To 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. Data 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.Aims
Methods
Introduction. Despite several preventive strategies, periprosthetic joint infection (PJI) following total joint arthroplasty (TJA) is still a devastating complication. Early diagnosis and appropriate treatment are crucial to achieve successful infection control, but challenging since there is no test with 100% sensitivity and 100%. Therefore, several national and international guidelines include synovial analysis of joint aspirates as important diagnostic criteria, but cut-off levels for synovial cell count (CC) and polymorphonuclear (granulocyte) percentage (PMN%) are still debatable. The current investigation was performed to analyze the overall accuracy and optimal cut-off of synovial CC and PMN% following