Kraan M.B. Haeseker J.M. da Silva E. de Jong B. Maraha A.J. van Griethuysen B.B. Wintermans M.J.C.A. van Trijp A.E. Muller M. Wong A. Ott E. Bathoorn M. Lokate J. Sinnige D.C. Melles L. Bank N.H. Renders J.W. Dorigo-Zetsma L.J. Bakker W. Ang K. Waar M.T. van der Beek M.A. Leversteijn-van Hall S.P. van Mens E. Schaftenaar M.H. Nabuurs-Franssen I. Maat P.D.J. Sturm B.M.W. Diederen L.G.M. Bode D.S.Y. Ong M. van Rijn S. Dinant M. den Reijer D.W. van Dam E.I.G.B. de Brauwer R.G. Bentvelsen A.L.M. Vlek M. de Graaf A. Troelstra K.B. Gast M.P.A. van Meer J. de Vries J.D. Machiels |
| author_facet | Y. El Ghouch Y. El Ghouch M. C. Schut K. C. E. Sigaloff W. Altorf-Van Der Kuil J. M. Prins R. P. Schade R. P. Schade the ISIS-AR study group J.W.T. Cohen Stuart D.C. Melles K. van Dijk A. Alzubaidy M. Scholing S.D. Kuil G.J. Blaauw W. Altorf van der Kuil S.M. Bierman S.C. de Greeff S.R. Groenendijk R. Hertroys L. Kruithof I.M. Nauta D.W. Notermans J. Polman W.J. van den Reek A.F. Schoffelen F. Velthuis C.C.H. Wielders B.J. de Wit R.E. Zoetigheid W. van den Bijllaardt E.M. Kraan M.B. Haeseker J.M. da Silva E. de Jong B. Maraha A.J. van Griethuysen B.B. Wintermans M.J.C.A. van Trijp A.E. Muller M. Wong A. Ott E. Bathoorn M. Lokate J. Sinnige D.C. Melles L. Bank N.H. Renders J.W. Dorigo-Zetsma L.J. Bakker W. Ang K. Waar M.T. van der Beek M.A. Leversteijn-van Hall S.P. van Mens E. Schaftenaar M.H. Nabuurs-Franssen I. Maat P.D.J. Sturm B.M.W. Diederen L.G.M. Bode D.S.Y. Ong M. van Rijn S. Dinant M. den Reijer D.W. van Dam E.I.G.B. de Brauwer R.G. Bentvelsen A.L.M. Vlek M. de Graaf A. Troelstra K.B. Gast M.P.A. van Meer J. de Vries J.D. Machiels |
| author_sort | Y. El Ghouch |
| collection | DOAJ |
| description | ObjectivesPhenotypical Extended Spectrum β-Lactamase (ESBL)-production is commonly determined using the combination disk diffusion test or gradient test. This requires overnight incubation, prolonging time-to-detection and increasing duration of empirical treatment for patients with infections caused by gram-negative bacteria. To achieve instant confirmation without incubation, we developed a machine learning (ML)-model that predicts phenotypic ESBL-confirmation using Minimum Inhibitory Concentrations from routine automated antimicrobial susceptibility testing (AST)-results.MethodsData from the Dutch national laboratory-based surveillance system ISIS-AR collected between 2013 and 2022 from 49 laboratories were used: 178,044 isolates of E. coli (141,576), K. pneumoniae (33,088), and P. mirabilis (3,380) that exhibited resistance to cefotaxime and/or ceftazidime, and had available results of phenotypical ESBL-confirmation testing. We evaluated Logistic Regression, Random Forest and XGBoost models and calculated SHAP-values (SHapley Additive exPlanations) to identify most contributing features. We externally validated models using 5,996 isolates collected in Amsterdam University Medical Centres’ between 2013 and 2022.ResultsXGBoost achieved an AUROC (Area Under Receiver Operating Characteristics) of 0.97, a sensitivity of 0.89 and an accuracy of 0.93. The most contributing features were the antibiotics cefotaxime, cefoxitin and trimethoprim for E. coli and K. pneumoniae, and cefuroxime, imipenem and cefotaxime for P. mirabilis. External validation yielded AUROCs of 0.93 (E. coli), 0.89 (K. pneumoniae) and 0.93 (P. mirabilis).ConclusionML-models for prediction of ESBL-production using routine AST-system data achieved high performances. Implementing these models in laboratory practice could shorten time-to-detection. Once deployed, this approach could facilitate widespread screening for phenotypic ESBL-production. |
| format | Article |
| id | doaj-art-847feb182c134d15b1cb4497b1538036 |
| institution | OA Journals |
| issn | 1664-302X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj-art-847feb182c134d15b1cb4497b15380362025-08-20T02:28:55ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2025-04-011610.3389/fmicb.2025.15827031582703Rapid extended-spectrum beta-lactamase-confirmation by using a machine learning model directly on routine automated susceptibility testing resultsY. El Ghouch0Y. El Ghouch1M. C. Schut2K. C. E. Sigaloff3W. Altorf-Van Der Kuil4J. M. Prins5R. P. Schade6R. P. Schade7the ISIS-AR study groupJ.W.T. Cohen StuartD.C. MellesK. van DijkA. AlzubaidyM. ScholingS.D. KuilG.J. BlaauwW. Altorf van der KuilS.M. BiermanS.C. de GreeffS.R. GroenendijkR. HertroysL. KruithofI.M. NautaD.W. NotermansJ. PolmanW.J. van den ReekA.F. SchoffelenF. VelthuisC.C.H. WieldersB.J. de WitR.E. ZoetigheidW. van den BijllaardtE.M. KraanM.B. HaesekerJ.M. da SilvaE. de JongB. MarahaA.J. van GriethuysenB.B. WintermansM.J.C.A. van TrijpA.E. MullerM. WongA. OttE. BathoornM. LokateJ. SinnigeD.C. MellesL. BankN.H. RendersJ.W. Dorigo-ZetsmaL.J. BakkerW. AngK. WaarM.T. van der BeekM.A. Leversteijn-van HallS.P. van MensE. SchaftenaarM.H. Nabuurs-FranssenI. MaatP.D.J. SturmB.M.W. DiederenL.G.M. BodeD.S.Y. OngM. van RijnS. DinantM. den ReijerD.W. van DamE.I.G.B. de BrauwerR.G. BentvelsenA.L.M. VlekM. de GraafA. TroelstraK.B. GastM.P.A. van MeerJ. de VriesJ.D. MachielsDepartment of Medical Microbiology and Infection Prevention, Amsterdam UMC, Amsterdam, NetherlandsDepartment of Internal Medicine, Amsterdam UMC, Amsterdam, NetherlandsDepartment of Laboratory Medicine, Amsterdam UMC, Amsterdam, NetherlandsDepartment of Internal Medicine, Amsterdam UMC, Amsterdam, NetherlandsCentre for Infectious Disease Control (CIb), National Institute for Public Health and the Environment (RIVM), Bilthoven, NetherlandsDepartment of Internal Medicine, Amsterdam UMC, Amsterdam, NetherlandsDepartment of Medical Microbiology and Infection Prevention, Amsterdam UMC, Amsterdam, NetherlandsDepartment of Internal Medicine, Amsterdam UMC, Amsterdam, NetherlandsObjectivesPhenotypical Extended Spectrum β-Lactamase (ESBL)-production is commonly determined using the combination disk diffusion test or gradient test. This requires overnight incubation, prolonging time-to-detection and increasing duration of empirical treatment for patients with infections caused by gram-negative bacteria. To achieve instant confirmation without incubation, we developed a machine learning (ML)-model that predicts phenotypic ESBL-confirmation using Minimum Inhibitory Concentrations from routine automated antimicrobial susceptibility testing (AST)-results.MethodsData from the Dutch national laboratory-based surveillance system ISIS-AR collected between 2013 and 2022 from 49 laboratories were used: 178,044 isolates of E. coli (141,576), K. pneumoniae (33,088), and P. mirabilis (3,380) that exhibited resistance to cefotaxime and/or ceftazidime, and had available results of phenotypical ESBL-confirmation testing. We evaluated Logistic Regression, Random Forest and XGBoost models and calculated SHAP-values (SHapley Additive exPlanations) to identify most contributing features. We externally validated models using 5,996 isolates collected in Amsterdam University Medical Centres’ between 2013 and 2022.ResultsXGBoost achieved an AUROC (Area Under Receiver Operating Characteristics) of 0.97, a sensitivity of 0.89 and an accuracy of 0.93. The most contributing features were the antibiotics cefotaxime, cefoxitin and trimethoprim for E. coli and K. pneumoniae, and cefuroxime, imipenem and cefotaxime for P. mirabilis. External validation yielded AUROCs of 0.93 (E. coli), 0.89 (K. pneumoniae) and 0.93 (P. mirabilis).ConclusionML-models for prediction of ESBL-production using routine AST-system data achieved high performances. Implementing these models in laboratory practice could shorten time-to-detection. Once deployed, this approach could facilitate widespread screening for phenotypic ESBL-production.https://www.frontiersin.org/articles/10.3389/fmicb.2025.1582703/fullESBLmachine learningantimicrobial resistancebacteriasurveillance |
| spellingShingle | Y. El Ghouch Y. El Ghouch M. C. Schut K. C. E. Sigaloff W. Altorf-Van Der Kuil J. M. Prins R. P. Schade R. P. Schade the ISIS-AR study group J.W.T. Cohen Stuart D.C. Melles K. van Dijk A. Alzubaidy M. Scholing S.D. Kuil G.J. Blaauw W. Altorf van der Kuil S.M. Bierman S.C. de Greeff S.R. Groenendijk R. Hertroys L. Kruithof I.M. Nauta D.W. Notermans J. Polman W.J. van den Reek A.F. Schoffelen F. Velthuis C.C.H. Wielders B.J. de Wit R.E. Zoetigheid W. van den Bijllaardt E.M. Kraan M.B. Haeseker J.M. da Silva E. de Jong B. Maraha A.J. van Griethuysen B.B. Wintermans M.J.C.A. van Trijp A.E. Muller M. Wong A. Ott E. Bathoorn M. Lokate J. Sinnige D.C. Melles L. Bank N.H. Renders J.W. Dorigo-Zetsma L.J. Bakker W. Ang K. Waar M.T. van der Beek M.A. Leversteijn-van Hall S.P. van Mens E. Schaftenaar M.H. Nabuurs-Franssen I. Maat P.D.J. Sturm B.M.W. Diederen L.G.M. Bode D.S.Y. Ong M. van Rijn S. Dinant M. den Reijer D.W. van Dam E.I.G.B. de Brauwer R.G. Bentvelsen A.L.M. Vlek M. de Graaf A. Troelstra K.B. Gast M.P.A. van Meer J. de Vries J.D. Machiels Rapid extended-spectrum beta-lactamase-confirmation by using a machine learning model directly on routine automated susceptibility testing results Frontiers in Microbiology ESBL machine learning antimicrobial resistance bacteria surveillance |
| title | Rapid extended-spectrum beta-lactamase-confirmation by using a machine learning model directly on routine automated susceptibility testing results |
| title_full | Rapid extended-spectrum beta-lactamase-confirmation by using a machine learning model directly on routine automated susceptibility testing results |
| title_fullStr | Rapid extended-spectrum beta-lactamase-confirmation by using a machine learning model directly on routine automated susceptibility testing results |
| title_full_unstemmed | Rapid extended-spectrum beta-lactamase-confirmation by using a machine learning model directly on routine automated susceptibility testing results |
| title_short | Rapid extended-spectrum beta-lactamase-confirmation by using a machine learning model directly on routine automated susceptibility testing results |
| title_sort | rapid extended spectrum beta lactamase confirmation by using a machine learning model directly on routine automated susceptibility testing results |
| topic | ESBL machine learning antimicrobial resistance bacteria surveillance |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2025.1582703/full |
| work_keys_str_mv | AT yelghouch rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT yelghouch rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mcschut rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT kcesigaloff rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT waltorfvanderkuil rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT jmprins rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT rpschade rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT rpschade rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT theisisarstudygroup rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT jwtcohenstuart rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT dcmelles rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT kvandijk rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT aalzubaidy rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mscholing rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT sdkuil rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT gjblaauw rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT waltorf rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT vanderkuil rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT smbierman rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT scdegreeff rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT srgroenendijk rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT rhertroys rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT lkruithof rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT imnauta rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT dwnotermans rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT jpolman rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT wjvandenreek rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT afschoffelen rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT fvelthuis rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT cchwielders rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT bjdewit rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT rezoetigheid rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT wvandenbijllaardt rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT emkraan rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mbhaeseker rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT jmdasilva rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT edejong rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT bmaraha rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT ajvangriethuysen rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT bbwintermans rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mjcavantrijp rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT aemuller rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mwong rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT aott rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT ebathoorn rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mlokate rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT jsinnige rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT dcmelles rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT lbank rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT nhrenders rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT jwdorigozetsma rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT ljbakker rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT wang rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT kwaar rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mtvanderbeek rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT maleversteijnvanhall rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT spvanmens rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT eschaftenaar rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mhnabuursfranssen rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT imaat rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT pdjsturm rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT bmwdiederen rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT lgmbode rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT dsyong rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mvanrijn rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT sdinant rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mdenreijer rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT dwvandam rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT eigbdebrauwer rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT rgbentvelsen rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT almvlek rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mdegraaf rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT atroelstra rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT kbgast rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT mpavanmeer rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT jdevries rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults AT jdmachiels rapidextendedspectrumbetalactamaseconfirmationbyusingamachinelearningmodeldirectlyonroutineautomatedsusceptibilitytestingresults |