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
Aims. Orthopaedic surgeries are complex, frequently performed procedures associated with significant haemorrhage and perioperative blood transfusion. Given refinements in surgical techniques and changes to transfusion practices, we aim to describe contemporary transfusion practices in orthopaedic surgery in order to inform perioperative planning and blood banking requirements. Methods. We performed a retrospective cohort study of adult patients who underwent orthopaedic surgery at four Canadian hospitals between 2014 and 2016. We studied all patients admitted to hospital for nonarthroscopic joint surgeries, amputations, and fracture surgeries. For each surgery and surgical subgroup, we characterized the proportion of patients who received red blood cell (RBC) transfusion, the mean/median number of
