Objective: To determine patient-specific and injury-specific factors that may predict infection and other adverse clinical results in the setting of tibial pilon fractures.Design: Retrospective chart review.Setting: Level 1 academic trauma center. Patients:Two hundred forty-eight patients who underwent operative treatment for tibial pilon fractures between 2010 and 2020. Intervention: External fixation and/or open reduction and internal fixation.Main Outcome Measurements: Fracture-related infection rates and specific bacteriology, risk factors associated with development of a fracture-related infection, and predictors of adverse clinical results.Results: Two hundred forty-eight patients were enrolled. There was an infection rate of 21%. The 3 most common pathogens cultured were methicillin-resistant Staphylococcus aureus (20.3%), Enterobacter cloacae (16.7%), and methicillin-resistant Staphylococcus aureus (15.5%). There was no significant difference in age, sex, race, body mass index, or smoking status between those who developed an infection and those who did not. Patients with diabetes mellitus (P = 0.0001), open fractures (P = 0.0043), and comminuted fractures (OTA/AO 43C2 and 43C3) (P = 0.0065) were more likely to develop a fracture-related infection. The presence of a polymicrobial infection was positively associated with adverse clinical results (P = 0.006). History of diabetes was also positively associated with adverse results (P = 0.019).Conclusions: History of diabetes and severe fractures, such as those that were open or comminuted fractures, were positively associated with developing a fracture-related infection after the operative fixation of tibial pilon fractures. History of diabetes and presence of a polymicrobial infection were independently associated with adverse clinical results.

No abstract

AimsTo identify variables independently associated with same-day discharge (SDD) of patients following revision total knee arthroplasty (rTKA) and to develop machine learning algorithms to predict suitable candidates for outpatient rTKA.MethodsData were obtained from the American College of Surgeons National Quality Improvement Programme (ACS-NSQIP) database from the years 2018 to 2020. Patients with elective, unilateral rTKA procedures and a total hospital length of stay between zero and four days were included. Demographic, preoperative, and intraoperative variables were analyzed. A multivariable logistic regression (MLR) model and various machine learning techniques were compared using area under the curve (AUC), calibration, and decision curve analysis. Important and significant variables were identified from the models.ResultsOf the 5,600 patients included in this study, 342 (6.1%) underwent SDD. The random forest (RF) model performed the best overall, with an internally validated AUC of 0.810. The ten crucial factors favoring SDD in the RF model include operating time, anaesthesia type, age, BMI, American Society of Anesthesiologists grade, race, history of diabetes, rTKA type, sex, and smoking status. Eight of these variables were also found to be significant in the MLR model.ConclusionThe RF model displayed excellent accuracy and identified clinically important variables for determining candidates for SDD following rTKA. Machine learning techniques such as RF will allow clinicians to accurately risk-stratify their patients preoperatively, in order to optimize resources and improve patient outcomes.Cite this article: Bone Jt Open 2023;4(6):399–407.

Supplemental Digital Content is Available in the Text.