{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:07:52Z","timestamp":1779944872835,"version":"3.53.1"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"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>Hospital-acquired pneumonia (HAP) is a frequent and serious complication following traumatic brain injury (TBI), leading to prolonged hospitalization and poor functional outcomes. Early identification of patients at high risk of HAP remains challenging. Systemic inflammation and nutritional status are recognized contributors to post-TBI infection susceptibility; however, these factors are not adequately incorporated into existing predictive models. This study aimed to develop and validate an inflammatory\u2013nutritional machine learning model for predicting HAP after TBI and to evaluate its prognostic stratification performance using an independent testing cohort from a second center.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 567 adult patients with TBI were included in this retrospective multicenter cohort study conducted at two hospitals. Patients were divided into a training set (n\u202f=\u202f396) and an independent testing set (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f171). Baseline laboratory data obtained within 24\u202fh of admission were used to calculate the Pan-Immune-Inflammation Value (PIV) and Prognostic Nutritional Index (PNI) scores. HAP, defined as occurring \u226548\u202fh after admission, was designated as the primary outcome, and functional prognosis at discharge was assessed using the modified Rankin Scale (mRS). Six machine learning models were constructed and compared. Model performance was evaluated using discrimination, calibration, decision curve analysis, and 10-fold cross-validation. Model interpretability was assessed with Shapley Additive Explanations (SHAP), and Kaplan\u2013Meier analyses were conducted for prognostic stratification.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The Light Gradient Boosting Machine exhibited the best overall performance, achieving an area under the receiver operating characteristic curve of 0.815 in the testing cohort, with good calibration and superior clinical net benefit. Cross-validation confirmed stable predictive capability. SHAP analysis identified PIV as the most influential predictor, followed by PNI, demonstrating consistent feature importance across cohorts. Model-derived risk stratification was significantly associated with functional outcomes, with high-risk patients exhibiting a markedly lower likelihood of favorable prognosis (mRS 0\u20132) in both cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The inflammatory\u2013nutritional machine learning model integrating PIV and PNI provides accurate and interpretable prediction of HAP after TBI and effectively stratifies functional prognosis, supporting its potential value for early risk assessment and future individualized decision-support in patients with TBI, pending prospective validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnut.2026.1785139","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:00:15Z","timestamp":1779944415000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An inflammatory\u2013nutritional machine learning model for risk stratification of hospital-acquired pneumonia in traumatic brain injury: a multicenter study"],"prefix":"10.3389","volume":"13","author":[{"given":"Chenzhu","family":"Cai","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, Jinjiang Municipal Hospital (Shanghai Sixth People\u2019s Hospital Fujian)","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Software, North University of China","place":["Taiyuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longjie","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Second Affiliated Hospital of Fujian Medical University","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanglu","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Second Affiliated Hospital of Fujian Medical University","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingfa","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Jinjiang Municipal Hospital (Shanghai Sixth People\u2019s Hospital Fujian)","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Qi","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Jinjiang Municipal Hospital (Shanghai Sixth People\u2019s Hospital Fujian)","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xieli","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Jinjiang Municipal Hospital (Shanghai Sixth People\u2019s Hospital Fujian)","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1097\/TA.0000000000002562","article-title":"Effects of hospital-acquired pneumonia on long-term recovery and hospital resource utilization following moderate to severe traumatic brain injury","volume":"88","author":"Kumar","year":"2020","journal-title":"J Trauma Acute Care Surg"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1097\/TA.0000000000000526","article-title":"Hospital-acquired pneumonia is an independent predictor of poor global outcome in severe traumatic brain injury up to 5 years after discharge","volume":"78","author":"Kesinger","year":"2015","journal-title":"J Trauma Acute Care Surg"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1089\/sur.2024.208","article-title":"Ventilator-associated pneumonia predicts severe cognitive disability in severe traumatic brain injury","volume":"26","author":"Srinivas","year":"2025","journal-title":"Surg Infect"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.bbi.2014.09.003","article-title":"Variable neuroendocrine-immune dysfunction in individuals with unfavorable outcome after severe traumatic brain injury","volume":"45","author":"Santarsieri","year":"2015","journal-title":"Brain Behav Immun"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1900","DOI":"10.3389\/fimmu.2018.01900","article-title":"Inflammasomes in tissue damages and immune disorders after trauma","volume":"9","author":"Bortolotti","year":"2018","journal-title":"Front Immunol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e58838","DOI":"10.1371\/journal.pone.0058838","article-title":"Nutritional support for patients sustaining traumatic brain injury: A systematic review and meta-analysis of prospective studies","volume":"8","author":"Wang","year":"2013","journal-title":"PLoS One"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"683","DOI":"10.3390\/nu15030683","article-title":"The assessment of the risk of malnutrition (undernutrition) in stroke patients","volume":"15","author":"Di Vincenzo","year":"2023","journal-title":"Nutrients"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1093\/jnci\/djaf325","article-title":"Prediagnostic dietary phytosterol intake, inflammatory biomarkers, and colorectal cancer survival: a cohort study","volume":"118","author":"Wu","year":"2025","journal-title":"J Natl Cancer Inst"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e572","DOI":"10.1016\/j.wneu.2024.02.077","article-title":"Prognostic nutritional index and the risk of postoperative complications after spine surgery: a meta-analysis","volume":"185","author":"Guo","year":"2024","journal-title":"World Neurosurg"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"108165","DOI":"10.1016\/j.jstrokecerebrovasdis.2024.108165","article-title":"Association between prognostic nutritional index and stroke: a nationally representative cross-sectional study from NHANES","volume":"34","author":"Pan","year":"2025","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"103257","DOI":"10.1016\/j.rpth.2025.103257","article-title":"Prognostic value of the Pan-immune-inflammation value for mortality in sepsis-induced coagulopathy: A medical information mart for intensive care study","volume":"9","author":"Yang","year":"2025","journal-title":"Res Pract Thromb Haemost"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1097\/SHK.0000000000001872","article-title":"Admission lymphopenia predicts infectious complications and mortality in traumatic brain injury victims","volume":"57","author":"Campbell","year":"2022","journal-title":"Shock"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1186\/s13054-019-2680-6","article-title":"Cortisol total\/CRP ratio for the prediction of hospital-acquired pneumonia and initiation of corticosteroid therapy in traumatic brain-injured patients","volume":"23","author":"Bouras","year":"2019","journal-title":"Crit Care"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"2406","DOI":"10.1161\/STROKEAHA.118.022352","article-title":"Safety and outcome of endovascular treatment in prestroke-dependent patients","volume":"49","author":"Goldhoorn","year":"2018","journal-title":"Stroke"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"2006","DOI":"10.1002\/14651858.CD001530.pub2","article-title":"Nutritional support for head-injured patients","author":"Perel","year":"2006","journal-title":"Cochrane Database Syst Rev"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"383","DOI":"10.3389\/fphar.2016.00383","article-title":"Dynamic profiling: Modeling the dynamics of inflammation and predicting outcomes in traumatic brain injury patients","volume":"7","author":"Constantine","year":"2016","journal-title":"Front Pharmacol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1161\/01.STR.0000258346.68966.9d","article-title":"Infection after acute ischemic stroke: a manifestation of brain-induced immunodepression","volume":"38","author":"Chamorro","year":"2007","journal-title":"Stroke"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/j.bbi.2009.04.006","article-title":"Detrimental consequences of brain injury on peripheral cells","volume":"23","author":"Catania","year":"2009","journal-title":"Brain Behav Immun"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.expneurol.2007.08.011","article-title":"Modulation of the cAMP signaling pathway after traumatic brain injury","volume":"208","author":"Atkins","year":"2007","journal-title":"Exp Neurol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"15787","DOI":"10.2147\/JIR.S551284","article-title":"A multicenter study of systemic inflammatory biomarkers for prognostic evaluation in iCCA patients","volume":"18","author":"Tao","year":"2025","journal-title":"J Inflamm Res"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"627","DOI":"10.21037\/gs.2019.10.10","article-title":"Novel lymphocyte to red blood cell ratio (LRR), neutrophil to red blood cell ratio (NRR), monocyte to red blood cell ratio (MRR) as predictive and prognostic biomarkers for locally advanced breast cancer","volume":"8","author":"Wang","year":"2019","journal-title":"Gland Surg"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.3389\/fimmu.2018.01256","article-title":"Dysregulated MicroRNA involvement in multiple sclerosis by induction of T helper 17 cell differentiation","volume":"9","author":"Chen","year":"2018","journal-title":"Front Immunol"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1622160","DOI":"10.1155\/2022\/1622160","article-title":"Low-density granulocytes in immune-mediated inflammatory diseases","volume":"2022","author":"Ning","year":"2022","journal-title":"J Immunol Res"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1177\/0003319715578258","article-title":"Association between platelet to lymphocyte ratio and saphenous vein graft disease","volume":"67","author":"Yayla","year":"2016","journal-title":"Angiology"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1186\/s12890-022-01928-w","article-title":"Pulmonary infection in traumatic brain injury patients undergoing tracheostomy: predicators and nursing care","volume":"22","author":"Zhang","year":"2022","journal-title":"BMC Pulm Med"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1385\/ncc:5:2:108","article-title":"Ventilator-associated pneumonia in severe traumatic brain injury","volume":"5","author":"Zygun","year":"2006","journal-title":"Neurocrit Care"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"3863","DOI":"10.2147\/IDR.S473825","article-title":"A machine learning model based on CT imaging metrics and clinical features to predict the risk of hospital-acquired pneumonia after traumatic brain injury","volume":"17","author":"Li","year":"2024","journal-title":"Infect Drug Resist"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1518599","DOI":"10.3389\/fneur.2025.1518599","article-title":"Risk factors analysis and prediction model construction of hospital-acquired pneumonia after traumatic brain injury","volume":"16","author":"Wei","year":"2025","journal-title":"Front Neurol"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"51","DOI":"10.3390\/diseases11010051","article-title":"Neutrophil to lymphocyte ratio as a predictor of postoperative outcomes in traumatic brain injury: a systematic review and meta-analysis","volume":"11","author":"Nguyen","year":"2023","journal-title":"Diseases"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"2419","DOI":"10.3389\/fimmu.2019.02419","article-title":"NLRX1 is a multifaceted and enigmatic regulator of immune system function","volume":"10","author":"Nagai-Singer","year":"2019","journal-title":"Front Immunol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"177","DOI":"10.3340\/jkns.2024.0157","article-title":"Early adequate nutrition in ICU is associated with survival gain: retrospective cohort study in patient with traumatic brain injury","volume":"68","author":"Oh","year":"2025","journal-title":"J Korean Neurosurg Soc"}],"container-title":["Frontiers in Nutrition"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1785139\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:00:18Z","timestamp":1779944418000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1785139\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":31,"alternative-id":["10.3389\/fnut.2026.1785139"],"URL":"https:\/\/doi.org\/10.3389\/fnut.2026.1785139","relation":{},"ISSN":["2296-861X"],"issn-type":[{"value":"2296-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]},"article-number":"1785139"}}