Risk factors including surgery department and antibiotic prophylaxis were significant predictors of surgical site infections, with a KNN model achieving the highest accuracy on the dataset.
Observational (n=4,031)
No
What are the significant risk factors for surgical site infections, and can artificial intelligence models accurately predict their occurrence?
Specific clinical factors including postoperative length of stay and antibiotic prophylaxis regimens are significant predictors of surgical site infections, which can be effectively predicted using a KNN machine learning model.
Background: Surgical site infections (SSIs) have a major role in the evolution of medical care. Despite centuries of medical progress, the management of surgical infection remains a pressing concern. Nowadays, the SSIs continue to be an important factor able to increase the hospitalization duration, cost, and risk of death, in fact, the SSIs are a leading cause of morbidity and mortality in modern health care. Methods: A study based on statistical test and logistic regression for unveiling the association between SSIs and different risk factors was carried out. Successively, a predictive analysis of SSIs on the basis of risk factors was performed. Results: The obtained data demonstrated that the level of surgery contamination impacts significantly on the infection rate. In addition, data also reveals that the length of postoperative hospital stay increases the rate of surgical infections. Finally, the postoperative length of stay, surgery department and the antibiotic prophylaxis with 2 or more antibiotics are a significant predictor for the development of infection. Conclusions: The data report that the type of surgery department and antibiotic prophylaxis there are a statistically significant predictor of SSIs. Moreover, KNN model better handle the imbalanced dataset (48 infected and 3983 healthy), observing highest accuracy value.
Scala et al. (Sun,) conducted a observational in Surgical site infections (n=4,031). Risk factors (surgery contamination, postoperative stay, surgery department, antibiotic prophylaxis) was evaluated on Surgical site infections. Risk factors including surgery department and antibiotic prophylaxis were significant predictors of surgical site infections, with a KNN model achieving the highest accuracy on the dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: