{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:27:40Z","timestamp":1793132860368,"version":"4.5.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":42,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NextGenerationEU-MUR PNRR Extended Partnership initiative on Emerging Infectious Diseases"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Microbiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Multidrug-resistant\n                      <jats:italic>Klebsiella pneumoniae<\/jats:italic>\n                      represents a significant challenge in healthcare settings, prompting numerous studies on the rapid detection of antimicrobial resistance. Mass spectrometry has been recently integrated into routine laboratory diagnostics, providing highly sensitive results for pathogen identification. Furthermore, previously published studies have demonstrated its potential application in predicting antimicrobial resistance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>\n                      The study collected 686 clinical isolates of\n                      <jats:italic>K. pneumoniae<\/jats:italic>\n                      from three Italian hospitals and used their MALDI-TOF mass spectra as input to machine learning models for predicting susceptibility profiles to amikacin and meropenem, which were selected as the most represented antibiotic molecules within the aminoglycoside and carbapenem classes, commonly used for the treatment of\n                      <jats:italic>K. pneumoniae<\/jats:italic>\n                      infections. After preprocessing,\n                      <jats:italic>K. pneumoniae<\/jats:italic>\n                      spectra were fed to machine learning classifiers within a nested cross-validation framework. Several performance metrics were computed to compare models and identify the most appropriate one for each antibiotic. Given the multicentric nature of the study, a batch-effect correction step was applied to reduce site-specific variability using the in-house developed Python package\n                      <jats:italic>combatlearn<\/jats:italic>\n                      (available on GitHub:\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/EttoreRocchi\/combatlearn\" ext-link-type=\"uri\">https:\/\/github.com\/EttoreRocchi\/combatlearn<\/jats:ext-link>\n                      ).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The XGBoost model achieved the best performance for both antibiotics (AUROC\u2009=\u20090.822\u2009\u00b1\u20090.028 for amikacin; AUROC\u2009=\u20090.887\u2009\u00b1\u20090.019 for meropenem). A per-site performance analysis revealed that, while performances\u2019 variability was inherently linked to each center\u2019s sample size,\n                      <jats:italic>combatlearn<\/jats:italic>\n                      -based harmonization effectively aligned mean AUROC values across sites.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>\n                      Our study demonstrates the capability of MALDI-TOF mass spectra to predict amikacin and meropenem resistance in\n                      <jats:italic>K. pneumoniae<\/jats:italic>\n                      directly from clinical spectra, supporting its potential as a rapid and cost-effective approach for both antimicrobial resistance surveillance through machine learning models and clinical decision support in routine microbiology practice.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12866-025-04657-2","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T06:53:30Z","timestamp":1768805610000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Combining mass spectrometry and machine learning models for predicting Klebsiella pneumoniae antimicrobial resistance: a multicenter experience from clinical isolates in Italy"],"prefix":"10.1186","volume":"26","author":[{"given":"Ettore","family":"Rocchi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuele","family":"Nicitra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maddalena","family":"Calvo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valeria","family":"Cento","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Peiretti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zian","family":"Asif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giulia","family":"Menchinelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brunella","family":"Posteraro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Sala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Colosimo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monica","family":"Cricca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vittorio","family":"Sambri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurizio","family":"Sanguinetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gastone","family":"Castellani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefania","family":"Stefani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"4657_CR1","unstructured":"https:\/\/asm.org\/articles\/2021\/november\/beyond-the-matrix-mass-spec-as-a-clinical-microbio . (Accessed on 28th June 2025)."},{"key":"4657_CR2","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.3390\/healthcare11131946","volume":"11","author":"MA Salam","year":"2023","unstructured":"Salam MA, Al-Amin MY, Salam MT, Pawar JS, Akhter N, Rabaan AA, et al. Antimicrobial resistance: a growing serious threat for global public health. Healthcare. 2023;11:1946. https:\/\/doi.org\/10.3390\/healthcare11131946.","journal-title":"Healthcare"},{"key":"4657_CR3","unstructured":"https:\/\/www.ecdc.europa.eu\/sites\/default\/files\/documents\/Antimicrobial%20resistance%20surveillance%20in%20Europe%202023%20-%202021%20data.pdf . (Accessed on 9th July 2025)."},{"key":"4657_CR4","unstructured":"https:\/\/www.epicentro.iss.it\/antibiotico-resistenza\/ar-iss\/RIS-5_2024.pdf . (Accessed on 10th July 2025)."},{"issue":"3","key":"4657_CR5","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1093\/jac\/dkw513","volume":"72","author":"ZR Palacios-Baena","year":"2017","unstructured":"Palacios-Baena ZR, Guti\u00e9rrez-Guti\u00e9rrez B, De Cueto M, et al. Development and validation of the INCREMENT-ESBL predictive score for mortality in patients with bloodstream infections due to extended-spectrum-\u03b2-lactamase-producing Enterobacteriaceae. J Antimicrob Chemother. 2017;72(3):906\u201313. https:\/\/doi.org\/10.1093\/jac\/dkw513.","journal-title":"J Antimicrob Chemother"},{"key":"4657_CR6","doi-asserted-by":"publisher","unstructured":"Burckhardt I, Zimmermann S. Using matrix-assisted laser desorption ionization-time of flight mass spectrometry to detect carbapenem resistance within 1 to 2.5 hours. J Clin Microbiol. 2011. https:\/\/doi.org\/10.1128\/jcm.00287-11.","DOI":"10.1128\/jcm.00287-11"},{"issue":"9","key":"4657_CR7","doi-asserted-by":"publisher","first-page":"3222","DOI":"10.1128\/JCM.00984-11","volume":"49","author":"J Hrab\u00e1k","year":"2011","unstructured":"Hrab\u00e1k J, Walkov\u00e1 R, Studentov\u00e1 V, Chud\u00e1ckov\u00e1 E, Bergerov\u00e1 T. Carbapenemase activity detection by matrix-assisted laser desorption ionization-time of flight mass spectrometry. J Clin Microbiol. 2011;49(9):3222\u20137. https:\/\/doi.org\/10.1128\/JCM.00984-11.","journal-title":"J Clin Microbiol"},{"key":"4657_CR8","doi-asserted-by":"publisher","unstructured":"Johansson A, Nagy E, S\u00f3ki J, ESGAI (ESCMID Study Group on Anaerobic Infections). Detection of carbapenemase activities of Bacteroides fragilis strains with matrix-assisted laser desorption ionization\u2013time of flight mass spectrometry (MALDI-TOF MS). Anaerobe. 2014;26:49\u201352. https:\/\/doi.org\/10.1016\/j.anaerobe.2014.01.006.","DOI":"10.1016\/j.anaerobe.2014.01.006"},{"issue":"6","key":"4657_CR9","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1007\/s10096-013-2031-5","volume":"33","author":"JS Jung","year":"2014","unstructured":"Jung JS, Eberl T, Sparbier K, et al. Rapid detection of antibiotic resistance based on mass spectrometry and stable isotopes. Eur J Clin Microbiol Infect Dis. 2014;33(6):949\u201355. https:\/\/doi.org\/10.1007\/s10096-013-2031-5.","journal-title":"Eur J Clin Microbiol Infect Dis"},{"key":"4657_CR10","doi-asserted-by":"publisher","unstructured":"Ovia\u00f1o M, Gato E, Bou G. Rapid detection of KPC-producing enterobacterales susceptible to Imipenem\/Relebactam by using the MALDI-TOF MS MBT STAR-Carba IVD assay. Front Microbiol. 2020;11:328. https:\/\/doi.org\/10.3389\/fmicb.2020.00328. (Published 2020 Feb 28).","DOI":"10.3389\/fmicb.2020.00328"},{"key":"4657_CR11","doi-asserted-by":"publisher","unstructured":"Correa-Mart\u00ednez CL, Idelevich EA, Sparbier K, Kostrzewa M, Becker K. Rapid detection of Extended-Spectrum \u03b2-Lactamases (ESBL) and AmpC \u03b2-Lactamases in Enterobacterales: development of a screening panel using the MALDI-TOF MS-based direct-on-target microdroplet growth assay. Front Microbiol. 2019;10:13. https:\/\/doi.org\/10.3389\/fmicb.2019.00013.","DOI":"10.3389\/fmicb.2019.00013"},{"key":"4657_CR12","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1038\/s41591-021-01619-9","volume":"28","author":"C Weis","year":"2022","unstructured":"Weis C, Cu\u00e9nod A, Rieck B, et al. Direct antimicrobial resistance prediction from clinical MALDI-TOF mass spectra using machine learning. Nat Med. 2022;28:164\u201374. https:\/\/doi.org\/10.1038\/s41591-021-01619-9.","journal-title":"Nat Med"},{"key":"4657_CR13","unstructured":"The European Committee on Antimicrobial Susceptibility Testing. Breakpoint tables for interpretation of MICs and zone diameters. Version 15.0. 2025. https:\/\/www.eucast.org., Accessed on 10th February 2025 (Accessed on 3th July 2025)."},{"issue":"1","key":"4657_CR14","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1038\/s41591-021-01619-9","volume":"28","author":"C Weis","year":"2022","unstructured":"Weis C, Cu\u00e9nod A, Rieck B, et al. Direct antimicrobial resistance prediction from clinical MALDI-TOF mass spectra using machine learning. Nat Med. 2022;28(1):164\u201374. https:\/\/doi.org\/10.1038\/s41591-021-01619-9.","journal-title":"Nat Med"},{"key":"4657_CR15","doi-asserted-by":"publisher","unstructured":"Ryan CG, Clayton E, Griffin WL, Sie SH, Cousens DR. SNIP, a statistics-sensitive background treatment for the quantitative analysis of PIXE spectra in geoscience applications. Nucl Instrum Methods Phys Res Sect B Beam Interact Mater Atoms. 1988;34(3):396\u2013402. https:\/\/doi.org\/10.1016\/0168-583X(88)90063-8.","DOI":"10.1016\/0168-583X(88)90063-8"},{"issue":"1","key":"4657_CR16","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1093\/biostatistics\/kxj037","volume":"8","author":"WE Johnson","year":"2007","unstructured":"Johnson WE, Li C, Rabinovic A. Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics. 2007;8(1):118\u201327. https:\/\/doi.org\/10.1093\/biostatistics\/kxj037.","journal-title":"Biostatistics"},{"key":"4657_CR17","doi-asserted-by":"publisher","unstructured":"Li J, Shi Y, Song X, Yin X, Liu H. Mechanisms of antimicrobial resistance in Klebsiella: advances in detection methods and clinical implications. Infect Drug Resist. 2025;18:1339\u201354. https:\/\/doi.org\/10.2147\/IDR.S509016.","DOI":"10.2147\/IDR.S509016"},{"key":"4657_CR18","doi-asserted-by":"publisher","unstructured":"Kao K, Alocilja EC. A review of the diagnostic approaches for the detection of antimicrobial resistance, including the role of biosensors in detecting carbapenem resistance genes. Genes. 2025;16(7):794. https:\/\/doi.org\/10.3390\/genes16070794.","DOI":"10.3390\/genes16070794"},{"issue":"3","key":"4657_CR19","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.cll.2019.04.001","volume":"39","author":"KP Smith","year":"2019","unstructured":"Smith KP, Kirby JE. Rapid susceptibility testing methods. Clin Lab Med. 2019;39(3):333\u201344. https:\/\/doi.org\/10.1016\/j.cll.2019.04.001.","journal-title":"Clin Lab Med"},{"key":"4657_CR20","doi-asserted-by":"publisher","unstructured":"Wang HY, Chung CR, Chen CJ, et al. Clinically applicable system for rapidly predicting Enterococcus faecium susceptibility to Vancomycin. Microbiol Spectr. 2021;9(3):e0091321. https:\/\/doi.org\/10.1128\/Spectrum.00913-21.","DOI":"10.1128\/Spectrum.00913-21"},{"key":"4657_CR21","doi-asserted-by":"publisher","unstructured":"Vella A, De Carolis E, Mello E, et al. Potential use of MALDI-ToF mass spectrometry for rapid detection of antifungal resistance in the human pathogen Candida glabrata. Sci Rep. 2017;7(1):9099. https:\/\/doi.org\/10.1038\/s41598-017-09329-4.","DOI":"10.1038\/s41598-017-09329-4"},{"key":"4657_CR22","doi-asserted-by":"publisher","unstructured":"L\u00f3pez-Cort\u00e9s XA, Manr\u00edquez-Troncoso JM, Sep\u00falveda AY, Soto PS. Integrating machine learning with MALDI-TOF mass spectrometry for rapid and accurate antimicrobial resistance detection in clinical pathogens. Int J Mol Sci. 2025;26(3):1140. https:\/\/doi.org\/10.3390\/ijms26031140.","DOI":"10.3390\/ijms26031140"},{"key":"4657_CR23","doi-asserted-by":"publisher","unstructured":"Yu J, Lin YT, Chen WC, et al. Direct prediction of carbapenem-resistant, carbapenemase-producing, and colistin-resistant Klebsiella pneumoniae isolates from routine MALDI-TOF mass spectra using machine learning and outcome evaluation. Int J Antimicrob Agents. 2023;61(6):106799. https:\/\/doi.org\/10.1016\/j.ijantimicag.2023.106799.","DOI":"10.1016\/j.ijantimicag.2023.106799"},{"key":"4657_CR24","doi-asserted-by":"publisher","unstructured":"Nguyen H-A, Peleg AY, Song J, et al. Predicting Pseudomonas aeruginosa drug resistance using artificial intelligence and clinical MALDI-TOF mass spectra. mSystems. 2024;9(9):e0078924. https:\/\/doi.org\/10.1128\/msystems.00789-24.","DOI":"10.1128\/msystems.00789-24"},{"key":"4657_CR25","unstructured":"https:\/\/qlik.qualitasiciliassr.it\/anonimo\/single\/?appid=85ada16c-4b41-4bc6-9ca1-405b8243d0c2&sheet=6ad6f3ac-3369-41c5-bd72-792243f9091b&opt=ctxmenu,currsel (Accessed on 7th July 2025)."},{"issue":"14","key":"4657_CR26","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","volume":"380","author":"A Rajkomar","year":"2019","unstructured":"Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347\u201358. https:\/\/doi.org\/10.1056\/NEJMra1814259.","journal-title":"N Engl J Med"},{"key":"4657_CR27","doi-asserted-by":"publisher","unstructured":"Kim JI, Maguire F, Tsang KK, et al. Machine learning for antimicrobial resistance prediction: current practice, limitations, and clinical perspective. Clin Microbiol Rev. 2022;35(3):e0017921. https:\/\/doi.org\/10.1128\/cmr.00179-21.","DOI":"10.1128\/cmr.00179-21"},{"key":"4657_CR28","doi-asserted-by":"publisher","unstructured":"Sivori F, Francalancia M, Truglio M, et al. Meropenem\/vaborbactam activity against carbapenem-resistant Klebsiella pneumoniae from catheter-related bloodstream infections. Front Cell Infect Microbiol. 2025;15:1616353. https:\/\/doi.org\/10.3389\/fcimb.2025.1616353. (Published 2025 Jul 31).","DOI":"10.3389\/fcimb.2025.1616353"},{"key":"4657_CR29","doi-asserted-by":"publisher","unstructured":"Tozluyurt A. The effectiveness of aztreonam, aztreonam-avibactam, cefiderocol on blaNDM-producing E. coli isolates. Mol Genet Microbiol Virol. 2024;39:158\u201364. https:\/\/doi.org\/10.3103\/S0891416824700198.","DOI":"10.3103\/S0891416824700198"},{"key":"4657_CR30","doi-asserted-by":"publisher","unstructured":"Jacobs MR, Abdelhamed AM, Good CE, Mack AR, Bethel CR, Marshall S, et al. ARGONAUT-III and -V: susceptibility of carbapenem-resistant Klebsiella pneumoniae and multidrug-resistant Pseudomonas aeruginosa to the bicyclic boronate \u03b2-lactamase inhibitor taniborbactam combined with cefepime. Antimicrob Agents Chemother. 2024;68(9):e0075124. https:\/\/doi.org\/10.1128\/aac.00751-24.","DOI":"10.1128\/aac.00751-24"}],"container-title":["BMC Microbiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12866-025-04657-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12866-025-04657-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12866-025-04657-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T09:16:37Z","timestamp":1772442997000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12866-025-04657-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["4657"],"URL":"https:\/\/doi.org\/10.1186\/s12866-025-04657-2","relation":{},"ISSN":["1471-2180"],"issn-type":[{"value":"1471-2180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]},"assertion":[{"value":"30 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study involved bacterial isolates obtained from routine clinical diagnostic procedures and did not require any additional biological sampling. All isolates were anonymized, and no patient-related data were accessed. According to Italian regulations, studies based solely on anonymized bacterial isolates do not require ethical approval. In accordance with the Declaration of Helsinki, research using non-identifiable human material does not represent research involving human subjects; therefore, ethical review and informed consent were waived. The study was conducted in compliance with the General Data Protection Regulation (GDPR, EU 2016\/679) and the Italian Legislative Decree 196\/2003 (as amended by Legislative Decree 101\/2018).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"180"}}