RESUMO
BACKGROUND: Anterior knee pain (AKP) following total knee arthroplasty (TKA) with patellar preservation is a common complication that significantly affects patients' quality of life. This study aimed to develop a machine-learning model to predict the likelihood of developing AKP after TKA using radiological variables. METHODS: A cohort of 131 anterior stabilized TKA cases (105 patients) without patellar resurfacing was included. Patients underwent a follow-up evaluation with a minimum 1-year follow-up. The primary outcome was AKP, and radiological measurements were used as predictor variables. There were 2 observers who made the radiological measurement, which included lower limb dysmetria, joint space, and coronal, sagittal, and axial alignment. Machine-learning models were applied to predict AKP. The best-performing model was selected based on accuracy, precision, sensitivity, specificity, and Kappa statistics. Python 3.11 with Pandas and PyCaret libraries were used for analysis. RESULTS: A total of 35 TKA had AKP (26.7%). Patient-reported outcomes were significantly better in the patients who did not have AKP. The Gradient Boosting Classifier performed best for both observers, achieving an area under the curve of 0.9261 and 0.9164, respectively. The mechanical tibial slope was the most important variable for predicting AKP. The Shapley test indicated that high/low mechanical tibial slope, a shorter operated leg, a valgus coronal alignment, and excessive patellar tilt increased AKP risk. CONCLUSIONS: The results suggest that global alignment, including sagittal, coronal, and axial alignment, is relevant in predicting AKP after TKA. These findings provide valuable insights for optimizing TKA outcomes and reducing the incidence of AKP.
RESUMO
Background Total knee arthroplasty (TKA) is a cost-effective treatment for the end-stage of knee osteoarthritis. Despite the improvements in this surgery, a significant percentage of patients still report dissatisfaction after knee arthroplasty. Radiological results have been used to predict clinical outcomes and satisfaction after knee replacement. This study aims to evaluate the concordance of a set of radiographic views to assess alignment on total knee arthroplasty. Methods A concordance study was designed with 105 patients (130 TKA) that underwent conventional total knee arthroplasty cruciate-retaining design recruited for the study and scheduled for their annual radiograph control. Measurements were performed on the following radiograph after total knee replacement: full-length standing anteroposterior and lateral radiograph, anteroposterior standing, lateral and axial knee view, and the knee "seated view". A musculoskeletal radiologist and a knee surgeon were recruited to perform the radiological measurement and then estimate the interobserver agreement. Results There was an excellent correlation between Limb Length (LL), Hip-knee-ankle angle (HKA), Sagittal mechanical tibial component alignment (smTA), extension lateral and medial joint space (eLJS and eMJS), 90º flexion lateral and medial joint space (fLJS and fMJS) and Sagittal anatomic lateral view tibial component alignment (saLTA); the good correlation between Mechanical lateral femoral component alignment (mLFA), Sagittal anatomic tibial component alignment (saTA), Sagittal anatomic lateral view femoral component alignment 2 (saLFA2), Patella Height (PH); and moderate to poor correlation for the rest of measurements. Conclusion Excellent and good concordance can be achieved for radiographic measurements in different knee views to assess results after TKA. These findings must encourage future studies to address functional and survival outcomes using all knee views and not just one plane.
