Aims. Precise implant positioning, tailored to individual spinopelvic biomechanics and phenotype, is paramount for stability in total hip arthroplasty (THA). Despite a few studies on instability prediction, there is a notable gap in research utilizing artificial intelligence (AI). The objective of our pilot study was to evaluate the feasibility of developing an AI algorithm tailored to individual spinopelvic mechanics and patient phenotype for predicting impingement. Methods. This international, multicentre prospective cohort study across two centres encompassed 157 adults undergoing primary robotic arm-assisted THA. Impingement during specific flexion and extension stances was identified using the virtual range of motion (ROM) tool of the robotic software. The primary AI model, the Light Gradient-Boosting Machine (LGBM), used tabular data to predict impingement presence, direction (flexion or extension), and type. A secondary model integrating tabular data with plain anteroposterior pelvis radiographs was evaluated to assess for any potential enhancement in prediction accuracy. Results. We identified nine predictors from an analysis of baseline spinopelvic characteristics and surgical planning parameters. Using fivefold cross-validation, the LGBM achieved 70.2% impingement prediction accuracy. With impingement data, the LGBM estimated direction with 85% accuracy, while the support vector machine (SVM) determined impingement type with 72.9% accuracy. After integrating imaging data with a multilayer perceptron (tabular) and a convolutional neural network (radiograph), the LGBM’s prediction was 68.1%. Both combined and LGBM-only had similar impingement direction prediction rates (around 84.5%). Conclusion. This study is a pioneering effort in leveraging AI for impingement prediction in THA, utilizing a comprehensive, real-world clinical dataset. Our machine-learning algorithm demonstrated promising accuracy in predicting impingement, its type, and direction. While the addition of imaging data to our deep-learning algorithm did not boost accuracy, the potential for refined annotations, such as landmark markings, offers avenues for future enhancement. Prior to clinical integration, external validation and larger-scale testing of this algorithm are essential. Cite this article: Bone Jt Open 2024;5(8):671–680

Objective: To evaluate if the complete resection of the femoral bump, in cam-type FAI increases the postoperative flexion and internal rotation. Material and Method: We reviewed 24 consecutive pre-operative and postoperative hip CT scans in 24 patients with FAI (22 male and 2 female, mean age 36.9 years) who underwent arthroscopic hip surgery for the removal of a bony prominence on the femoral neck-head junction. We measured the alpha angle in two places: in the classical location, in the mid plane of the femoral neck axis and proximally, in the same plane but in first quarter of the femoral neck height. Then we compared these results with the presence of a residual prominence diagnosed in the 3 dimensionally reconstructed images of the postoperative CT scan and the virtual range of motion of the 3D models using impaction detection software. Results: We found 7 cases with a residual bony prominence at the femoral neck-head junction in the 3D model of the proximal femur after the surgery. In this group the mean mid femoral neck alpha angle was significantly improved from 69.7° before the surgery to 48.3° (p=0.028), however the proximal alpha angle was not significantly improved 71.1° preoperative versus 62.7 (p=0.176) after the surgery. In the 17 patients without a residual bump, both alpha angles were improved, the mid alpha angle from 64.9° before the surgery to 40.76° (p=0.000) after the surgery and the proximal alpha angle from 65.8° to 38.4° (p=0.000). The range of motion of hip in the impaction detection software was also significantly improved in both groups, from flexion of 103° to 116° (p=0.001) in the group without a residual bump and from 102 to 118 (p=0.046) in the group with a residual bony prominence after the surgery. The internal rotation at 90° of flexion was also improved in both groups with a statistically significant difference (p=0.001 versus p=0.028 respectively). Conclusion: The complete arthroscopic resection of the femoral bump improves significantly the ranges of flex-ion and internal rotation in patients with cam-type FAI

Aims

Pelvic tilt (PT) can significantly change the functional orientation of the acetabular component and may differ markedly between patients undergoing total hip arthroplasty (THA). Patients with stiff spines who have little change in PT are considered at high risk for instability following THA. Femoral component position also contributes to the limits of impingement-free range of motion (ROM), but has been less studied. Little is known about the impact of combined anteversion on risk of impingement with changing pelvic position.

Aims

Femoral component anteversion is an important factor in the success of total hip arthroplasty (THA). This retrospective study aimed to investigate the accuracy of femoral component anteversion with the Mako THA system and software using the Exeter cemented femoral component, compared to the Accolade II cementless femoral component.