Indices of systemic inflammation for predicting early infections after major joint arthroplasty

Background. Infectious complications after arthroplasty pose a serious problem for both the patient and the health facility. Therefore, their prognosis is of great clinical importance. The aim of the study — to determine the feasibility of using systemic inflammation indices (SII, SIRI, AISI) to predict the development of early periprosthetic joint infection at the stage of planning major joint arthroplasty. Methods. A single-center retrospective non-randomized comparative study of cases of primary hip or knee arthroplasty (n = 6036) was conducted: Group 1 — patients without subsequent development of infection at a period of ≤ 4 weeks after surgery (n = 5843); Group 2 — with subsequent development of periprosthetic joint infection (n = 193). Threshold values of quantitative indicators (BMI, age, inflammation indices SII, SIRI, and AISI) were calculated. The contribution of variables (including categorical ones such as sex and joint) to the risk of developing early infection was determined using AI-driven machine learning based on multivariate logistic regression. Results. The study groups were comparable in terms of sex, BMI, and operated joints, but differed in terms of age (p = 0.0067). The values of SIRI, SII, and AISI were statistically significantly higher in Group 2. SII (with a logistic regression 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 (95% CI: 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 0.30 and 0.50, and a high risk with a coefficient between 0.51 and 0.72. Conclusion. The use of systemic inflammation indices (SII, SIRI, AISI) in a mathematical model for predicting early periprosthetic infection can help in taking necessary measures for preoperative preparation of the patient before primary arthroplasty to reduce the incidence of this infectious complication.