Indices of systemic inflammation in predicting early infections after arthroplasty

Infectious complications after arthroplasty are a serious problem for both the patient and the medical institution, and their prognosis is of great clinical importance. The purpose of this study is to determine the feasibility of using systemic inflammation indices (SII, SIRI, AISI) to predict the risk of early infectious complications during the planning stage of major joint arthroplasty. Materials and methods. A single-center retrospective non-randomized comparative study of cases of primary hip or knee joint endoprosthetics (n=6036) was conducted: group 1 - patients without subsequent development of infection (n=5843); group 2 - with subsequent development of early deep or superficial infection in the endoprosthetic area (n=193). Threshold values of quantitative indicators (BMI, age, and inflammation indices - SII, SIRI, and AISI) were calculated, and the contribution of features (including non-categorical features such as gender and joint) to the risk of developing early infection was determined using machine learning based on multivariate logistic regression. Results. The study groups were comparable in terms of gender, BMI, and operated joints, but differed in terms of age (p=0.0067). The SIRI, SII, and AISI indices were statistically significantly higher in patients of group 2. The SII index (with a logistic function coefficient of 0.2108) was the most significant factor in predicting the development of infection. The obtained SII and SIRI threshold values were 498.9 and 0.8 (respectively), with an AUC of 0.55 (0.54–0.56). The constructed model for predicting the risk of early infection after arthroplasty based on multivariate logistic regression showed an average accuracy level of AUC=0.62 (95% CI: 0.30-0.72), indicating a low risk of infection with a coefficient between 0.3 and 0.5, and a high risk with a coefficient between 0.5 and 0.72. Conclusion. The use of a predictive model for the risk of early infectious complications can help in taking measures for preoperative preparation of the patient before primary endoprosthetics to reduce the risk of subsequent early infection.