{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:04:22Z","timestamp":1789535062928,"version":"build-2803163510"},"reference-count":35,"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. Cell. Infect. Microbiol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Infectious spondylitis, encompassing spinal tuberculosis (STB), pyogenic spondylitis (PS), and brucellar spondylitis (BS), is difficult to diagnose preoperatively because the three entities present with overlapping clinical features. Differentiation is often delayed by prolonged culture turnaround times and the unavailability of serological testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this multicenter retrospective diagnostic study at five tertiary hospitals in China (2015\u20132023), patients with STB (n = 1,000), PS (n = 579), and BS (n = 255) were enrolled and assigned to derivation (n = 1,439) and external validation (n = 395) cohorts. We developed and validated a multimodal machine learning model that integrates routine preoperative clinical and laboratory variables with radiomic features extracted from non-contrast MRI. Unimodal, early fusion, and late fusion architectures were compared. Pathogen-specific serological tests were excluded from the primary model to avoid data leakage. We evaluated discrimination, calibration, clinical utility, and incremental value; SHAP analysis provided case-level interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The late fusion LightGBM model achieved the highest external validation performance (macro-averaged AUC 0.852, 95% CI 0.822\u20130.882). Radiomic integration provided significant incremental value over the clinical-only model (\u0394AUC 0.080; NRI 0.398; IDI 0.072). Calibration was good (Brier score 0.158), and decision curve analysis demonstrated positive net benefit across clinically relevant thresholds. SHAP analysis revealed class-specific, biologically plausible predictors: low serum albumin and elevated T1W GLCM contrast for STB; high CRP and NLR for PS; and residence in an endemic region for BS. Secondary analysis showed that adding serological tests yielded only modest incremental improvement (\u0394AUC 0.042).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This preoperative multimodal explainable AI model achieves accurate and interpretable differentiation of STB, PS, and BS using only routine clinical data and non-contrast MRI, although its sensitivity for BS remains limited and prospective validation is warranted. It may serve as a clinically actionable decision-support tool for preoperative triage, particularly when serological confirmation is pending or unavailable.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcimb.2026.1925786","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:31:20Z","timestamp":1789533080000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Preoperative differentiation of spinal tuberculosis, pyogenic, and brucellar spondylitis: a multimodal machine learning study across five centers"],"prefix":"10.3389","volume":"16","author":[{"given":"Xingyu","family":"Duan","sequence":"first","affiliation":[{"name":"Department of Orthopedics, General Hospital of Ningxia Medical University","place":["Yinchuan, China"]},{"name":"First Clinical Medical College, Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, General Hospital of Ningxia Medical University","place":["Yinchuan, China"]},{"name":"First Clinical Medical College, Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichao","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Zhoukou Central Hospital","place":["Zhoukou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxing","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, General Hospital of Ningxia Medical University","place":["Yinchuan, China"]},{"name":"First Clinical Medical College, Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghong","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Tuberculosis, Henan Infectious Disease Hospital (The Sixth People\u2019s Hospital of Zhengzhou)","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hekun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, General Hospital of Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of General Practice, The First People\u2019s Hospital of Zhengzhou","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wensheng","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Spinal and Spinal Cord Surgery, Henan Provincial People\u2019s Hospital","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningkui","family":"Niu","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, General Hospital of Ningxia Medical University","place":["Yinchuan, China"]},{"name":"Ningxia Key Laboratory of Clinical Pathogenic Microorganisms, General Hospital of Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.02754","article-title":"XGBoost: A Scalable Tree Boosting System","author":"Chen","year":"2016","journal-title":"arXiv [Preprint]"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"Bmj"},{"key":"B3","doi-asserted-by":"publisher","first-page":"847","DOI":"10.3855\/jidc.9265","article-title":"Development of an interferon-\u03b3 release assay (IGRA) for detection of Brucella abortus and clinical diagnosis of brucellosis","volume":"11","author":"Feng","year":"2017","journal-title":"J. Infect. Dev. Ctries"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pntd.0012030","article-title":"Diagnosis of human brucellosis: Systematic review and meta-analysis","volume":"18","author":"Freire","year":"2024","journal-title":"PloS Negl.Trop. Dis."},{"key":"B5","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1186\/s13018-025-05622-5","article-title":"MMP expression and its clinical significance in intervertebral disc destruction of spinal tuberculosis, Brucellar spondylitis, and pyogenic spondylitis","volume":"20","author":"Gao","year":"2025","journal-title":"J. Orthop. Surg. Res."},{"key":"B6","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1023\/A:1010920819831","article-title":"A simple generalisation of the area under the ROC curve for multiple class classification problems","volume":"45","author":"Hand","year":"2001","journal-title":"Mach. Learn."},{"key":"B7","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"Hanley","year":"1982","journal-title":"Radiology"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1016\/j.spinee.2024.12.035","article-title":"Comparative diagnostic accuracy of ChatGPT-4 and machine learning in differentiating spinal tuberculosis and spinal tumors","volume":"25","author":"Hu","year":"2025","journal-title":"Spine J."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2022.983579","article-title":"Analysis of the diagnostic efficacy of the QuantiFERON-TB Gold In-Tube assay for preoperative differential diagnosis of spinal tuberculosis","volume":"12","author":"Hu","year":"2022","journal-title":"Front. Cell. Infect. Microbiol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"401","DOI":"10.17305\/bb.2023.9663","article-title":"Development and validation of a diagnostic model to differentiate spinal tuberculosis from pyogenic spondylitis by combining multiple machine learning algorithms","volume":"24","author":"Huang","year":"2024","journal-title":"Biomol. Biomed."},{"key":"B11","doi-asserted-by":"publisher","first-page":"4229","DOI":"10.1007\/s00586-023-07683-8","article-title":"Utility of clinicoradiological, microbiological, histopathological, and molecular methods in the diagnosis of spinal tuberculosis","volume":"32","author":"Jain","year":"2023","journal-title":"Eur. Spine J."},{"key":"B12","doi-asserted-by":"publisher","first-page":"3305","DOI":"10.2147\/idr.S410914","article-title":"Clinical value of metagenomic next-generation sequencing using spinal tissue in the rapid diagnosis of spinal tuberculosis","volume":"16","author":"Jin","year":"2023","journal-title":"Infect. Drug Resist."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.2214\/ajr.182.6.1821405","article-title":"Discrimination of tuberculous spondylitis from pyogenic spondylitis on MRI","volume":"182","author":"Jung","year":"2004","journal-title":"AJR Am. J. Roentgenol."},{"key":"B14","first-page":"3146","article-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Ke","year":"2017"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1858","DOI":"10.1016\/j.spinee.2019.05.002","article-title":"Spinal tuberculosis: a comprehensive review for the modern spine surgeon","volume":"19","author":"Khanna","year":"2019","journal-title":"Spine J."},{"key":"B16","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1016\/j.spinee.2024.12.018","article-title":"Management of severe pyogenic spinal infections: the 2SICK study by the EANS spine section","volume":"25","author":"Kramer","year":"2025","journal-title":"Spine J."},{"key":"B17","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1093\/biostatistics\/kxs047","article-title":"Multicategory reclassification statistics for assessing improvements in diagnostic accuracy","volume":"14","author":"Li","year":"2013","journal-title":"Biostatistics"},{"key":"B18","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1186\/s13018-022-03250-x","article-title":"Neutrophil-lymphocyte ratio as a potential marker for differential diagnosis between spinal tuberculosis and pyogenic spinal infection","volume":"17","author":"Liu","year":"2022","journal-title":"J. Orthop. Surg. Res."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.tube.2024.102546","article-title":"Study on the role and molecular mechanism of METTL3-mediated miR-29a-3p in the inflammatory response of spinal tuberculosis","volume":"148","author":"Ma","year":"2024","journal-title":"Tuberculosis (Edinb)"},{"key":"B20","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1007\/s00586-025-08647-w","article-title":"Differences analysis between spinal tuberculosis and brucella spondylitis with preoperative non-invasive differential diagnosis","volume":"34","author":"Ma","year":"2025","journal-title":"Eur. Spine J."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1080\/24699322.2025.2599329","article-title":"Deep learning diagnosis model of spinal tuberculosis based on CT bone window gradient attention mechanism: multi-center study","volume":"31","author":"Mo","year":"2026","journal-title":"Comput. Assist. Surg. (Abingdon)"},{"key":"B22","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1002\/sim.2929","article-title":"Evaluating the added predictive ability of a new marker: from area under the ROC curve to reclassification and beyond","volume":"27","author":"Pencina","year":"2008","journal-title":"Stat. Med."},{"key":"B23","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1002\/sim.4085","article-title":"Extensions of net reclassification improvement calculations to measure usefulness of new biomarkers","volume":"30","author":"Pencina","year":"2011","journal-title":"Stat. Med."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108719","article-title":"The value of MRI radiomics in distinguishing different types of spinal infections","volume":"264","author":"Qin","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1002\/jsp2.1331","article-title":"Analysis of the value of potential biomarker S100-A8 protein in the diagnosis and pathogenesis of spinal tuberculosis","volume":"7","author":"Ren","year":"2024","journal-title":"JOR Spine"},{"key":"B26","doi-asserted-by":"publisher","first-page":"3154","DOI":"10.1007\/s00586-024-08286-7","article-title":"Trends in infectious spondylitis from 2000 to 2020","volume":"33","author":"Tanishima","year":"2024","journal-title":"Eur. Spine J."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2026.103902","article-title":"A multiparameter model (OsteoSC-M3) for early detection and risk stratification of osteoporosis in women: a multicentre cohort study in China","volume":"95","author":"Teng","year":"2026","journal-title":"EClinicalMedicine"},{"key":"B28","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/1754-9485.12157","article-title":"MR findings in spinal tuberculosis in an endemic country","volume":"58","author":"Thammaroj","year":"2014","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1186\/s12879-025-11331-5","article-title":"Diagnostic accuracy of T-SPOT.TB and TST in detecting active tuberculosis in patients with rheumatic immune diseases: a fully matched comparative study","volume":"25","author":"Wang","year":"2025","journal-title":"BMC Infect. Dis."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1567","DOI":"10.1186\/s12879-025-12101-z","article-title":"Clinical epidemiological characteristics and treatment outcomes of Brucella spondylitis in Ningxia, China: a 12\u2013year single\u2013center retrospective study","volume":"25","author":"Wang","year":"2025","journal-title":"BMC Infect. Dis."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1177\/03000605231195156","article-title":"MRI radiomics-based evaluation of tuberculous and brucella spondylitis","volume":"51","author":"Wang","year":"2023","journal-title":"J. Int. Med. Res."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1080\/07853890.2023.2249004","article-title":"Identification of spinal tuberculosis subphenotypes using routine clinical data: a study based on unsupervised machine learning","volume":"55","author":"Yao","year":"2023","journal-title":"Ann. Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1186\/s12879-025-11863-w","article-title":"Multimodal imaging-based interpretable radiomics for differentiating brucella and tuberculosis spondylitis: a two-center study","volume":"25","author":"Yimit","year":"2025","journal-title":"BMC Infect. Dis."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1653506","article-title":"Ensemble machine learning models for predicting bone metastasis in bladder cancer","volume":"15","author":"Yu","year":"2025","journal-title":"Front. Oncol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"45566","DOI":"10.1038\/s41598-025-28576-4","article-title":"The bacterial spectrum of spinal infections based on blood culture, tissue culture, and molecular methods: a systematic review and meta-analysis","volume":"15","author":"Zhang","year":"2025","journal-title":"Sci. Rep."}],"container-title":["Frontiers in Cellular and Infection Microbiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2026.1925786\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:31:28Z","timestamp":1789533088000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2026.1925786\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":35,"alternative-id":["10.3389\/fcimb.2026.1925786"],"URL":"https:\/\/doi.org\/10.3389\/fcimb.2026.1925786","relation":{},"ISSN":["2235-2988"],"issn-type":[{"value":"2235-2988","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1925786"}}