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
Implant loosening is a common cause of a poor outcome and pain after total knee arthroplasty (TKA). Despite the increase in use of expensive techniques like arthrography, the detection of prosthetic loosening is often unclear pre-operatively, leading to diagnostic uncertainty and extensive workup. The objective of this study was to evaluate the ability of a machine learning (ML) algorithm to diagnose prosthetic loosening from pre-operative radiographs, and to observe what model inputs improve the performance of the model. 754 patients underwent a first-time revision of a total joint at our institution from 2012–2018. Pre-operative X-Rays (XR) were collected for each patient. AP and lateral X-Rays, in addition to demographic and comorbidity information, were collected for each patient. Each patient was determined to have either loose or fixed prosthetics based on a manual abstraction of the written findings in their operative report, which is considered the gold standard of diagnosing prosthetic loosening. We trained a series of deep convolution neural network (CNN) models to predict if a prosthesis was found to be loose in the operating room from the pre-operative XR. Each XR was pre-processed to segment the bone, implant, and bone-implant interface. A series of CNN models were built using existing, proven CNN architectures and weights optimized to our dataset. We then integrated our best performing model with historical patient data to create a final model and determine the incremental accuracy provided by additional layers of clinical information fed into the model. The models were evaluated by its accuracy, sensitivity and specificity.Background
Methods
We evaluated the impact of pre-coating the tibial
component with polymethylmethacrylate (PMMA) on implant survival
in a cohort of 16 548 primary NexGen total knee replacements (TKRs)
in 14 113 patients. In 13 835 TKRs a pre-coated tray was used while
in 2713 TKRs the non-pre-coated version of the same tray was used.
All the TKRs were performed between 2001 and 2009 and were cemented.
TKRs implanted with a pre-coated tibial component had a lower cumulative
survival than those with a non-pre-coated tibial component (p =
0.01). After adjusting for diagnosis, age, gender, body mass index,
American Society of Anesthesiologists grade, femoral coupling design, surgeon
volume and hospital volume, pre-coating was an independent risk
factor for all-cause aseptic revision (hazard ratio 2.75, p = 0.006).
Revision for aseptic loosening was uncommon for both pre-coated
and non-pre-coated trays (rates of 0.12% and 0%, respectively).
Pre-coating with PMMA does not appear to be protective of revision
for this tibial tray design at short-term follow-up. Cite this article:
