[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128207-en":3,"doc-seo-128207-105":31,"detail-sidebar-cat-0-en-105":96},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128207,2336475104362,"Eden","https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868",8,"Research & Report","Direct Detection of Carbapenemase-Producing Klebsiella pneumoniae by MALDI-TOF Analysis of Full Spectra - Applying Machine Learning","MALDI-TOF MS supports rapid microbiological workflows by enabling bacteria identification and antimicrobial resistance detection in one integrated approach. A machine learning method using random forest models directly predicts carbapenemase-producing Klebsiella pneumoniae (CPK) from complete-cell spectra without additional hands-on steps. A training database of 4,547 mass spectra profiles includes 715 clinical isolates represented by 324 CPK across 37 ST. The culture medium strongly affects prediction, with best results when isolates are cultured in the same media as the modeling set, reaching 97.83% CPK accuracy. OXA-48 or KPC carriage prediction achieves 95.24% accuracy. Receiver operating characteristics and precision-recall metrics reach 1.00 for CPK. Shapley-value interpretation indicates full proteome patterns—not selected peaks or biomarkers—drive classification, yielding detection within minutes and reducing resistance-reporting time.","BACTERIOLOGY  \nDirect Detection of Carbapenemase-Producing Klebsiella pneumoniae by MALDI-TOF Analysis of Full Spectra Applying Machine Learning  \nEva Gato,a Manuel J. Arroyo,b Gema Méndez,b Ana Candela,a Bruno Kotska Rodiño-Janeiro,a Javier Fernández,c  \nBelén Rodríguez-Sánchez,d Luis Mancera,b Jorge Arca-Suárez,a,e Alejandro Beceiro,a,e Germán Bou,a,e Marina Oviañoa,e  \naServicio de Microbiología, Complejo Hospitalario Universitario A Coruña, A Coruña, Spain  \nbClover Bioanalytical Software S. L., Granada, Spain  \ncServicio de Microbiología, Hospital Central de Asturias, Oviedo, Spain dServicio de Microbiología, Hospital General Gregorio Marañón, Madrid, Spain  \ne Centro de Investigación Biomedica en Red Enfermedades Infecciosas (CIBERINFEC) . Instituto de Salud Carlos III (ISCIII), Madrid, Spain Eva Gato, Manuel J. Arroyo, and Gema Méndez contributed equally to this work. Author order was determined in order of increasing seniority.  \nABSTRACT MALDI-TOF MS is considered to be an important tool for the future development of rapid microbiological techniques. We propose the application of MALDI-TOF MS as a dual technique for the identification of bacteria and the detection of resistance, with no extra hands-on procedures. We have developed a machine learning approach that uses the random forest algorithm for the direct prediction of carbapenemase-producing Klebsiella pneumoniae (CPK) isolates, based on the spectra of complete cells. For this purpose, we used a database of 4,547 mass spectra profiles, including 715 unduplicated clinical isolates that are represented by 324 CPK with 37 different ST. The impact of the culture medium was determinant in the CPK prediction, being that the isolates were tested and cultured in the same media, compared to the isolates used to build the model (blood agar). The proposed method has an accuracy of 97.83% for the prediction of CPK and an accuracy of 95.24% for the prediction of OXA-48 or KPC carriage. For the CPK prediction, the RF algorithm yielded a value of 1.00 for both the area under the receiver operating characteristic curve and the area under the precision-recall curve. The contribution of individual mass peaks to the CPK prediction was determined using Shapley values, which revealed that the complete proteome, rather than a series of mass peaks or potential biomarkers (as previously suggested), is responsible for the algorithm-based classification. Thus, the use of the full spectrum, as proposed here, with a pattern-matching analytical algorithm produced the best outcome. The use of MALDI-TOF MS coupled with machine learning algorithm processing enabled the identification of CPK isolates within only a few minutes, thereby reducing the time to detection of resistance.  \nThe increasing  \nognized as a  \nemergence of carbapenemase-producing Klebsiella pneumoniae (CPK) is recglobal health concern by different organizations, such as the European  \nCentre for Disease Control (ECDC), the Centers for Disease Control and Prevention (CDC), and the World Health Organization (WHO) (1–4), as infections produced by these bacteria are associated with substantial morbidity, mortality, and health care costs (5). Carbapenemases can confer resistance to almost all available beta-lactams, which are the antibiotics most commonly used to treat infections caused by Enterobacterales (6). Thus, early identification can improve the choice of therapeutic options. The detection of antimicrobial resistance is usually based on widely approved molecular techniques (7). However, these techniques are more time-consuming and expensive than matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF). In addition, molecular techniques are generally narrow-spectrum assays with  \nEditor Erin McElvania, NorthShore University HealthSystem  \nCopyright © 2023 Gato et al. This is an openaccess article distributed under the terms of the Creative Commons Attribution 4 .0 International license.  \nAddress correspondence to ","cbCaicx2TxYng7r1","https://ap.wps.com/l/cbCaicx2TxYng7r1","pdf",2374296,3,1,13,"English","en",105,"# Abstract\n## Rationale for rapid MALDI-TOF MS and resistance detection\n## Machine learning approach and dataset composition\n## Model performance and interpretability (Shapley values)\n## Impact of culture medium and time-to-detection context","[{\"question\":\"What is the document’s main goal for MALDI-TOF MS in CPK detection?\",\"answer\":\"Develop a machine learning approach that uses MALDI-TOF full-spectrum data to directly predict carbapenemase-producing Klebsiella pneumoniae while also supporting resistance detection without extra hands-on steps.\"},{\"question\":\"How was the machine learning model trained and what data were used?\",\"answer\":\"A random forest model was trained on 4,547 mass spectra profiles, including 715 unduplicated clinical isolates represented by 324 CPK isolates across 37 different ST.\"},{\"question\":\"Why does the culture medium matter in the CPK prediction results?\",\"answer\":\"The impact of culture medium was described as determinant: isolates cultured and tested in the same media used to build the model (blood agar) produced the best prediction outcomes.\"},{\"question\":\"What do Shapley values suggest about what drives CPK classification?\",\"answer\":\"Shapley-value analysis indicates that classification relies on patterns representing the complete proteome rather than on individual mass peaks or previously suggested single biomarkers.\"}]","Direct Detection of Carbapenemase-Producing Klebsiella pneumoniae by MALDI-TOF Analysis of Full Spectra - Applying Machine Learning | PDF",1785945599,33,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":91,"head_meta":93,"extra_data":95,"updated_unix":29},"direct-detection-of-carbapenemase-producing-klebsiella-pneumoniae-by-maldi-tof-analysis-of-full-spectra-applying-machine-learning","",{"@graph":37,"@context":90},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/direct-detection-of-carbapenemase-producing-klebsiella-pneumoniae-by-maldi-tof-analysis-of-full-spectra-applying-machine-learning/128207/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-28","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82,86],{"name":73,"@type":74,"acceptedAnswer":75},"What is the document’s main goal for MALDI-TOF MS in CPK detection?","Question",{"text":76,"@type":77},"Develop a machine learning approach that uses MALDI-TOF full-spectrum data to directly predict carbapenemase-producing Klebsiella pneumoniae while also supporting resistance detection without extra hands-on steps.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How was the machine learning model trained and what data were used?",{"text":81,"@type":77},"A random forest model was trained on 4,547 mass spectra profiles, including 715 unduplicated clinical isolates represented by 324 CPK isolates across 37 different ST.",{"name":83,"@type":74,"acceptedAnswer":84},"Why does the culture medium matter in the CPK prediction results?",{"text":85,"@type":77},"The impact of culture medium was described as determinant: isolates cultured and tested in the same media used to build the model (blood agar) produced the best prediction outcomes.",{"name":87,"@type":74,"acceptedAnswer":88},"What do Shapley values suggest about what drives CPK classification?",{"text":89,"@type":77},"Shapley-value analysis indicates that classification relies on patterns representing the complete proteome rather than on individual mass peaks or previously suggested single biomarkers.","https://schema.org",{"og:url":52,"og:type":92,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":94,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":97},[98,102,106,110,115,120,125,128,133,136,140],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":107,"show_sort_weight":108,"slug":109},"Exam",70,"exam",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},5,"Comic",60,"comic",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},6,"Technology",50,"technology",{"id":121,"doc_module":4,"doc_module_name":47,"category_name":122,"show_sort_weight":123,"slug":124},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":126,"slug":127},30,"research-report",{"id":129,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":131,"slug":132},9,"Religion & Spirituality",20,"religion-spirituality",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":131,"slug":135},"World Cup","world-cup",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":137,"slug":139},10,"Lifestyle","lifestyle",{"id":141,"doc_module":4,"doc_module_name":47,"category_name":142,"show_sort_weight":111,"slug":143},19,"General","general"]