Abstract / Summary
To develop and validate a predictive model for infectious diseases of the spine (IDS) utilizing peripheral blood laboratory indicators. This retrospective case-control study enrolled 292 patients with spinal disorders treated between January 2018 and April 2025. The cohort consisted of 190 IDS patients and 102 control patients without IDS. Variable selection was conducted using the least absolute shrinkage and selection operator (LASSO) regression, followed by multivariate logistic regression analysis to identify independent predictors of IDS and construct a predictive nomogram. The discriminative ability of the nomogram model was assessed via receiver operating characteristic (ROC) curve analysis. Model calibration was evaluated with calibration curves, while clinical utility was determined through decision curve analysis. Internal validation was performed via bootstrap resampling with 1000 iterations and 500 repeated 10-fold cross-validation. LASSO regression identified nine candidate predictors: lymphocytes (LY), hemoglobin (Hb), platelets, alanine aminotransferase, albumin, blood glucose, creatinine, C-reactive protein (CRP), and neutrophil-to-lymphocyte ratio (NLR). Logistic regression analysis showed that LY, Hb, CRP, and NLR were independent predictors of IDS, and all four indicators were incorporated into the nomogram model. The nomogram achieved an area under the curve of 0.847 (95% CI : 0.802–0.892). The calibration curve indicated excellent agreement between the model’s predicted outcomes and observed outcomes. Clinical decision curve analysis demonstrated that the model delivered a superior net benefit compared with alternative strategies when the threshold probability exceeded 10%. Internal validation yielded an overall accuracy of 0.779. The nomogram model, based on peripheral blood laboratory parameters, effectively predicts IDS. Level IV (Oxford CEBM 2011) retrospective singlecenter casecontrol observational study without external cohort validation.