The aim of this study was to evaluate the ability of a machine-learning algorithm to diagnose prosthetic loosening from preoperative radiographs and to investigate the inputs that might improve its performance. A group of 697 patients underwent a first-time revision of a total hip (THA) or total knee arthroplasty (TKA) at our institution between 2012 and 2018. Preoperative anteroposterior (AP) and lateral radiographs, and historical and comorbidity information were collected from their electronic records. Each patient was defined as having loose or fixed components based on the operation notes. We trained a series of convolutional neural network (CNN) models to predict a diagnosis of loosening at the time of surgery from the preoperative radiographs. We then added historical data about the patients to the best performing model to create a final model and tested it on an independent dataset.Aims
Methods
Increasingly, patients with bilateral hip arthritis wish to undergo staged total hip arthroplasty (THA). With the rise in demand for arthroplasty, perioperative risk assessment and counselling is crucial for shared decision making. However, it is unknown if complications that occur after a unilateral hip arthroplasty predict complications following surgery of the contralateral hip. We used nationwide linked discharge data from the Healthcare Cost and Utilization Project between 2005 and 2014 to analyze the incidence and recurrence of complications following the first- and second-stage operations in staged bilateral total hip arthroplasty (BTHAs). Complications included perioperative medical adverse events within 30 to 60 days, and infection and mechanical complications within one year. Conditional probabilities and odds ratios (ORs) were calculated to determine whether experiencing a complication after the first stage of surgery increased the risk of developing the same complication after the second stage.Aims
Patients and Methods
