Predictive Model Development for Invasive Syndrome in Type 2 Diabetes Mellitus Patients with Klebsiella pneumoniae Liver Abscess: A 5-Year Multi-Center Retrospective Case-Control Study

Objective To develop and validate a robust nomogram for predicting the risk of invasive Klebsiella pneumoniae liver abscess syndrome (IKPLAS) in patients with type 2 diabetes mellitus (T2DM) and Klebsiella pneumoniae liver abscess. Methods This multi-center retrospective case-control study analyzed clinical data from 213 patients with T2DM and Klebsiella pneumoniae liver abscess, treated between January 1, 2019, and January 1, 2024, at Beijing Rehabilitation Hospital, Capital Medical University; The Sanming Integrative Medicine Hospital; and The First Affiliated Hospital of Guangzhou Medical University. Patients were divided into IKPLAS (n = 25) and non-IKPLAS (Non-IKPLAS, n = 188) groups. Variables including fasting blood glucose (FBG), hemoglobin (Hb), blood urea nitrogen (BUN), abscess size, and Sequential Organ Failure Assessment (SOFA) score were evaluated. Lasso regression and multivariate logistic regression analyses were performed to identify significant predictors, which were then used to construct a nomogram. The model's performance was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Results The multivariate logistic regression identified FBG (OR = 1.20, 95% CI: 0.98–1.48, P = 0.006), Hb (OR = 0.90, 95% CI: 0.86–0.95, P < 0.001), BUN (OR = 1.22, 95% CI: 1.03–1.43, P = 0.017), abscess size (OR = 0.76, 95% CI: 0.61–0.94, P = 0.010), and SOFA score (OR = 3.08, 95% CI: 2.18–4.36, P < 0.001) as significant predictors of IKPLAS. The nomogram demonstrated excellent predictive capability, with an area under the ROC curve (AUC) of 0.966 (95% CI: 0.943–0.989) in the training set and 0.946 (95% CI: 0.902–0.991) in the validation set. Calibration curves indicated strong concordance between predicted and observed outcomes. The DCA showed that the nomogram provided significant clinical net benefit, particularly within the risk threshold range of 0.10 to 0.40. Conclusion The developed nomogram is an effective tool for predicting the risk of IKPLAS in patients with T2DM and Klebsiella pneumoniae liver abscess. It enables early identification of high-risk patients, thereby supporting timely clinical intervention and improving patient prognosis.