{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T22:22:45Z","timestamp":1790202165839,"version":"4.1.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Carbapenem-resistant\n                      <jats:italic>Klebsiella pneumoniae<\/jats:italic>\n                      (CRKP) infections in intensive care units are associated with poor outcomes. The delay in obtaining culture-based susceptibility results often forces clinicians to choose between under-treatment and overtreatment with empirical antibiotics. A reliable early risk assessment using only standard clinical data could help address this challenge.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This single-center retrospective cohort study included 401 ICU patients with culture-confirmed\n                      <jats:italic>K. pneumoniae<\/jats:italic>\n                      infections (January 2022 to January 2025). Patients were randomly allocated to training (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f281) and validation (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f120) sets. Predictors extracted from electronic health records comprised demographics, severity scores (APACHE II, SOFA), comorbidities, invasive procedures, inflammatory markers, specimen type, history of multidrug-resistant (MDR) infection, and antibiotic exposure within the preceding 90\u202fdays. Feature selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression on the training set. The selected features were used to develop an XGBoost model, whose performance was compared against six other machine learning algorithms (logistic regression, random forest, etc.). Model discrimination was evaluated using the area under the receiver operating characteristic curve (AUC), calibration with Brier scores and calibration curves, and clinical utility with decision curve analysis. SHapley Additive exPlanations (SHAP) values were employed to interpret the model.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>CRKP isolates accounted for 15.7% (63\/401) of cases. LASSO regression identified nine predictors: procalcitonin (PCT), specimen type, prior MDR infection, prior carbapenem exposure, history of stroke, APACHE II score, white blood cell count, age, and hemoglobin. In the independent validation set, the XGBoost model achieved an AUC of 0.852 (95% CI: 0.745\u20130.959), with a sensitivity of 0.737, specificity of 0.891, accuracy of 0.867, and an F1-score of 0.636. The model demonstrated good calibration (Brier score: 0.088) and provided a net clinical benefit across a wide range of risk thresholds. SHAP analysis highlighted PCT, specimen source (blood), and prior resistance-related exposures as the most influential predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The integration of LASSO feature selection with the XGBoost algorithm, utilizing only routine clinical data, generates a reliable early-warning model for CRKP infection risk prior to the availability of susceptibility reports. This tool shows promising discriminative ability and calibration, offering potential to guide empirical therapy and support antimicrobial stewardship. Future multicenter prospective studies are warranted to validate its generalizability and real-world clinical impact.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1798927","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:52:39Z","timestamp":1776837159000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Interpretable machine learning for early detection of carbapenem-resistant Klebsiella pneumoniae in ICUs: risk prediction using LASSO and XGBoost"],"prefix":"10.3389","volume":"14","author":[{"given":"Qiuyan","family":"Pan","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory, Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine","place":["Suzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine","place":["Suzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine","place":["Suzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiazheng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine","place":["Suzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine","place":["Suzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine","place":["Suzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,22]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.jiac.2021.09.001","article-title":"Predicting mortality in intensive care unit patients infected with Klebsiella pneumoniae: a retrospective cohort study","volume":"28","author":"Tran","year":"2022","journal-title":"J Infect Chemother"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s13756-025-01603-9","article-title":"Assessment of the risk of aerosol transmission of CRKP during bronchoscopy in the intensive care unit","volume":"14","author":"Yang","year":"2025","journal-title":"Antimicrob Resist Infect Control"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"S9","DOI":"10.1016\/j.cmi.2016.01.001","article-title":"Resistance trends among clinical isolates in China reported from CHINET surveillance of bacterial resistance, 2005-2014","volume":"22","author":"Hu","year":"2016","journal-title":"Clin Microbiol Infect"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s44280-025-00092-0","article-title":"Antimicrobial resistance profile of clinical isolates from hospitals across China: CHINET 2024 surveillance report","volume":"3","author":"Guo","year":"2025","journal-title":"One Health Adv"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/j.jinf.2018.02.007","article-title":"Mortality due to KPC carbapenemase-producing Klebsiella pneumoniae infections: systematic review and meta-analysis: mortality due to KPC Klebsiella pneumoniae infections","volume":"76","author":"Ramos-Casta\u00f1eda","year":"2018","journal-title":"J Infect"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"12258","DOI":"10.1021\/acs.analchem.5c01101","article-title":"Pheno-molecular testing enabled by multiplex droplet digital PCR for rapid and high-content detection of carbapenem-resistant Enterobacterales","volume":"97","author":"Zhang","year":"2025","journal-title":"Anal Chem"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"i13","DOI":"10.1093\/jac\/dkae282","article-title":"Evaluating the impact of rapid antimicrobial susceptibility testing for bloodstream infections: a review of actionability, antibiotic use and patient outcome metrics","volume":"79","author":"MacVane","year":"2024","journal-title":"J Antimicrob Chemother"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1186\/s13054-021-03736-w","article-title":"Initial antimicrobial management of sepsis","volume":"25","author":"Niederman","year":"2021","journal-title":"Crit Care"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"105328","DOI":"10.1016\/j.phrs.2020.105328","article-title":"Polymyxin-induced nephrotoxicity and its predictors: a systematic review and meta-analysis of studies conducted using RIFLE criteria of acute kidney injury","volume":"163","author":"Sisay","year":"2021","journal-title":"Pharmacol Res"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"106184","DOI":"10.1016\/j.ijantimicag.2020.106184","article-title":"Systematic review of the impact of appropriate versus inappropriate initial antibiotic therapy on outcomes of patients with severe bacterial infections","volume":"56","author":"Bassetti","year":"2020","journal-title":"Int J Antimicrob Agents"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e2249353","DOI":"10.1001\/jamanetworkopen.2022.49353","article-title":"Association of appropriate empirical antimicrobial therapy with in-hospital mortality in patients with bloodstream infections in the US","volume":"6","author":"Ohnuma","year":"2023","journal-title":"JAMA Netw Open"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e00177-21","DOI":"10.1128\/mSystems.00177-21","article-title":"Patient and microbial genomic factors associated with carbapenem-resistant Klebsiella pneumoniae extraintestinal colonization and infection","volume":"6","author":"Lapp","year":"2021","journal-title":"mSystems"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"41","DOI":"10.2147\/idr.S437742","article-title":"Risk factors and predictive nomogram for carbapenem-resistant Klebsiella pneumoniae in children in a grade 3 first-class general Hospital in Central China","volume":"17","author":"Chu","year":"2024","journal-title":"Infect Drug Resist"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e03096","DOI":"10.1128\/spectrum.03096-23","article-title":"Development and application of a nomogram model for the prediction of carbapenem-resistant Klebsiella pneumoniae infection in neuro-ICU patients","volume":"12","author":"Lu","year":"2024","journal-title":"Microbiol Spectrum"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"20230774","DOI":"10.1515\/med-2023-0774","article-title":"Risk model and validation of carbapenem-resistant Klebsiella pneumoniae infection in patients with cerebrovascular disease in the ICU","volume":"18","author":"Liao","year":"2023","journal-title":"Open Med"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e0217024","DOI":"10.1128\/spectrum.02170-24","article-title":"Development and validation of a nomogram-based risk prediction model for carbapenem-resistant Klebsiella pneumoniae in hospitalized patients","volume":"13","author":"Xu","year":"2025","journal-title":"Microbiol Spectrum"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1109\/MedAI62885.2024.00077","volume-title":"2024 IEEE International Conference on Medical Artificial Intelligence (MedAI)","author":"Shan","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2541","DOI":"10.1007\/s11739-025-03896-5","article-title":"Enhancing mortality prediction in intensive care units: improving APACHE II, SOFA, and SAPS II scoring systems using long short-term memory","volume":"20","author":"Deng","year":"2025","journal-title":"Intern Emerg Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"ciae403","DOI":"10.1093\/cid\/ciae403","article-title":"Infectious Diseases Society of America 2024 guidance on the treatment of antimicrobial-resistant gram-negative infections","author":"Tamma","year":"2024","journal-title":"Clin Infect Dis"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1269408","DOI":"10.3389\/fmicb.2023.1269408","article-title":"Dissemination and characteristics of carbapenem-resistant Klebsiella pneumoniae in nine district hospitals in southwestern China","volume":"14","author":"Wang","year":"2023","journal-title":"Front Microbiol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"m441","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1186\/s12874-016-0267-3","article-title":"No rationale for 1 variable per 10 events criterion for binary logistic regression analysis","volume":"16","author":"van Smeden","year":"2016","journal-title":"BMC Med Res Methodol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"2238832","DOI":"10.1080\/0886022x.2023.2238832","article-title":"Development and validation of a LASSO-based prediction model for immunosuppressive medication nonadherence in kidney transplant recipients","volume":"45","author":"Dong","year":"2023","journal-title":"Ren Fail"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e2300247","DOI":"10.1200\/cci.23.00247","article-title":"Explainable machine learning model to preoperatively predict postoperative complications in inpatients with cancer undergoing major operations","volume":"8","author":"Hernandez","year":"2024","journal-title":"JCO Clin Cancer Inform"},{"key":"ref26","first-page":"30","volume-title":"A Unified Approach to Interpreting Model Predictions","author":"Lundberg","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"2292","DOI":"10.1093\/jac\/dkae227","article-title":"Epidemiology of carbapenem-resistant Klebsiella pneumoniae in China and the evolving trends of predominant clone ST11: a multicentre, genome-based study","volume":"79","author":"Shi","year":"2024","journal-title":"J Antimicrob Chemother"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"dlae052","DOI":"10.1093\/jacamr\/dlae052","article-title":"Antimicrobial resistance of clinical bacterial isolates in China: current status and trends","volume":"6","author":"Qin","year":"2024","journal-title":"JAC Antimicrob Resist"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"3514","DOI":"10.1128\/aac.02373-13","article-title":"Predictive models for identification of hospitalized patients harboring KPC-producing Klebsiella pneumoniae","volume":"58","author":"Tumbarello","year":"2014","journal-title":"Antimicrob Agents Chemother"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.2147\/idr.S362723","article-title":"Analysis of risk factors and mortality of patients with carbapenem-resistant Klebsiella pneumoniae infection","volume":"15","author":"Wu","year":"2022","journal-title":"Infect Drug Resist"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s13756-020-0686-0","article-title":"Risk factors for carbapenem-resistant Klebsiella pneumoniae infection relative to two types of control patients: a systematic review and meta-analysis","volume":"9","author":"Zhu","year":"2020","journal-title":"Antimicrob Resist Infect Control"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"783124","DOI":"10.3389\/fpubh.2021.783124","article-title":"Comparison of carbapenem-resistant Klebsiella pneumoniae strains causing intestinal colonization and extraintestinal infections: clinical, virulence, and molecular epidemiological characteristics","volume":"9","author":"Liao","year":"2021","journal-title":"Front Public Health"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1099\/jmm.0.000921","article-title":"The clinical significance of carbapenem-resistant Klebsiella pneumoniae rectal colonization in critically ill patients: from colonization to bloodstream infection","volume":"68","author":"Kontopoulou","year":"2019","journal-title":"J Med Microbiol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.3390\/pathogens12111277","article-title":"Factors associated with extended-spectrum \u03b2-lactamases and carbapenem-resistant Klebsiella pneumoniae bloodstream infections: a five-year retrospective study","volume":"12","author":"Tofarides","year":"2023","journal-title":"Pathogens"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"4833","DOI":"10.2147\/idr.S479374","article-title":"Risk factors for multidrug resistance in patients infected with carbapenem-resistant Klebsiella pneumoniae: a nomogram","volume":"17","author":"Gao","year":"2024","journal-title":"Infect Drug Resist"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1016\/j.cmi.2016.01.016","article-title":"Predictors of outcome in ICU patients with septic shock caused by Klebsiella pneumoniae carbapenemase-producing K. pneumoniae","volume":"22","author":"Falcone","year":"2016","journal-title":"Clin Microbiol Infect"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1038\/s41435-021-00126-8","article-title":"The aging gut microbiome and its impact on host immunity","volume":"22","author":"Bosco","year":"2021","journal-title":"Genes Immun"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1186\/s13756-020-00728-3","article-title":"Five-year change of prevalence and risk factors for infection and mortality of carbapenem-resistant Klebsiella pneumoniae bloodstream infection in a tertiary hospital in North China","volume":"9","author":"Li","year":"2020","journal-title":"Antimicrob Resist Infect Control"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"9767313","DOI":"10.1155\/2019\/9767313","article-title":"Carbapenem-resistant Klebsiella pneumoniae infections among ICU admission patients in Central China: prevalence and prediction model","volume":"2019","author":"Li","year":"2019","journal-title":"Biomed Res Int"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1156","DOI":"10.3390\/antibiotics14111156","article-title":"Treatment options for critically ill patients with infections caused by metallo-beta-lactamase-producing Klebsiella pneumoniae","volume":"14","author":"Mantzarlis","year":"2025","journal-title":"Antibiotics"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"642","DOI":"10.3109\/00365548.2014.923106","article-title":"Risk factors for infection and predictors of mortality among patients with KPC-producing Klebsiella pneumoniae bloodstream infections in the intensive care unit","volume":"46","author":"Papadimitriou-Olivgeris","year":"2014","journal-title":"Scand J Infect Dis"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1798927\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:52:46Z","timestamp":1776837166000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1798927\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,22]]},"references-count":41,"alternative-id":["10.3389\/fpubh.2026.1798927"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1798927","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,22]]},"article-number":"1798927"}}