A substantial fraction of patients undergoing knee arthroplasty (KA) or hip arthroplasty (HA) do not achieve an improvement as high as the minimal clinically important difference (MCID), i.e. do not achieve a meaningful improvement. Using three patient-reported outcome measures (PROMs), our aim was: 1) to assess machine learning (ML), the simple pre-surgery PROM score, and logistic-regression (LR)-derived performance in their prediction of whether patients undergoing HA or KA achieve an improvement as high or higher than a calculated MCID; and 2) to test whether ML is able to outperform LR or pre-surgery PROM scores in predictive performance. MCIDs were derived using the change difference method in a sample of 1,843 HA and 1,546 KA patients. An artificial neural network, a gradient boosting machine, least absolute shrinkage and selection operator (LASSO) regression, ridge regression, elastic net, random forest, LR, and pre-surgery PROM scores were applied to predict MCID for the following PROMs: EuroQol five-dimension, five-level questionnaire (EQ-5D-5L), EQ visual analogue scale (EQ-VAS), Hip disability and Osteoarthritis Outcome Score-Physical Function Short-form (HOOS-PS), and Knee injury and Osteoarthritis Outcome Score-Physical Function Short-form (KOOS-PS).Aims
Methods
Total hip arthroplasty (THA) and total knee arthroplasty (TKA) are common orthopaedic procedures requiring postoperative radiographs to confirm implant positioning and identify complications. Artificial intelligence (AI)-based image analysis has the potential to automate this postoperative surveillance. The aim of this study was to prepare a scoping review to investigate how AI is being used in the analysis of radiographs following THA and TKA, and how accurate these tools are. The Embase, MEDLINE, and PubMed libraries were systematically searched to identify relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews and Arksey and O’Malley framework were followed. Study quality was assessed using a modified Methodological Index for Non-Randomized Studies tool. AI performance was reported using either the area under the curve (AUC) or accuracy.Aims
Methods
The enhanced recovery after surgery (ERAS) concept in arthroplasty surgery has led to a reduction in postoperative length of stay in recent years. Patients with prolonged length of stay (PLOS) add to the burden of a strained NHS. Our aim was to identify the main reasons. A PLOS was arbitrarily defined as an inpatient hospital stay of four days or longer from admission date. A total of 2,000 consecutive arthroplasty patients between September 2017 and July 2018 were reviewed. Of these, 1,878 patients were included after exclusion criteria were applied. Notes for 524 PLOS patients were audited to determine predominant reasons for PLOS.Introduction
Methods
Aims
Patients and Methods
Wound complications are reported in up to 10% hip and knee arthroplasties and there is a proven association between wound complications and deep prosthetic infections. In this randomised controlled trial (RCT) we explore the potential benefits of a portable, single use, incisional negative pressure wound therapy dressing (iNPWTd) on wound exudate, length of stay (LOS), wound complications, dressing changes and cost-effectiveness following total hip and knee arthroplasties. A total of 220 patients undergoing elective primary total hip and knee arthroplasties were recruited into in a non-blinded RCT. For the final analysis there were 102 patients in the study group and 107 in the control group.Objectives
Methods
We performed a meta-analysis of modern total
joint replacement (TJR) to determine the post-operative mortality and
the cause of death using different thromboprophylactic regimens
as follows: 1) no routine chemothromboprophylaxis (NRC); 2) Potent
anticoagulation (PA) (unfractionated or low-molecular-weight heparin, ximelagatran,
fondaparinux or rivaroxaban); 3) Potent anticoagulation combined
(PAC) with regional anaesthesia and/or pneumatic compression devices
(PCDs); 4) Warfarin (W); 5) Warfarin combined (WAC) with regional anaesthesia
and/or PCD; and 6) Multimodal (MM) prophylaxis, including regional
anaesthesia, PCDs and aspirin in low-risk patients. Cause of death
was classified as autopsy proven, clinically certain or unknown.
Deaths were grouped into cardiopulmonary excluding pulmonary embolism
(PE), PE, bleeding-related, gastrointestinal, central nervous system,
and others (miscellaneous). Meta-analysis based on fixed effects
or random effects models was used for pooling incidence data. In all, 70 studies were included (99 441 patients; 373 deaths).
The mortality was lowest in the MM (0.2%) and WC (0.2%) groups.
The most frequent cause of death was cardiopulmonary (47.9%), followed
by PE (25.4%) and bleeding (8.9%). The proportion of deaths due
to PE was not significantly affected by the thromboprophylaxis regimen (PA, 35.5%;
PAC, 28%; MM, 23.2%; and NRC, 16.3%). Fatal bleeding was higher
in groups relying on the use of anticoagulation (W, 33.8%; PA, 9.4%;
PAC, 10.8%) but the differences were not statistically significant. Our study demonstrated that the routine use of PA does not reduce
the overall mortality or the proportion of deaths due to PE.
