| Abstrakt: |
A study conducted by the Department of Orthopedics in San Antonio, Texas, aimed to develop machine learning algorithms to predict the risk of postoperative surgical site infection in patients with lower extremity fractures. The study analyzed a dataset of 1,579 patients and identified five predictors associated with the risk of infection: operating room time, ankle region, open injury, body mass index, and age. The best-performing machine learning algorithm showed promising predictive performance. The proposed model can assist surgeons in identifying high-risk factors and empower patients to monitor and prevent complications. However, further research is needed to validate the model with larger datasets. [Extracted from the article] |
