Abstract: OBJECTIVE To explore the etiology of skin flap infection after cochlear implantation, and to construct a predictive risk model. METHODS A total of 82 patients with skin flap infection after cochlear implantation admitted in Changzhou Second People's Hospital Affiliated to Nanjing Medical University were selected as the infection group between Aug. 2018 and Aug. 2021, and the etiological characteristics of patients with flap infection were statistically analyzed. And 207 patients without infection after cochlear implantation during the same period were selected as the control group. The general data between the two groups were compared. Multivariate Logistic regression was used to analyze the factors influencing postoperative skin flap infection, and a risk prediction model was constructed. The Hosmer-Lemeshow test and receiver operating characteristic (ROC) curves were used to assess the model fit and the predictive value of postoperative skin flap infection. RESULTS A total of 85 strains of pathogens were detected in 82 patients with skin flap infection, among which the detection rate of Gram-positive bacteria was higher than that of Gram-negative bacteria, and the detection rate of Staphylococcus aureus was higher than that of the other pathogens (P<0.05). Length of surgery, incision length, co-infection with other sites, and co-infection with chronic otitis media were the influencing factors for flap infection after cochlear implantation, and postoperative application of antimicrobial drugs was the protective factor (P<0.05). Multivariate Logistic regression analysis showed that risk prediction model for the development of postoperative skin flap infection in patients undergoing cochlear implantation was as follow: P=1/1+e^{(-1.985+0.524X operation time+0.986X incision length+0.801X infection in the other sites+0.843X chronic otitis media-0.764X postoperative prophylactic usage of antibiotics)}. Hosmer-Lemeshow test showed that fit between the model and the observed value was good (P=0.976). ROC curve analysis showed that area under the curve (AUC) for the prediction model to predict postoperative flap infection in patients with cochlear implantation was 0.880, 95%CI: 0.833-0.926. CONCLUSION The main pathogen of skin flap infection after cochlear implantation was Staphylococcus aureus. The risk prediction model established by multivariate Logistic regression analysis had a high predictive value for patients to develop skin flap infection after surgery.