Dataset Information

Development of a Risk Prediction Model to Individualize Risk Factors for Surgical Site Infection After Mastectomy.

ABSTRACT: Little data are available regarding individual patients' risk of surgical site infection (SSI) following mastectomy with or without immediate reconstruction. Our objective was to develop a risk prediction model for mastectomy-related SSI.Using commercial claims data, we established a cohort of women <65 years of age who underwent a mastectomy from 1 January 2004-31 December 2011. International Classification of Diseases, Ninth Revision, Clinical Modification diagnosis codes were used to identify SSI within 180 days after surgery. SSI risk factors were determined with multivariable logistic regression using derivation data from 2004-2008 and validated with 2009-2011 data using discrimination and calibration measures.In the derivation cohort, 595 SSIs were identified in 7607 (7.8 %) women, and 396 SSIs were coded in 4366 (9.1 %) women in the validation cohort. Independent risk factors for SSIs included rural residence, rheumatologic disease, depression, diabetes, hypertension, liver disease, obesity, pre-existing pneumonia or urinary tract infection, tobacco use disorder, smoking-related diseases, bilateral mastectomy, and immediate reconstruction. Receipt of home healthcare was associated with lower risk. The model performed equally in the validation cohort per discrimination (C-statistics 0.657 and 0.649) and calibration (Hosmer-Lemeshow p = 0.091 and 0.462 for derivation and validation, respectively). Three risk strata were created based on predicted SSI risk, which demonstrated good correlation with the proportion of observed infections in the strata.We developed and internally validated an SSI risk prediction model that can be used to counsel women with regard to their individual risk of SSI post-mastectomy. Immediate reconstruction, diabetes, and smoking-related diseases were important risk factors for SSI in this non-elderly population of women undergoing mastectomy.

SUBMITTER: Olsen MA

PROVIDER: S-EPMC4929027 | biostudies-literature | 2016 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of a Risk Prediction Model to Individualize Risk Factors for Surgical Site Infection After Mastectomy.

Olsen Margaret A MA Nickel Katelin B KB Margenthaler Julie A JA Fox Ida K IK Ball Kelly E KE Mines Daniel D Wallace Anna E AE Colditz Graham A GA Fraser Victoria J VJ

Annals of surgical oncology 20160128 8

<h4>Background</h4>Little data are available regarding individual patients' risk of surgical site infection (SSI) following mastectomy with or without immediate reconstruction. Our objective was to develop a risk prediction model for mastectomy-related SSI.<h4>Methods</h4>Using commercial claims data, we established a cohort of women <65 years of age who underwent a mastectomy from 1 January 2004-31 December 2011. International Classification of Diseases, Ninth Revision, Clinical Modification di ...[more]

PMID: 26822880

Similar Datasets

Project description:BackgroundThere are limited data on risk factors for surgical site infection (SSI) after open or laparoscopic cholecystectomy.MethodsA retrospective cohort of commercially insured persons aged 18-64 years was assembled using International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM) procedure or Current Procedural Terminology, 4th edition codes for cholecystectomy from December 31, 2004 to December 31, 2010. Complex procedures and patients (eg, cancer, end-stage renal disease) and procedures with pre-existing infection were excluded. Surgical site infections within 90 days after cholecystectomy were identified by ICD-9-CM diagnosis codes. A Cox proportional hazards model was used to identify independent risk factors for SSI.ResultsSurgical site infections were identified after 472 of 66566 (0.71%) cholecystectomies; incidence was higher after open (n = 51, 4.93%) versus laparoscopic procedures (n = 421, 0.64%; P < .001). Independent risk factors for SSI included male gender, preoperative chronic anemia, diabetes, drug abuse, malnutrition/weight loss, obesity, smoking-related diseases, previous Staphylococcus aureus infection, laparoscopic approach with acute cholecystitis/obstruction (hazards ratio [HR], 1.58; 95% confidence interval [CI], 1.27-1.96), open approach with (HR, 4.29; 95% CI, 2.45-7.52) or without acute cholecystitis/obstruction (HR, 4.04; 95% CI, 1.96-8.34), conversion to open approach with (HR, 4.71; 95% CI, 2.74-8.10) or without acute cholecystitis/obstruction (HR, 7.11; 95% CI, 3.87-13.08), bile duct exploration, postoperative chronic anemia, and postoperative pneumonia or urinary tract infection.ConclusionsAcute cholecystitis or obstruction was associated with significantly increased risk of SSI with laparoscopic but not open cholecystectomy. The risk of SSI was similar for planned open and converted procedures. These findings suggest that stratification by operative factors is important when comparing SSI rates between facilities.

Project description:BackgroundSurgical site infection (SSI) is one of the most common types of health care-associated infections. It increases mortality, prolongs hospital length of stay, and raises health care costs. Many institutions developed risk assessment models for SSI to help surgeons preoperatively identify high-risk patients and guide clinical intervention. However, most of these models had low accuracies.ObjectiveWe aimed to provide a solution in the form of an Artificial intelligence-based Multimodal Risk Assessment Model for Surgical site infection (AMRAMS) for inpatients undergoing operations, using routinely collected clinical data. We internally and externally validated the discriminations of the models, which combined various machine learning and natural language processing techniques, and compared them with the National Nosocomial Infections Surveillance (NNIS) risk index.MethodsWe retrieved inpatient records between January 1, 2014, and June 30, 2019, from the electronic medical record (EMR) system of Rui Jin Hospital, Luwan Branch, Shanghai, China. We used data from before July 1, 2018, as the development set for internal validation and the remaining data as the test set for external validation. We included patient demographics, preoperative lab results, and free-text preoperative notes as our features. We used word-embedding techniques to encode text information, and we trained the LASSO (least absolute shrinkage and selection operator) model, random forest model, gradient boosting decision tree (GBDT) model, convolutional neural network (CNN) model, and self-attention network model using the combined data. Surgeons manually scored the NNIS risk index values.ResultsFor internal bootstrapping validation, CNN yielded the highest mean area under the receiver operating characteristic curve (AUROC) of 0.889 (95% CI 0.886-0.892), and the paired-sample t test revealed statistically significant advantages as compared with other models (P<.001). The self-attention network yielded the second-highest mean AUROC of 0.882 (95% CI 0.878-0.886), but the AUROC was only numerically higher than the AUROC of the third-best model, GBDT with text embeddings (mean AUROC 0.881, 95% CI 0.878-0.884, P=.47). The AUROCs of LASSO, random forest, and GBDT models using text embeddings were statistically higher than the AUROCs of models not using text embeddings (P<.001). For external validation, the self-attention network yielded the highest AUROC of 0.879. CNN was the second-best model (AUROC 0.878), and GBDT with text embeddings was the third-best model (AUROC 0.872). The NNIS risk index scored by surgeons had an AUROC of 0.651.ConclusionsOur AMRAMS based on EMR data and deep learning methods-CNN and self-attention network-had significant advantages in terms of accuracy compared with other conventional machine learning methods and the NNIS risk index. Moreover, the semantic embeddings of preoperative notes improved the model performance further. Our models could replace the NNIS risk index to provide personalized guidance for the preoperative intervention of SSIs. Through this case, we offered an easy-to-implement solution for building multimodal RAMs for other similar scenarios.

Project description:BackgroundThe rate of cesarean delivery is increasing in North America. Surgical site infection following this operation can make it difficult to recover, care for a baby and return home. We aimed to determine the incidence of surgical site infection to 30 days following cesarean delivery, associated risk factors and whether risk factors differed for predischarge versus postdischarge infection.MethodsWe identified a retrospective cohort in Nova Scotia by linking the provincial perinatal database to hospital admissions and physician billings databases to follow women for 30 days after they had given birth by cesarean delivery between Jan. 1, 1997 and Dec. 31, 2012. Logistic regression with generalized estimating equations was used to determine risk factors for infection.ResultsA total of 25 123 women had 33 991 cesarean deliveries over the study period. Of the 25 123, 923 had surgical site infections, giving an incidence rate of 2.7% (95% CI 2.54%-2.89%); the incidence decreased over time. Risk factors for infection (adjusted odds ratios ≥ 1.5) were prepregnancy weight 87.0 kg or more, gaining 30.0 kg or more during pregnancy, chorioamnionitis, maternal blood transfusion, anticoagulation therapy, alcohol or drug abuse, second stage of labour before surgery, delivery in 1997-2000 and delivery in a hospital performing 130-1249 cesarean deliveries annually. Women who gave birth earlier in the study period, those who gave birth in a hospital with 130-949 cesarean deliveries per year and those with more than 1 fetus were at a significantly higher risk for surgical site infection before discharge; women who smoked were at significantly higher risk for surgical site infection after discharge.InterpretationMost risk factors are known before delivery, and some are potentially modifiable. Although the incidence of surgical site infection decreased over time, targeted clinical and infection prevention and control interventions could further reduce the burden of illness associated with this health-care-related infection.

Project description:BACKGROUND:A surgical site infection (SSI) is a major post-operative complication from elective colorectal surgery; however, few studies have focused on evaluating the risk factors for SSI. This study aimed to analyze the relative correlation of medical and environmental factors as well as patient-related factors that contribute to the incidence of all types of SSI. METHODS:A retrospective search for eligible patients was conducted using the patient database of the Gastrointestinal Surgery Center of the Third Affiliated Hospital of Sun Yat-sen University from January 2011 to August 2017. Pre-operative demographic and surgical data were extracted and recoded according to the study protocol. Univariate and multivariate analyses were performed to clarify factors affecting the incidence of SSI. Propensity analysis was conducted to minimize bias in the demographic characteristics to explore the prophylactic effect of pre-operative administration of oral antibiotics. RESULTS:Univariate analysis of the baseline characteristics revealed that younger age (odds ratio [OR]: 0.378; 95% confidence interval [CI]: 0.218-0.657) and pre-operative oral antibiotic use (OR: 0.465; 95% CI: 0.255-0.850) were protective factors, while pre-operative anemia (OR: 4.591; 95% CI: 2.567-8.211), neoadjuvant chemotherapy history (OR: 2.398; 95% CI: 1.094-5.256), and longer surgical duration (OR: 2.393; 95% CI: 1.349-4.246; P?=?0.002) were identified as risk factors for SSI. Multivariate analysis indicated that age (P?=?0.003), surgical duration (P?=?0.001), and pre-operative oral antibiotic use (P?<?0.001) were independent factors that affect the incidence of SSI. Furthermore, a propensity-matched analysis confirmed the protective effect of oral antibiotic use, with a 1-day course of oral antibiotic producing a similar effect to a 3-day course. CONCLUSIONS:Age, surgical duration, and pre-operative oral antibiotic use were associated with the incidence of SSI. However, pre-operative oral antibiotic use was the only controllable factor. From the results of our study, pre-operative oral antibiotic use is recommended before elective colorectal surgery and a 1-day course is enough to provide the protective effect.

Dataset Information

Development of a Risk Prediction Model to Individualize Risk Factors for Surgical Site Infection After Mastectomy.

Publications

Development of a Risk Prediction Model to Individualize Risk Factors for Surgical Site Infection After Mastectomy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets