Predictors Of Surgical Site Infection Research Articles

Clinical evaluation of platelet-to-albumin ratio as a predictor of surgical site infection in pediatric patients with ulcerative colitis.

This study explored the predictive factors for surgical site infection (SSI) in a pediatric ulcerative colitis (UC) population. Data from 35 patients with UC who underwent surgery before 15years at Mie University Hospital between January 2000 and December 2022 were retrospectively reviewed. Potential preoperative and intraoperative predictors of SSI, including various demographic and clinical variables, were analyzed using the Mann-Whitney U test and logistic regression analysis. The optimal cutoff value for the variables was determined by examining the receiver operating characteristic curve. Of the 35 patients, 8 (22.9%) experienced SSI. The platelet-to-albumin ratio (PAR) is a more accurate predictor of SSI occurrence than the serum albumin level, platelet count, or C-reactive protein level. The sensitivity and specificity of PAR were 75.0% and 77.8%, respectively, with an area under the curve (AUC) of 0.782 (p = 0.018). A multivariable analysis revealed that preoperative PAR was the only significant independent predictor (cutoff value: 115,000, p = 0.047) when the optimal cutoff value was applied rather than the median value. This study demonstrated the value of the preoperative PAR in the management of pediatric patients with UC. Assessing the patient's PAR before surgery allows proactive treatment to reduce the risk of SSI.

Preoperative Hemoglobin Level Predicts Surgical Site Infections in Trauma Orthopedic Surgery: A Cohort Study

Background: Surgical site infections resulting from trauma orthopedic surgery increase morbidity and mortality rates and generate additional costs for the healthcare system. Preoperative and postoperative blood parameters have been described as risk predictors for surgical site infection in other surgical areas. The purpose of this study was to assess the role of preoperative and postoperative hematological parameters in predicting the risk of surgical site infections in trauma orthopedic surgery.Methods: Data on patients’ demographics were collected from their medical records and the operation reports. Preoperative and postoperative blood samples were collected for a complete blood count assay. The blood cell parameters as predictors of surgical site infection after trauma orthopedic surgery were determined by the Mann–Whitney U test to assess the differences in the median between the dependent and independent variables. p value < 0.05 was considered statistically significant.Results: Out of the 210 patients who were followed postsurgery, 14 (6.7%) developed surgical site infection following trauma orthopedic surgery. The mean age of the study participants was 33.08 ± 19.23 (Mean ± SD), with a range of 86 to 0.67 years old. Low preoperative hemoglobin level was identified as a predictor of surgical site infection following trauma orthopedic surgery (p = 0.019). None of the postoperative blood parameters measured was significantly associated with surgical site infections after trauma orthopedic surgery in Northern Ghana.Conclusion: In conclusion, our study demonstrates that preoperative hemoglobin level is a useful hematological parameter for predicting surgical site infection following trauma orthopedic surgery. These inexpensive and common hematological parameters could assist in guiding preventive efforts to reduce surgical site infections and improve outcomes for vulnerable patients undergoing trauma orthopedic surgery. Assessing preoperative hemoglobin levels is crucial in identifying patients at increased risk of developing surgical site infections. Preoperative optimization, including incorporating hemoglobin levels into predictive risk models can help to assess these at‐risk persons better. Educate patients on the need to optimize their hemoglobin levels before surgery and discuss potential interventions, including iron supplementation or transfusion.

Assessment of the American College of Surgeons Surgical Risk Calculator (ACS-SRC) for Prediction of Early Postoperative Complications in Patients Undergoing Cytoreductive Surgery for Ovarian Peritoneal Carcinomatosis.

Ovarian cancer (OC) is diagnosed at a locally advanced stage in two-thirds of cases. The first line of treatment consists of cytoreductive surgery (CRS) combined with neoadjuvant and/or adjuvant chemotherapy. However, CRS can be associated with high rates of postoperative complications (POCs), and detection of fragile patients at high risk of POCs is important. The American College of Surgeons Surgical Risk Calculator (ACS-SRC) provides a predictive model for early POCs (30 days) for any given surgical procedure. This study aimed to evaluate the performance of the ACS-SRC in predicting the occurrence of early POCs for patients undergoing CRS for OC. This was a retrospective study that included patients undergoing CRS for advanced OC between January 2010 and December 2022. Early POCs were reviewed, and the rate of POCs was compared with those predicted by the ACS-SRC to evaluate its accuracy (i.e., discrimination and calibration). A total of 218 patients were included, 112 of whom underwent extensive surgery/resection. A total of 94 complications were recorded. This cohort demonstrated correct calibration of the ACS-SRC for the prediction of surgical site infection, readmission, and the need for nursing care post-discharge (NCPD; transfer to revalidation center or need for nursing care at home). Using both the discrimination and calibration methods, the score only predicted NCPD. In this study, the ACS-SRC was shown to be of little value for patients undergoing cytoreductive surgery for ovarian peritoneal carcinomatosis, as it only accurately predicted NCPD.

Identifying potential predictors of the risk of surgical site infection following cardiac surgery: a scoping review.

This scoping review was undertaken to identify risk prediction models and pre-operative predictors of surgical site infection (SSI) in adult cardiac surgery. A particular focus was on the identification of novel predictors that could underpin the future development of a risk prediction model to identify individuals at high risk of SSI, and therefore guide a national SSI prevention strategy. A scoping review to systematically identify and map out existing research evidence on pre-operative predictors of SSI was conducted in two stages. Stage 1 reviewed prediction modelling studies of SSI in cardiac surgery. Stage 2 identified primary studies and systematic reviews of novel cardiac SSI predictors. The search identified 7887 unique reports; 7154 were excluded at abstract screening and 733 were selected for full-text assessment. Twenty-nine studies (across 30 reports) were included in Stage 1 and reported the development (N=14), validation (N=13), or both development and validation (N=2) of 52 SSI risk prediction models including 67 different pre-operative predictors. The remaining 703 reports were re-assessed in Stage 2; 49 studies met the inclusion criteria, and 56 novel pre-operative predictors that have not been assessed previously in models were identified. This review identified 123 pre-operative predictors of the risk of SSI following cardiac surgery, 56 of which have not been included previously in the development of cardiac SSI risk prediction models. These candidate predictors will be a valuable resource in the future development of risk prediction scores, and may be relevant to prediction of the risk of SSI in other surgical specialities.

Can machine learning models improve the prediction of surgical site infection in abdominal surgery than traditional statistical models?

To externally validate by revision and update the study on the efficacy of nosocomial infection control (SENIC) model of surgical site infection (SSI) using logistic regression (LR) and machine learning (ML) approaches. A retrospective analysis of hospital database-derived data from patients that had undergone gastrointestinal, colorectal and hernia surgeries (identified by ICD-9-CM). The SENIC index was calculated and fitted in an LR. MLs were developed using decision-tree (DT), random forest (RF), extreme-gradient-boosting (XGBoost) and Naïve Bayes (NB). The prevalence of an SSI was 3.21% (404 of 12 596 surgeries; 95% confidence interval [CI] 2.91%, 3.53%). The C-statistic for the original SENIC model was 0.668 (95% CI 0.648, 0.688) with an observed/expected (O/E) ratio of 0.998 (interquartile range [IQR] 0.750, 1.047). An updated-SENIC-LR model with six predictors had a C-statistic of 0.768 (95% CI 0.745, 0.790) and O/E ratio of 0.999 (IQR 0.976, 1.004). The performance of MLs considering 14 predictors was poorer than the updated-SENIC-LR with C-statistics of 0.679, 0.675, 0.656 and 0.651 for NB, XGBoost, RF and DT, respectively. Overfitting was detected for ML approaches, particularly for DT, RF and XGBoost. The updated-SENIC-LR model and NB may be useful for monitoring SSI risk following abdominal surgery.

Predictive Value of Preoperative Peripheral Blood Inflammatory Markers for Surgical Site Infection in Laparoscopic Radical Gastrectomy for Gastric Cancer.

Background: To investigate the predictive value of preoperative peripheral blood inflammatory markers for surgical site infection (SSI) in laparoscopic radical gastrectomy for gastric cancer. Methods: A retrospective analysis was conducted on patients undergoing laparoscopic radical gastrectomy for gastric cancer, categorized into SSI and non-SSI groups based on postoperative SSI occurrences. Patient demographics, surgical details, laboratory results, and SSI incidence data were extracted. Differences in indicators, including neutrophil-lymphocyte ratio (NLR), systemic immune-inflammation index (SII), and platelet-lymphocyte ratio (PLR), were assessed between the two groups. Multivariate logistic regression was utilized to determine the independent association of each indicator with SSI. Receiver operating characteristics (ROC) curve analysis was utilized to evaluate the predictive value of parameters. Results: Of 169 patients, 36 (21.30%) experienced SSI postoperatively. The SSI group exhibited higher preoperative NLR and SII (p < 0.05). After adjusting for variables, preoperative NLR (OR = 1.691, 95% CI: 1.211-2.417, p = 0.003) and SII (OR = 1.001, 95% CI: 1.000-1.002, p = 0.006) were identified as independent risk factors for SSI. Both NLR (AUC = 0.758, 95% CI: 0.666-0.850) and SII (AUC = 0.753, 95% CI: 0.660-0.850) demonstrated favorable diagnostic performance for predicting postoperative SSI. Conclusion: Preoperative NLR and SII significantly associate with postoperative SSI in laparoscopic radical gastrectomy for gastric cancer, making them valuable indicators for early prediction of SSI.

Evaluating XGBoost’s predictive accuracy on surgical site Infections in cardiac surgery

Abstract Background Surgical site infections (SSIs) pose a significant threat in cardiac surgery (CS), profoundly impacting patient prognosis. SSI incidence varies widely, reported between 3.5% and 26.8%. The study used a decade-long dataset from SSI surveillance in a specialized hospital in Italy, applying machine learning (ML) techniques to predict the SSI incidence among CS patients. Methods Data collected from 2013-2023 through the surveillance system of SSI in patients undergoing CS were used to train a predictive ML algorithm (XGBoost). Data included information on demographics, risk factors, surgery variables (incision site, prophylaxis, etc.), and the infection outcome derived from follow-up interviews at 30 days post-surgery, or 90 days for patients with prosthetic materials, according to the ECDC case definition of SSI. We used the R libraries “caret”, “smotefamily” and “xgboost” to train the algorithm. A train-test split of 70-30 was applied. Both downsampling of the majority class (no SSI) and oversampling of SSI cases with SMOTE were used in the training set to address class imbalance. Results A total of 10,534 subjects (65.9% males, mean age 68.3 years) who underwent CS (64.3% with prosthetic materials) were included, among which 533 SSIs were identified (mean incidence of 5.06%), with 430 cases (80.7%) occurring after discharge (38.7% deep SSI) and 103 (19.3%) before discharge (55.5% deep SSI). The trained XGBoost algorithm achieved an AUC of 0.62, sensitivity of 69%, and specificity of 50% in the prediction of SSI on the test dataset. Conclusions These findings suggest that while the XGBoost model provides a fair predictive capability, there is significant room for improvement in sensitivity and specificity. The use of artificial intelligence offers a promising opportunity to identify patients at risk of SSI. However, further research and comprehensive data are needed to refine the predictive model and effectively improve prevention measures. Key messages • Predominantly occurring post-discharge, SSIs in cardiac surgery necessitate enhanced prevention strategies, highlighting the critical phase after hospital discharge where surveillance is paramount. • Artificial intelligence may enhance post-discharge SSI surveillance, promising to identify patients at increased risk. Further research is needed to refine these AI tools for optimal sensitivity.

Risk-Adapted Use of Vancomycin in Secondary Scoliosis Surgery May Normalize SSI Risk in Surgical Correction of High-Risk Patients.

Introduction: Intrawound application of vancomycin is becoming increasingly controversial for the prevention of surgical site infection (SSI). As children undergoing spinal fusion for secondary scoliosis are at high risk for SSIs, evidence regarding the impact of intraoperative vancomycin installation on SSI rates in these patients is of utmost importance. Methodology: A single surgeon cohort of patients under 18 years of age undergoing surgery for secondary scoliosis in 2017 was analyzed with regard to the development of SSIs requiring surgical revision and adverse events. Use of vancomycin was restricted to cases with higher risk of infection. Patients undergoing distraction surgery for growing devices were excluded. Results: After exclusions, 64 patients remained (vancomycin n = 39, control n = 25). The SSI rates were 12.8% in patients receiving vancomycin (n = 5/39) and 4% in the control group (n = 1/25, p = 0.785). None of the patients suffered from adverse events. Univariable logistic regression revealed younger age (p = 0.03) and meningomyelocele as predictors for SSI (p = 0.006), while the high-risk group receiving vancomycin was not at higher odds for SSI, also after adjustment for possible confounders such as age or MMC (p = 0.031; p = 0.009). Discussion: SSI rates were comparable between groups, suggesting a normalization of SSI risk in the vancomycin-treated patients with a preoperatively increased risk of SSI. Future, larger studies in these rare diseases are needed to confirm these results.

Butyrylcholinesterase levels correlate with surgical site infection risk and severity after colorectal surgery: a prospective single-center study.

Surgical site infections (SSIs) after colorectal surgery remain a significant concern, which warrants effective predictive markers for prompt diagnosis and treatment. Butyrylcholinesterase (BChE), a non-specific cholinesterase enzyme, has been correlated with the risk of hepatic dysfunction progression and, more recently, infectious diseases and septic shock with ongoing research into the utility of BChE in multiple systemic inflammatory conditions. Whether these preliminary results can be translated into predicting infection after colorectal surgery remains in remains in question. This prospective study aimed to assess BChE's potential as a predictive marker for surgical site infections and anastomotic leaks after colorectal surgery. This single-center prospective study (11/2019-05/2023) enrolled 402 patients who underwent colorectal surgery. BChE levels were measured at four postoperative time points. The primary endpoints focused on BChE's association with complications, particularly surgical site infections (SSIs). Further known predictors of SSI were utilized to construct multivariable models to assess for independent association with SSI development. During the third and fifth day postsurgery, SSI patients had significantly lower mean BChE levels (3.90 KU/L vs. 4.54 KU/L p-value < 0.05, and 4.14 KU/L vs. 4.73 KU/L, p-value < 0.05; t-test, respectively). However, multivariate analysis revealed that when adjusted for other factors, low BChE levels on the first postoperative day were associated with 2.6 times higher odds of developing SSI (OR: 2.6, 95%CI: 1.3-3.9, p-value < 0.05). Similar results were found for low BChE levels on the third postoperative day as they were associated with a. 2.53 times higher odds for developing SSI (OR: 2.5, 95%CI: 1.27-3.87, p-value < 0.05) when adjusted for other factors. In conclusion, in this prospective observational study, low levels in the first and third postsurgery were associated with an increased risk for the development of SSIs but not sepsis.

Geriatric nutritional risk index as a predictor for surgical site infection in malignant musculoskeletal tumours of the trunk.

Surgical site infection (SSI) is common in surgery for malignant musculoskeletal tumours, specifically those arising from the trunk. In this study, we investigated the risk factors for SSI after resection of musculoskeletal tumours of the trunk. This retrospective observational study included 125 patients (72 males, 53 females) with musculoskeletal tumours of the trunk in our hospital from 1 April 2008 to 31 August 2023. The incidence of SSI and its risk factors were investigated. SSI was observed in 26% (32/125), and the median time to SSI was 22days. On multivariate analysis, the following were identified as risk factors for SSI: tumours arising caudal to Jacoby's line (hazard ratio [HR] 4.04; P =.0107), soft tissue reconstruction (HR 3.43; P =.0131), and low Geriatric Nutritional Risk Index (GNRI) (HR 0.96; P =.0304). Patients were classified into two risk categories based on GNRI scores: the risk group (GNRI ≤98) and no risk group (>98). The risk group showed a significantly lower overall noninfection survival rate (P =.023). Tumours arising caudal to Jacoby line, soft tissue reconstruction, and lower GNRI were risk factors for SSI. Preoperative and postoperative nutritional interventions should be considered to improve GNRI.

541 Development and External Validation of the “Global Surgical-Site Infection” (GloSSI) Predictive Model in Adult Patients Undergoing Abdominal Surgery

Abstract Aim To develop a novel prognostic score to predict 30-day surgical-site infection (SSI) following gastrointestinal surgery, and externally validate in comparison to existing prognostic models. Method This was a secondary analysis of 3 independent prospective international cohort studies conducted on a global basis. This included adults undergoing gastrointestinal surgery. Model development was performed in the GlobalSurg-2 dataset (January-July 2016). The primary outcome was 30-day SSI, with two predictive techniques explored: penalised regression (LASSO) and machine learning (XGBOOST). Final model selection based on prognostic accuracy (Area Under the Curve [AUC], 95% confidence interval) and clinical utility. Novel and previous scores were externally validated in GlobalSurg-1 (July-November 2014), and GlobalSurg-3 (April-October 2018). Results 30,029 patients were eligible: 14,019 (SSI=12.3%) in the derivation cohort, and 8,464 (SSI=11.4%) and 7,546 (SSI=15.7%) in the validation cohorts (GlobalSurg-1 and GlobalSurg-3 respectively). The LASSO model was selected due to similar discrimination to XGBoost in the GlobalSurg-2 dataset (AUC: 0.738, 0.725-0.750 versus 0.737, 0.709-0.765), but greater explainability. The final GloSSI score included six variables: country income, ASA, diabetes, and operative contamination, approach, and duration. Discrimination remained good on external validation in GlobalSurg-1 (AUC: 0.730, 0.715-0.744), but moderate discrimination in GlobalSurg-3 (AUC: 0.606, 95% CI 0.588-0.623). Nonetheless, this demonstrated superior performance to external validation of all previous models evaluated within GlobalSurg or prior datasets. Conclusions The GloSSI score allowed accurate prediction of SSI with 6 simple variables routinely available at surgery across income settings. This can inform use of intraoperative and postoperative interventions to modify the risk of SSI and minimise associated harm.

Clinical relevance of positive intraoperative bacterial culture in tibial plateau leveling osteotomy in dogs: a retrospective study

BackgroundTibial plateau leveling osteotomy (TPLO) belongs to the most frequently used surgical method for the treatment of cranial cruciate ligament rupture in dogs. Surgical site infection (SSI) is one of the possible postoperative complications. The aim of this study was to evaluate the diagnostic value of intraoperative bacterial culture as a tool for the detection of intraoperative bacterial contamination progressing to infection development in canine TPLO. Electronic patient records from dogs who underwent TPLO between January 2018 to December 2020 were retrospectively reviewed. Intraoperative bacterial culture results, used antimicrobial drugs and presence of SSI were recorded.ResultsNinety-eight dogs were included in the study. SSI rate was 10.2%. All dogs who developed SSI (n = 10) had negative intraoperative bacterial cultures. None of the dogs with positive intraoperative bacterial culture (n = 6) developed SSI. The most cultured bacteria causing SSI was Staphylococcus pseudintermedius (n = 4).ConclusionsIntraoperative bacterial culture in dogs undergoing TPLO is not suitable as a predictor of surgical site infection.

Analysing predictors of surgical site infections in patients undergoing emergency surgery for traumatic pulmonary haemorrhage.

Identifying predictors for surgical site infections (SSIs) after emergency surgical treatment for traumatic pulmonary haemorrhage (TPH) is crucial for improving patient outcomes. This study aims to ascertain these predictors. In this comprehensive retrospective study, conducted from January 2020 to December 2023 at our institution, 75 patients were analysed, including a case group of 25 patients with SSIs and a control group of 50 without SSIs post-TPH surgery. Inclusion criteria focused on patients aged 18 and above undergoing thoracotomy or minimally invasive thoracic surgery for TPH. Exclusion criteria included compromised immune systems, chronic pulmonary diseases, prior thoracic surgery or active infections at admission. We assessed several predictors: anaemia; operation time over 2 h; hospital stay over 5 days; intraoperative blood loss exceeding 500 mL; body mass index (BMI) ≥25 kg/m2; age ≥ 50 years; use of surgical drains; the presence of open wounds; diabetes mellitus and non-prophylactic antibiotic use. Statistical analysis involved univariate and multivariate logistic regression, using SPSS Version 27.0. Univariate analysis revealed significant associations between SSIs and surgical drain placement, diabetes mellitus, open wounds and non-prophylactic antibiotic use (p < 0.01). Multivariate analysis confirmed these factors as significant predictors of SSIs, with notable odds ratios. Other variables like anaemia, extended hospital stay, excessive intraoperative blood loss, older age and higher BMI did not significantly predict SSIs. Significant predictors for SSIs following TPH surgery include surgical drain placement, diabetes mellitus, open wounds and non-prophylactic antibiotic use. Identifying and managing these risks is crucial in clinical practice to reduce SSIs incidence and improve patient outcomes.

Post-operative site infections among surgical patients at Southern Ethiopia: A prospective cohort study

ObjectiveThe current study was conducted to estimate the magnitude of SSI among surgically treated patients and identify the predictors associated with it. Backgroundsummary: Despite the fact that surgical site infection (SSI) is still a global health care-associated infection related to patients' discomfort, morbidity, and mortality, it is the most preventable nosocomial infection if all necessary measures are taken into account. MethodsAn institution-based prospective cohort study was conducted at a large teaching hospital in southern Ethiopia. Patients admitted to the surgical ward with a non-traumatic acute abdomen were participants in the study and were followed prospectively for 30 days. The collected data was entered into Epi-Data 4 and exported to STATA 16 for analysis. A logistic regression (bi-variable and multivariable) model was computed to detect the association between SSI and predictors. In the final model, variables with a p-value <0.05 were declared statistically significant. ResultsIn this study, a total of 169 patients were enrolled. More than 3/4th (78.9%) of them were male, and the mean ± SD age of participants was 42.14 ± 12.5 years. Eighteen participants (10.5%) suffered from surgical site infection (SSI). Predictors of SSI were ever smoking [AOR = 3.9; 95% CI (1.2–16.5)], American Society of Anesthesiologists score ≥3 [AOR = 8.9; 95% CI (1.7–45.5)], appendectomy [AOR = 7.7; 95% CI (1.3–45.7)], and co-morbid diabetes [AOR = 13.8; 95% CI (2.6–72.1)]. ConclusionThe magnitude of SSI was considerable in the study setting. Predictors of SSI were smoking, ASA score, appendectomy, and co-morbid diabetes. We strongly recommend that health-care professionals provide health education and patient counseling on smoking and health-seeking behaviors. Considering co-morbid conditions before surgery has paramount importance. Moreover, further large-scale studies are suggested.

Classification Models for Early Prediction of Surgical Site Infections

Nosocomial infections and antimicrobial resistance are problems of enormous magnitude that impact the morbidity and mortality of hospitalized patients as well as the cost of healthcare. Implementation of control policies and programs assumes an important role in reducing the negative impacts on patient welfare and hospital management. In this context, this study aims to analyze how the integration of data from different sources and analysis of risk factors and history pre- and post-surgery can help in the early detection of surgical site infection. For this project, data was collected from Hospital Senhora de Oliveira in Guimarães (HSOG), which concerns surgeries performed, admissions, emergency room visits, antibiotic prescriptions, and recorded infections. The results showed that it is possible to use predictive models for better infection management (models with SE above 88% and PC and AUC above 90%).

Timing of Surgery and Preoperative Predictors of Surgical Site Infections for Patients with Depressed Skull Fractures in a Sub-Saharan Tertiary Hospital: A Prospective Cohort Study.

Surgical site infections (SSIs) remain a major cause of life-threatening morbidity following surgery for depressed skull fractures (DSFs) among patients with traumatic brain injury (TBI). The timing of the surgery for DSF has been questioned as a risk of SSI without a clear cutoff. We aimed to compare the risk of SSI within 3 months between surgery done before versus after 48 h of injury and with its preoperative predictors. We conducted a prospective cohort study at Mulago Hospital, Uganda. Patients with mild-to-moderate TBI with DSF were followed up perioperatively from the operating time up to 3 months. The outcome variables were the incidence risk of SSI, types of SSI, microbial culture patterns of wound isolates, and hospital length of stay. We enrolled 127 patients with DSF, median age = 24 (interquartile range [IQR] = 17-31 years), 88.2% (112/127) male, and assault victims = 53.5%. The frontal bone involved 59%, while 50.4% had a dural tear. The incidence of SSI was 18.9%, mainly superficial incisional infection; Gram-negative microorganisms were the most common isolates (64.7%). The group of surgical intervention >48 h had an increased incidence of SSI (57.3% vs. 42.7%, p = 0.006), a longer median of postoperative hospital stay (8[IQR = 6-12] days versus 5 [IQR = 4-9], [p < 0.001]), and a higher rate of reoperation (71.4% vs. 28.6%, p = 0.05) in comparison with the group of ≤48 h. In multivariate analysis between the group of SSI and no SSI, surgical timing >48 h (95% confidence interval [CI], 1.25-6.22), pneumocranium on computed tomography [CT] scan (95% CI: 1.50-5.36), and involvement of air sinus (95% CI: 1.55-5.47) were associated with a >2.5-fold increase in the rate of SSI. The SSI group had a longer median hospital stay (p value <0.001). The SSI risk in DSF is high following a surgical intervention >48 h of injury, with predictors such as the frontal location of DSF, pneumocranium on a CT scan, and involvement of the air sinus. We recommend early surgical intervention within 48 h of injury.

Surgical Site Infections in Major Lower Limb Amputation: An International Multicentre Audit (SIMBA): Study Protocol

Background: Over 3,000 major lower limb amputations (MLLA) occur in the UK per annum. A significant proportion of patients following MLLA will go on to develop a surgical site infection (SSI). SSIs can range from a simple superficial infection that is treated with oral antibiotic therapy to deeper infections which can lead to wound dehiscence and, ultimately, surgical revision. SSIs can have a significant impact on patient mobility, function, morbidity and mortality as well as wider effects on carers, community services and hospital systems. Despite these potential impacts there are limited data to determine the rate of SSI in patients undergoing MLLA, adjuncts that successfully prevent SSI, factors that predispose patients to SSI and compliance with national guidance set out by key stakeholders in vascular surgical care. Methods: To address this gap in evidence we propose a large, international, prospective, collaborative audit that aims to compare current practice against recommendations set out by the National Institute of Health and Care Excellence and The Vascular Society of Great Britain and Ireland and to determine the frequency of significant outcomes related to SSI (as defined by the Centre for Disease Control) in consecutive patients undergoing MLLA over an 8-month period including the incidence of SSI, wound dehiscence and surgical revision at 30 days, frequency of use of adjuncts designed to reduce SSI and predictors of SSI. Outcomes will also be captured at 1 year post-MLLA if funding permits. Discussion: This multicentre audit will allow us to describe the incidence and burden of SSI and wound dehiscence in patients undergoing MLLA. The strengths of this audit will lie in its use of contemporaneous data collection from numerous hospitals and the in-depth data collection focusing primarily on MLLA SSI. It is anticipated that the audit will provide impactful data for future comparisons with global practice and support the design of robust and meaningful studies.

Machine learning application for prediction of surgical site infection after posterior cervical surgery.

Surgical site infection (SSI) is one of the most common complications of posterior cervical surgery. It is difficult to diagnose in the early stage and may lead to severe consequences such as wound dehiscence and central nervous system infection. This retrospective study included patients who underwent posterior cervical surgery at The Second Affiliated Hospital and Yuying Childrens Hospital of Wenzhou Medical University from September 2018 to June 2022. We employed several machine learning methods, such as the gradient boosting (GB), random forests (RF), artificial neural network (ANN) and other popular machine learning models. To minimize the variability introduced by random splitting, the results underwent 10-fold cross-validation repeated 10 times. Five measurements were averaged across 10 repetitions with 10-fold cross-validation, the RF model achieved the highest AUROC (0.9916), specificity (0.9890) and precision (0.9759). The GB model achieved the highest sensitivity (0.9535) and the KNN achieved the highest sensitivity (0.9958). The application of machine learning techniques facilitated the development of a precise model for predicting SSI after posterior cervical surgery. This dynamic model can be served as a valuable tool for clinicians and patients to assess SSI risk and prevent it in clinical practice.

1310. Prediction of Surgical Site Infection Following Ankle Fracture: A Machine Learning Approach

Abstract Background Surgical site infections (SSI) are a common complication in foot and ankle surgery. In the US, ankle fracture incidence is 4.22/10,000 person-years. The development of a predictive model for SSI in foot and ankle surgery may provide insights that would enable the prevention of wound complications to reduce their burden. In this study, we analyzed a patient data set to compare 5 different machine learning models and determine which is most effective in determining the risk for surgical site infection after ankle fracture. Methods We included 935 ankle fracture patients, of whom 114 patients developed SSI in the case group. We used the risk factors for SSI obtained from univariate analysis to develop 5 sets of models using the following machine learning (ML) methods: Decision Tree (DC), Random Forest (RF), Neural Network (NN), Gradient Boosting (GB), and Adaboost. Results In univariate analysis, older mean age (58.1 y.o. vs 49.3 y.o, p&amp;lt; 0.001), higher mean American Society of Anesthesia score (2.1 vs 1.9, p&amp;lt; 0.001), and longer hospital stay relating to the ankle fracture (6.3 days vs 4.1 days, p&amp;lt; 0.001) were correlated with SSI risk when compared to non-infected patients. We also demonstrated that factors such as the presence of an external fixation prior to the ORIF (OR=2.91, p&amp;lt; 0.001), diabetes (OR=2.00, p=0.03), oral steroid use (OR=3.45, p&amp;lt; 0.001), multiple fractures (OR=2.29, p=0.003), liver disease (OR=2.76, p=0.02), hypertension (OR=2.05, p&amp;lt; 0.001), illicit drug use (OR=2.31, p=0.01), smoking (OR=1.71, p=0.02), open wounds (OR=3.32, p&amp;lt; 0.001), and CCI (OR=1.73, p=0.04) were also correlated with a higher incidence of SSI as compared to our control group. Our machine learning models performed well, with AUCs ranging from 0.74 to 0.86. GB had the highest AUC (0.86) and other favorable metrics including an accuracy of 0.88, F1-score of 0.89, precision of 0.91, sensitivity of 0.88, and specificity of 0.77 (table 1).Table 1.Performance Metrics of the Machine Learning Prediction Model for SSI following Ankle Fracture Conclusion Early prediction of SSI risk may lead to strategies to prevent complications in high-risk patients after ankle fracture fixation. With the goals of enhancing patient outcomes, lowering healthcare costs, and optimizing the use of healthcare resources, machine learning models may enable the identification of patients at high risk of SSI for tailored preventive treatments. Disclosures All Authors: No reported disclosures

Hemoglobin A1c as a Predictor of Surgical Site Infection in Patients With Orthopaedic Trauma.

Previous research involving diabetes mellitus (DM), glycemic control, and complications in orthopaedic patients has primarily focused on elective procedures. The purpose of this study was to evaluate hemoglobin A1c (A1c) as a predictor of postoperative surgical site infection (SSI) in patients with orthopaedic trauma. Patients aged 18 years or older treated surgically for an acute fracture by a fellowship-trained orthopaedic trauma surgeon at a single academic tertiary referral center with a laboratory value for A1c available within 3 months of their surgery were identified retrospectively. Postoperative SSI was defined according to 'Fracture related infection: A consensus on definition from an international expert group,' by Metsemakers et al. A total of 925 patients met criteria for analysis. A receiver operating characteristic curve was calculated using A1c as a predictor for signs suggestive and confirmatory of SSI and demonstrated an area under the curve of 0.535 and 0.539, respectively. No significant difference was found in the rate of signs suggestive or confirmatory of SSI in patients with normal A1c levels (<6.5) compared with patients with A1c levels consistent with a diagnosis of DM (>6.5), P-value = 0.199 and P-value = 0.297, respectively. No significant difference was found in the rate of signs suggestive or confirmatory of SSI in patients with completely uncontrolled DM (A1c > 10) compared with patients with A1c levels <10, P-value 0.528 and P-value = 0.552, respectively. Existing literature has demonstrated an association with postoperative infection in orthopaedic patients who have elevated A1c values. In this cohort of patients with orthopaedic trauma, hemoglobin A1c was not a valuable tool to predict postoperative SSI. Given these findings, routine A1c monitoring is not a reliable predictor of SSI criteria in patients with orthopaedic trauma based on the current consensus definition of SSI in fracture surgery.