{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:04:14Z","timestamp":1789535054868,"version":"build-2803163510"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"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. Nutr."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Malnutrition and systemic inflammation are highly prevalent among critically ill patients with bone infections and may independently predict adverse outcomes. Five composite nutrition-inflammation indices\u2014the modified Nutrition Risk in the Critically Ill (mNUTRIC) score, Prognostic Nutritional Index (PNI), Geriatric Nutritional Risk Index (GNRI), Index of Nutritional Assessment (INA), and Hemoglobin-Albumin-Lymphocyte-Platelet (HALP) score\u2014have been proposed as prognostic tools; however, their comparative performance in the bone infection intensive care unit (ICU) population has not been systematically defined.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Material and method<\/jats:title>\n                    <jats:p>\n                      A dual-cohort retrospective study design was employed. The internal derivation cohort comprised ICU patients with bone infections from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database (\n                      <jats:italic>n<\/jats:italic>\n                      = 917; 28-day ICU mortality 12.1%), and the external validation cohort was drawn from the Affiliated Hospital of Qingdao University (\n                      <jats:italic>n<\/jats:italic>\n                      = 256; 28-day mortality 16.0%). All five indices were calculated from laboratory and clinical data collected within 24 h of ICU admission. Multivariable logistic regression (three hierarchical adjustment models), restricted cubic spline (RCS) analysis, and subgroup analyses were performed to examine the independent associations of each index with 28-day ICU mortality. For predictive model development, a dual LASSO-Boruta feature selection strategy was applied to the derivation cohort, yielding 14 core features (events-per-variable ratio [EPV] = 7.9). Five machine learning (ML) models \u2014 logistic regression (LR), random forest (RF), XGBoost, LightGBM, and support vector machine (SVM) \u2014 were trained with synthetic minority over-sampling technique (SMOTE) and five-fold stratified cross-validation. Discriminative performance was assessed by the area under the receiver operating characteristic curve (AUROC). The optimal model was further evaluated using SHapley Additive exPlanations (SHAP) values computed directly for the final LightGBM model with external stability validation, calibration curves, and decision curve analysis (DCA). A fully nested cross-validation with feature selection repeated within each training fold confirmed the robustness of the external performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>\n                      A total of 917 ICU patients with bone infections were included in the derivation cohort. In the fully adjusted model, HALP lowest tertile (T1, \u2264 171.11; odds ratio [OR] = 3.41, 95% confidence interval [CI] 2.13\u20135.46,\n                      <jats:italic>p<\/jats:italic>\n                      &amp;lt; 0.001) and low PNI (&amp;lt; 45; OR = 2.48, 95% CI 1.09\u20135.66,\n                      <jats:italic>p<\/jats:italic>\n                      = 0.031) remained independently associated with 28-day ICU mortality, whereas the associations of mNUTRIC, GNRI, and INA were attenuated to non-significance after full adjustment. RCS analysis confirmed a significant nonlinear dose-response relationship for HALP (\n                      <jats:italic>p<\/jats:italic>\n                      -nonlinearity &amp;lt; 0.001). In both cohorts, PNI (derivation AUROC 0.761; external 0.742) and HALP (0.745; 0.713) demonstrated the highest discriminative performance among the five indices, while GNRI lost discrimination owing to a near-universal at-risk classification (94.9% of the derivation cohort). Subgroup analysis showed the HALP\u2013mortality association was consistent across all clinical strata (all interaction\n                      <jats:italic>p<\/jats:italic>\n                      &amp;gt; 0.27). Among ML models, LightGBM achieved the highest external AUROC (0.956, 95% CI 0.921\u20130.985). SHAP analysis of the final LightGBM model identified APS III, acute kidney injury (AKI), and arterial oxygen tension (PO\n                      <jats:sub>2<\/jats:sub>\n                      ) as the most important predictors, with the ranking highly stable in the external validation cohort. DCA demonstrated superior net clinical benefit for the ML model over any single index across clinically relevant threshold probabilities.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Among five nutrition-inflammation indices evaluated in critically ill patients with bone infections, HALP and PNI were the leading independent predictors of 28-day ICU mortality, with HALP showing a robust, strongly nonlinear threshold effect that was consistent across all subgroups and adjustment models. In contrast to its dominant role in cardiothoracic populations, GNRI lost discriminative value here because nearly all patients were classified as at-risk. An interpretable ML model integrating 14 routinely available clinical features achieved excellent external discrimination (AUROC = 0.956) and clinical utility, supporting its potential as a decision-support tool for early risk stratification in this high-risk population.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnut.2026.1949102","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:30:10Z","timestamp":1789533010000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparative evaluation of five nutrition-inflammation indices for predicting 28-day ICU mortality in critically ill patients with bone infections: a dual-cohort study with external validation and interpretable machine learning"],"prefix":"10.3389","volume":"13","author":[{"given":"Zishuo","family":"Xi","sequence":"first","affiliation":[{"name":"Department of Bone Oncology, The Affiliated Hospital of Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialin","family":"He","sequence":"additional","affiliation":[{"name":"Department of Bone Oncology, The Affiliated Hospital of Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Bone Oncology, The Affiliated Hospital of Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Bone Oncology, The Affiliated Hospital of Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guiyang","family":"Zi","sequence":"additional","affiliation":[{"name":"Department of Bone Oncology, The Affiliated Hospital of Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenkai","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Bone Oncology, The Affiliated Hospital of Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Yue","sequence":"additional","affiliation":[{"name":"Department of Bone Oncology, The Affiliated Hospital of Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2106\/JBJS.N.01350","article-title":"Trends in the epidemiology of bone infections: a population-based study, 1969 to 2009","volume":"97","author":"Kremers","year":"2015","journal-title":"J Bone Joint Surg Am."},{"key":"B2","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1186\/s12877-016-0248-8","article-title":"Chronic bone infections increases long-term mortality risk in the elderly: a nationwide population-based cohort study","volume":"16","author":"Huang","year":"2016","journal-title":"BMC Geriatr."},{"key":"B3","doi-asserted-by":"publisher","first-page":"E102","DOI":"10.1097\/BSD.0000000000000597","article-title":"The epidemiology of vertebral bone infections in the United States from 1998 to 2013","volume":"31","author":"Issa","year":"2018","journal-title":"Clin Spine Surg."},{"key":"B4","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1186\/s12879-021-06274-6","article-title":"What is the burden of bone infections in Germany? An analysis of inpatient data from 2008 through 2018","volume":"21","author":"Walter","year":"2021","journal-title":"BMC Infect Dis."},{"key":"B5","doi-asserted-by":"publisher","first-page":"e002412","DOI":"10.1136\/bmjopen-2012-002412","article-title":"Incidence and risk factors for mortality of vertebral bone infections: a retrospective analysis using the Japanese diagnosis procedure combination database","volume":"3","author":"Akiyama","year":"2013","journal-title":"BMJ Open."},{"key":"B6","doi-asserted-by":"publisher","first-page":"4805","DOI":"10.3390\/jcm12144805","article-title":"Risk factors for the in-hospital mortality in pyogenic vertebral bone infections: a cross-sectional study on 9753 patients","volume":"12","author":"Ziarko","year":"2023","journal-title":"J Clin Med."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1378730","DOI":"10.3389\/fimmu.2024.1378730","article-title":"The correlation between serum calcium levels and prognosis in patients with severe acute bone infections","volume":"15","author":"Liu","year":"2024","journal-title":"Front Immunol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1038\/s41598-024-82891-w","article-title":"Association between red blood cell distribution width and mortality in severe bone infections patients","volume":"15","author":"Liu","year":"2025","journal-title":"Sci Rep."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1038\/s41598-024-83418-z","article-title":"Development and validation of a prognostic nomogram model for severe bone infections patients","volume":"15","author":"Liu","year":"2025","journal-title":"Sci Rep."},{"key":"B10","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1038\/s41579-022-00686-0","article-title":"Skeletal infections: microbial pathogenesis, immunity and clinical management","volume":"20","author":"Masters","year":"2022","journal-title":"Nat Rev Microbiol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"e00932","DOI":"10.1128\/IAI.00932-19","article-title":"Staphylococcus aureus bone infections: Bone, Bugs, and Surgery","volume":"88","author":"Urish","year":"2020","journal-title":"Infect Immun."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1219895","DOI":"10.3389\/fimmu.2023.1219895","article-title":"The effect of Staphylococcus aureus on innate and adaptive immunity and potential immunotherapy for S","volume":"14","author":"Chen","year":"2023","journal-title":"aureus-induced bone infections Front Immunol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1016\/j.it.2016.04.003","article-title":"Immune Dysfunction as a Cause and Consequence of Malnutrition","volume":"37","author":"Bourke","year":"2016","journal-title":"Trends Immunol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"e115","DOI":"10.1371\/journal.pmed.0040115","article-title":"Malnutrition and infection: complex mechanisms and global impacts","volume":"4","author":"Schaible","year":"2007","journal-title":"PLoS Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"846246","DOI":"10.3389\/fimmu.2022.846246","article-title":"Inflammatory stimuli alter bone marrow composition and compromise bone health in the malnourished host","volume":"13","author":"Osorio","year":"2022","journal-title":"Front Immunol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1186\/s13018-024-05165-1","article-title":"Association between malnutrition status and total joint arthroplasty periprosthetic joint infection and surgical site infection: a systematic review and meta-analysis","volume":"19","author":"Chen","year":"2024","journal-title":"J Orthop Surg Res."},{"key":"B17","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.clnu.2015.01.015","article-title":"Identifying critically-ill patients who will benefit most from nutritional therapy: Further validation of the \u2018modified NUTRIC' nutritional risk assessment tool","volume":"35","author":"Rahman","year":"2016","journal-title":"Clin Nutr."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1016\/j.clnu.2016.08.004","article-title":"Association of modified NUTRIC score with 28-day mortality in critically ill patients","volume":"36","author":"Mukhopadhyay","year":"2017","journal-title":"Clin Nutr."},{"key":"B19","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1038\/s41430-017-0008-7","article-title":"Nutritional assessment of critically ill patients: validation of the modified NUTRIC score","volume":"72","author":"de Vries","year":"2018","journal-title":"Eur J Clin Nutr."},{"key":"B20","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1186\/s12871-021-01439-x","article-title":"The association between the modified Nutrition Risk in Critically Ill (mNUTRIC) score and clinical outcomes in the intensive care unit","volume":"21","author":"Wang","year":"2021","journal-title":"BMC Anesthesiol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"e24297","DOI":"10.1002\/jcla.24297","article-title":"Prognostic nutrition index is associated with the all-cause mortality in sepsis patients: A retrospective cohort study","volume":"36","author":"Wu","year":"2022","journal-title":"J Clin Lab Anal."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1605032","DOI":"10.3389\/fnut.2025.1605032","article-title":"Association between prognostic nutritional index and all-cause mortality in critically ill patients with ventilator-associated pneumonia: a retrospective study based on MIMIC-IV database","volume":"12","author":"Ji","year":"2025","journal-title":"Front Nutr."},{"key":"B23","doi-asserted-by":"publisher","first-page":"738","DOI":"10.3390\/diagnostics14070738","article-title":"Relationship between Prognostic Nutritional Index and Amputation in Patients with Diabetic Foot Ulcer","volume":"14","author":"Coskun","year":"2024","journal-title":"Diagnostics."},{"key":"B24","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1016\/j.clnu.2013.01.007","article-title":"Performance of the Geriatric Nutritional Risk Index in predicting 28-day hospital mortality in older adult patients with sepsis","volume":"32","author":"Lee","year":"2013","journal-title":"Clin Nutr."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1258037","DOI":"10.3389\/fmed.2023.1258037","article-title":"Association between geriatric nutritional risk index and 28 days mortality in elderly patients with sepsis: a retrospective cohort study","volume":"10","author":"Li","year":"2023","journal-title":"Front Med (Lausanne)."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1450","DOI":"10.1038\/s41598-025-28609-y","article-title":"Prognostic nutritional indices predict 60 day mortality in ICU patients with sepsis","volume":"15","author":"Fang","year":"2025","journal-title":"Sci Rep."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1359","DOI":"10.3390\/nu16091359","article-title":"Prognostic Nutritional Index and Instant Nutritional Assessment Are Associated with Clinical Outcomes in a Geriatric Cohort of Acutely Inpatients","volume":"16","author":"Capurso","year":"2024","journal-title":"Nutrients."},{"key":"B28","doi-asserted-by":"publisher","first-page":"41370","DOI":"10.18632\/oncotarget.5629","article-title":"Prognostic significance of the combination of preoperative hemoglobin, albumin, lymphocyte and platelet in patients with gastric carcinoma: a retrospective cohort study","volume":"6","author":"Chen","year":"2015","journal-title":"Oncotarget."},{"key":"B29","doi-asserted-by":"publisher","first-page":"109496","DOI":"10.1016\/j.intimp.2022.109496","article-title":"Hemoglobin, albumin, lymphocyte, and platelet (HALP) score and cancer prognosis: A systematic review and meta-analysis of 13,110 patients","volume":"114","author":"Xu","year":"2023","journal-title":"Int Immunopharmacol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"153","DOI":"10.18632\/oncotarget.28367","article-title":"What is hemoglobin, albumin, lymphocyte, platelet (HALP) score? A comprehensive literature review of HALP's prognostic ability in different cancer types","volume":"14","author":"Farag","year":"2023","journal-title":"Oncotarget."},{"key":"B31","doi-asserted-by":"publisher","first-page":"1206958","DOI":"10.3389\/fnut.2023.1206958","article-title":"Evaluating the baseline hemoglobin, albumin, lymphocyte, and platelet (HALP) score in the United States adult population and comorbidities: an analysis of the NHANES","volume":"10","author":"Antar","year":"2023","journal-title":"Front Nutr."},{"key":"B32","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1186\/s12879-025-10739-3","article-title":"The relationship between hemoglobin, albumin, lymphocyte, and platelet (HALP) score and 28-day mortality in patients with sepsis: a retrospective analysis of the MIMIC-IV database","volume":"25","author":"Li","year":"2025","journal-title":"BMC Infect Dis."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1002\/sim.3841","article-title":"Dose-response analyses using restricted cubic spline functions in public health research","volume":"29","author":"Desquilbet","year":"2010","journal-title":"Stat Med."},{"key":"B34","doi-asserted-by":"publisher","first-page":"e38082","DOI":"10.2196\/38082","article-title":"Predicting Mortality in Intensive Care Unit Patients With Heart Failure Using an Interpretable Machine Learning Model: Retrospective Cohort Study","volume":"24","author":"Li","year":"2022","journal-title":"J Med Internet Res."},{"key":"B35","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1093\/postmj\/qgad144","article-title":"Explainable artificial intelligence model for mortality risk prediction in the intensive care unit: a derivation and validation study","volume":"100","author":"Hu","year":"2024","journal-title":"Postgrad Med J."},{"key":"B36","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1186\/s12911-024-02630-z","article-title":"Prediction of sepsis mortality in ICU patients using machine learning methods","volume":"24","author":"Gao","year":"2024","journal-title":"BMC Med Inform Decis Mak."},{"key":"B37","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":"B38","doi-asserted-by":"publisher","first-page":"4230","DOI":"10.1002\/sim.9025","article-title":"Minimum sample size for external validation of a clinical prediction model with a binary outcome","volume":"40","author":"Riley","year":"2021","journal-title":"Stat Med."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-023-01945-2","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data."}],"container-title":["Frontiers in Nutrition"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1949102\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:30:13Z","timestamp":1789533013000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1949102\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":39,"alternative-id":["10.3389\/fnut.2026.1949102"],"URL":"https:\/\/doi.org\/10.3389\/fnut.2026.1949102","relation":{},"ISSN":["2296-861X"],"issn-type":[{"value":"2296-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1949102"}}