To examine whether natural language processing (NLP) using a clinically based large language model (LLM) could be used to predict patient selection for total hip or total knee arthroplasty (THA/TKA) from routinely available free-text radiology reports. Data pre-processing and analyses were conducted according to the Artificial intelligence to Revolutionize the patient Care pathway in Hip and knEe aRthroplastY (ARCHERY) project protocol. This included use of de-identified Scottish regional clinical data of patients referred for consideration of THA/TKA, held in a secure data environment designed for artificial intelligence (AI) inference. Only preoperative radiology reports were included. NLP algorithms were based on the freely available GatorTron model, a LLM trained on over 82 billion words of de-identified clinical text. Two inference tasks were performed: assessment after model-fine tuning (50 Epochs and three cycles of k-fold cross validation), and external validation.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
To establish the utility of adding the laboratory-based synovial alpha-defensin immunoassay to the traditional diagnostic work-up of a prosthetic joint infection (PJI). A group of four physicians evaluated 158 consecutive patients who were worked up for PJI, of which 94 underwent revision arthroplasty. Each physician reviewed the diagnostic data and decided on the presence of PJI according to the 2014 Musculoskeletal Infection Society (MSIS) criteria (yes, no, or undetermined). Their initial randomized review of the available data before or after surgery was blinded to each alpha-defensin result and a subsequent randomized review was conducted with each result. Multilevel logistic regression analysis assessed the effect of having the alpha-defensin result on the ability to diagnose PJI. Alpha-defensin was correlated to the number of synovial white blood cells (WBCs) and percentage of polymorphonuclear cells (%PMN).Aims
Methods
This study aimed to develop a virtual clinic for the purpose of reducing face-to-face orthopaedic consultations. Anonymized experts (hip and knee arthroplasty patients, surgeons, physiotherapists, radiologists, and arthroplasty practitioners) gave feedback via a Delphi Consensus Technique. This consisted of an iterative sequence of online surveys, during which virtual documents, made up of a patient-reported questionnaire, standardized radiology report, and decision-guiding algorithm, were modified until consensus was achieved. We tested the patient-reported questionnaire on seven patients in orthopaedic clinics using a ‘think-aloud’ process to capture difficulties with its completion.Aims
Patients and Methods
Increasing innovation in rapid prototyping (RP)
and additive manufacturing (AM), also known as 3D printing, is bringing
about major changes in translational surgical research. This review describes the current position in the use of additive
manufacturing in orthopaedic surgery. Cite this article:
The interaction between surgical lighting and laminar airflow
is poorly understood. We undertook an experiment to identify any
effect contemporary surgical lights have on laminar flow and recommend
practical strategies to limit any negative effects. Neutrally buoyant bubbles were introduced into the surgical field
of a simulated setup for a routine total knee arthroplasty in a
laminar flow theatre. Patterns of airflow were observed and the
number of bubbles remaining above the surgical field over time identified.
Five different lighting configurations were assessed. Data were analysed
using simple linear regression after logarithmic transformation.Aims
Materials and Methods
We hypothesised there was no clinical value in
using an autologous blood transfusion (ABT) drain in either primary total
hip (THR) or total knee replacement (TKR) in terms of limiting allogeneic
blood transfusions when a modern restrictive blood management regime
was followed. A total of 575 patients (65.2% men), with a mean age
of 68.9 years (36 to 94) were randomised in this three-arm study
to no drainage (group A), or to wound drainage with an ABT drain
for either six hours (group B) or 24 hours (group C). The primary
outcome was the number of patients receiving allogeneic blood transfusion.
Secondary outcomes were post-operative haemoglobin (Hb) levels,
length of hospital stay and adverse events. This study identified only 41 transfused patients, with no significant
difference in distribution between the three groups (p = 0.857).
The mean pre-operative haemoglobin (Hb) value in the transfused
group was 12.8 g/dL (9.8 to 15.5) Cite this article:
We analysed data from the Oxford hip and knee questionnaires collected by the New Zealand Joint Registry at six months and five years after joint replacement, to determine if there was any relationship between the scores and the risk of early revision. Logistic regression of the six-month scores indicated that for every one-unit decrease in the Oxford score, the risk of revision within two years increased by 9.7% for total hip replacement (THR), 9.9% for total knee replacement (TKR) and 12.0% for unicompartmental knee replacement (UKR). Our findings showed that 70% of the revisions within two years for TKR and 67% for THR and UKR would have been captured by monitoring the lowest 22%, 28% and 28%, respectively, of the Oxford scores. When analysed using the Kalairajah classification a score of <
27 (poor) was associated with a risk of revision within two years of 7.6% for THR, 7.0% for TKR and 24.3% for UKR, compared with risks of 0.7%, 0.7% and 1.8%, respectively, for scores >
34 (good or excellent). Our study confirms that the Oxford hip and knee scores at six months are useful predictors of early revision after THR and TKR and we recommend their use for the monitoring of the outcome and potential failure in these patients.
We have investigated the accuracy of the templating of digital radiographs in planning total hip replacement using two common object-based calibration methods with the ball placed laterally (method 1) or medially (method 2) and compared them with two non-object-based methods. The latter comprised the application of a fixed magnification of 121% (method 3) and calculation of magnification based on the object-film-distance (method 4). We studied the post-operative radiographs of 57 patients (19 men, 38 women, mean age 73 years (53 to 89)) using the measured diameter of the prosthetic femoral head and comparing it with the true value. Both object-based methods (1 and 2) produced large errors (mean/maximum: 2.55%/17.4% and 2.04%/6.46%, respectively). Method 3 applying a fixed magnification and method 4 (object-film-distance) produced smaller errors (mean/maximum 1.42%/5.22% and 1.57%/4.24%, respectively; p <
0.01). The latter results were clinically relevant and acceptable when planning was allowed to within one implant size. Object-based calibration (methods 1 and 2) has fundamental problems with the correct placement of the calibration ball. The accuracy of the fixed magnification (method 3) matched that of object-film-distance (method 4) and was the most reliable and efficient calibration method in digital templating.
The routine use of surgical drains in total hip arthroplasty remains controversial. They have not been shown to decrease the rate of wound infection significantly and can provide a retrograde route for it. Their use does not reduce the size or incidence of post-operative wound haematomas. This prospective, randomised study was designed to evaluate the role of drains in routine total hip arthroplasty. We investigated 552 patients (577 hips) undergoing unilateral or bilateral total hip arthroplasty who had been randomised to either having a drain for 24 hours or not having a drain. All patients followed standardised pre-, intra-, and post-operative regimes and were independently assessed using the Harris hip score before operation and at six, 18 and 36 months follow-up. The rate of superficial and deep infection was 2.9% and 0.4%, respectively, in the drained group and 4.8% and 0.7%, respectively in the undrained group. One patient in the undrained group had a haematoma which did not require drainage or transfusion. The rate of transfusion after operation in the drained group was significantly higher than for undrained procedures (p <
0.042). The use of a drain did not influence the post-operative levels of haemoglobin, the revision rates, Harris hip scores, the length of hospital stay or the incidence of thromboembolism. We conclude that drains provide no clear advantage at total hip arthroplasty, represent an additional cost, and expose patients to a higher risk of transfusion.
Patients who have undergone total hip or knee replacement (THR and TKR, respectively) are at high risk of venous thromboembolism. We aimed to determine the time courses of both the incidence of venous thromboembolism and effective prophylaxis. Patients with elective primary THR and TKR were enrolled in the multi-national Global Orthopaedic Registry. Data on the incidence of venous thromboembolism and prophylaxis were collected from 6639 THR and 8326 TKR patients. The cumulative incidence of venous thromboembolism within three months of surgery was 1.7% in the THR and 2.3% in the TKR patients. The mean times to venous thromboembolism were 21.5 days ( The risk of venous thromboembolism extends beyond the usual period of hospitalisation, while the duration of prophylaxis is often shorter than this. Practices should be re-assessed to ensure that patients receive appropriate durations of prophylaxis.
