To compare the gait of unicompartmental knee arthroplasty (UKA)
and total knee arthroplasty (TKA) patients with healthy controls,
using a machine-learning approach. 145 participants (121 healthy controls, 12 patients with cruciate-retaining
TKA, and 12 with mobile-bearing medial UKA) were recruited. The
TKA and UKA patients were a minimum of 12 months post-operative,
and matched for pattern and severity of arthrosis, age, and body
mass index. Participants walked on an instrumented treadmill until their
maximum walking speed was reached. Temporospatial gait parameters,
and vertical ground reaction force data, were captured at each speed.
Oxford knee scores (OKS) were also collected. An ensemble of trees
algorithm was used to analyse the data: 27 gait variables were used
to train classification trees for each speed, with a binary output
prediction of whether these variables were derived from a UKA or
TKA patient. Healthy control gait data was then tested by the decision
trees at each speed and a final classification (UKA or TKA) reached
for each subject in a majority voting manner over all gait cycles
and speeds. Top walking speed was also recorded.Aims
Patients and Methods
To analyse the distribution of osteoarthritis of the knee, to determine what proportion of patients may be suitable for a partial knee replacement and finally to assess the risk of wear progression. The intra-operative articular surface mappings were collected for 250 consecutive patients undergoing knee arthroscopy. Patients were graded using the Outerbridge Classification. Radiographs including antero-posterior standing, postero-anterior flexion (Rosenberg), lateral and skyline views were graded (Kellgren and Lawrence) and compared with the arthroscopic findings. 13.3% of knees showed ‘isolated’ medial disease of Outerbridge Grade 3 or worse. Isolated lateral disease was noted in 1.4%, patello-femoral disease in 24.3%, bi-compartmental (Medial/PFJ) disease in 30.9% with tibio-femoral and tri-compartmental disease in 15.2%. The combination of lateral and patello-femoral disease was seen in 14.8%. The mean age of patients with tri-compartmental disease (60.9 years) was greater than the mean age of those suffering with osteoarthritis limited to one or two compartments (54 years) Radiological analysis revealed AP views had only 66% sensitivity and 73% specificity for the presence of Grade 3/4 lesions in the medial compartment. Rosenberg views had 73% sensitivity and 83% specificity. Skyline views had a sensitivity of 56% and 100% specificity.Statement of purpose
Summary of methods used and results
