Arthroplasties are widely performed to improve mobility and quality of life for symptomatic knee/hip osteoarthritis patients. With increasing rates of Total Joint Replacements in the United Kingdom, predicting length of stay is vital for hospitals to control costs, manage resources, and prevent postoperative complications. A longer Length of stay has been shown to negatively affect the quality of care, outcomes and patient satisfaction. Thus, predicting LOS enables us to make full use of medical resources. Clinical characteristics were retrospectively collected from 1,303 patients who received TKA and THR. A total of 21 variables were included, to develop predictive models for LOS by multiple machine learning (ML) algorithms, including Random Forest Classifier (RFC), K-Nearest Neighbour (KNN), Extreme Gradient Boost (XgBoost), and Na¯ve Bayes (NB). These models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance. A feature selection approach was used to identify optimal predictive factors. Based on the ROC of Training result, XgBoost algorithm was selected to be applied to the Test set. The areas under the ROC curve (AUCs) of the 4 models ranged from 0.730 to 0.966, where higher AUC values generally indicate better predictive performance. All the ML-based models performed better than conventional statistical methods in ROC curves. The XgBoost algorithm with 21 variables was identified as the best predictive model. The feature selection indicated the top six predictors: Age, Operation Duration, Primary Procedure, BMI, creatinine and Month of Surgery. By analysing clinical characteristics, it is feasible to develop ML-based models for the preoperative prediction of LOS for patients who received TKA and THR, and the XgBoost algorithm performed the best, in terms of accuracy of predictive performance. As this model was originally crafted at Ashford and St. Peters Hospital, we have naturally named it as THE ASHFORD OUTCOME.
The aim of this abstract is to show that acute osteomyelitis is one of the most feared complication of orthopedic surgery. A rapid and aggressive treatment is mandatory in order to avoid significant bone loss, joint destruction and, in most cases, salvage of the limb. After apparent cure of the infection, sequelae must be addressed. In this case, the joint destruction was important, so reconstruction procedures where impossible. In a superficial and relatively small joint such as the elbow, it is preferred to do an arthrodesis than an arthroplasty because the risk of reactivation of the infection with implant involvement is very important. We present a case report of a 69 years old woman, who had a supra-intra-condylar fracture (AO 13-C1) of the right humerus. She was treated with open reduction and internal fixation with 2 internal lag screws and 2 external lag screws. After 6 weeks, she was admitted with a dislocated elbow associated with pain, loss of limb function, cubita nerve palsy and a purulent discharge from the surgical wound. She started vancomycin and was submitted to surgery with debriment, hardware removal and fixation with an external fixator was used. The local signs of infection disappeared progressively. After normalization of the laboratory parameters of infection, the patient was submitted to an elbow arthrodesis using a posterior contour plate. The elbow achieved solid fixation and infection was eradicated, at least for the time being, allowing the patient to use the upper limb in her daily live activities. The treatment of post operative acute osteomyilits is challenging, In this case, after apparent solution of the infection, a solid fixation of the elbow was achieved, allowing the use of the upper limb in the patient daily activities.
The aim of this abstract is to show that when dealing with an infected non-union, all possibilities of treatment must be considered in order to choose the best treatment plan for each patient. This case shows the evolution of an infected non-union following type III open fractures which, after the used of several methods that failed, had to be solved with amputation. We present a case report of a 41 years old man, with a type IIIA open fracture of the right tibia and fibula. Initially, he was treated with an external fixator, which was removed and plate implanted. After this, he who presented to us with an infected non-union. He was submitted to surgery, the plate was removed and a circular external fixator was used. Six months later, the external fixator was removed and a reamed intramedullary nail was implanted with bone graft from iliac crest. One year later, the facture site was still mobile, so he was submitted to fixation with internal plate. As this last method also failed, a bellow knee amputation was performed, 4 years after the initial event. After several attempts with several distinctive methods, the infected non-union had to be solved with the sacrifice of the limb. The treatment of infected non-union is one of the most difficult in Orthopedic Surgery. There are several procedure that can be used. When all these fail, amputation and consequent limb prosthetic substitution, might allow the patient to return to the society.