Logistic model of SMPP occurrence.

Mycoplasma pneumoniae (MP) is the primary causative agent of community-acquired pneumonia. Severe mycoplasma pneumoniae pneumonia (SMPP) can result in multiorgan damage and even respiratory failure or death. This study aimed to evaluate the predictive value of the Systemic Immune-Inflammation Index (SII) for SMPP. This retrospective study included 254 hospitalized children with MP infections (SMPP group, n = 103; non-SMPP group, n = 151). Patient data, including complete blood count parameters (white blood cell, absolute neutrophil, absolute lymphocyte, absolute monocyte, and platelet counts), C-reactive protein (CRP), serum amyloid A (SAA), and other markers, were collected. Furthermore, the SII, Systemic Inflammation Response Index (SIRI), neutrophil/lymphocyte ratio (NLR), monocyte/lymphocyte ratio (MLR), and platelet/lymphocyte ratio (PLR) were calculated. T-tests and the Mann–Whitney U test were used to analyze differences between the groups. Logistic regression was applied to analyze the risk factors. Receiver operating characteristic (ROC) curves were plotted to evaluate the predictive performance of the SII and CRP for SMPP. The SMPP group exhibited significantly higher CRP and SAA levels, SII, NLR, MLR, PLR, and SIRI than the non-SMPP group (all P < 0.001). Logistic regression revealed that the SII (odds ratio [OR] = 1.006, 95% confidence interval [CI]: 1.001–1.010) and CRP (OR = 1.080, 95% CI: 1.041–1.120) were independent risk factors. ROC curve of the SII (area under the ROC curve = 0.883, sensitivity = 0.699, and specificity = 0.881) outperformed that of CRP. Thus, SII can serve as an effective biomarker for SMPP prediction. It can be a rapid and cost-effective method when combined with routine blood tests, thereby demonstrating considerable potential for clinical application.