Introduction. Instability remains a common complication following total hip arthroplasty (THA) and continues to account for the highest percentage of revisions in numerous registries. Many risk factors have been described, yet a patient-specific risk assessment tool remains elusive. The purpose of this study was to apply a machine learning algorithm to develop a patient-specific risk score capable of dynamic adjustment based on operative decisions. Methods. 22,086 THA performed between 1998–2018 were evaluated. 632 THA sustained a postoperative dislocation (2.9%). Patients were robustly characterized based on non-modifiable factors: demographics, THA indication, spinal disease, spine surgery, neurologic disease, connective tissue disease; and modifiable operative decisions: surgical approach, femoral head size, acetabular liner (standard/elevated/constrained/dual-mobility). Models were built with a binary outcome (event/no event) at 1-year and 5-year postoperatively. Inverse Probability Censoring Weighting accounted for censoring bias. An ensemble algorithm was created that included Generalized Linear Model, Generalized Additive Model, Lasso Penalized Regression, Kernel-Based Support Vector Machines, Random Forest and Optimized Gradient Boosting Machine. Convex combination of weights minimized the negative binomial log-likelihood loss function. Ten-fold cross-validation accounted for the rarity of dislocation events. Results. The 1-year model achieved an area under the curve (AUC)=0.63, sensitivity=70%, specificity=50%, positive predictive value (PPV)=3% and negative predictive value (NPV)=99%. The 5-year model achieved an AUC=0.62, sensitivity=69%, specificity=51%, PPV=7% and NPV=97%. All cohort-level accuracy metrics performed better than chance. The two most influential predictors in the model were surgical approach and acetabular liner. Conclusions. This machine learning algorithm demonstrates high sensitivity and NPV, suggesting screening tool utility. The model is strengthened by a multivariable dataset portending differential dislocation risk. Two modifiable variables (approach and acetabular liner) were the most influential in dislocation risk. Calculator utilization in “app” form could enable individualized risk prognostication. Furthermore, algorithm development through machine learning facilitates perpetual model performance enhancement with future data input

Aims

Patients with femoral neck fractures (FNFs) treated with total hip arthroplasty (THA) have an almost ten-fold increased risk of dislocation compared to patients undergoing elective THA. The surgical approach influences the risk of dislocation. To date, the influence of differing head sizes and dual-mobility components (DMCs) on the risk of dislocation has not been well studied.

Aims

The gluteus minimus (GMin) and gluteus medius (GMed) have unique structural and functional segments that may be affected to varying degrees, by end-stage osteoarthritis (OA) and normal ageing. We used data from patients with end-stage OA and matched healthy controls to 1) quantify the atrophy of the GMin and GMed in the two groups and 2) describe the distinct patterns of the fatty infiltration in the different segments of the GMin and GMed in the two groups.

Aims

Patients with abnormal spinopelvic mobility are at increased risk for instability. Measuring the change in sacral slope (ΔSS) can help determine spinopelvic mobility preoperatively. Sacral slope (SS) should decrease at least 10° to demonstrate adequate posterior pelvic tilt. There is potential for different ΔSS measurements in the same patient based on sitting posture. The purpose of this study was to determine the effect of sitting posture on the ΔSS in patients undergoing total hip arthroplasty (THA).

The accurate reconstruction of hip anatomy and biomechanics is thought to be important in achieveing good clinical outcomes following total hip arthroplasty (THA). To this end some newer hip designs have introduced further modularity into the design of the femoral component such that neck­shaft angle and anteversion, which can be adjusted intra-operatively. The clinical effect of this increased modularity is unknown. We have investigated the changes in these anatomical parameters following conventional THA with a prosthesis of predetermined neck–shaft angle and assessed the effect of changes in the hip anatomy on clinical outcomes.

In total, 44 patients (mean age 65.3 years (standard deviation (sd) 7); 17 male/27 female; mean body mass index 26.9 (kg/m²) (sd 3.1)) underwent a pre- and post-operative three-dimensional CT scanning of the hip. The pre- and post-operative neck–shaft angle, offset, hip centre of rotation, femoral anteversion, and stem alignment were measured. Additionally, a functional assessment and pain score were evaluated before surgery and at one year post-operatively and related to the post-operative anatomical changes.

The mean pre-operative neck–shaft angle was significantly increased by 2.8° from 128° (sd 6.2; 119° to 147°) to 131° (sd 2.1; 127° to 136°) (p = 0.009). The mean pre-operative anteversion was 24.9° (sd 8; 7.9 to 39.1) and reduced to 7.4° (sd 7.3; -11.6° to 25.9°) post-operatively (p < 0.001). The post-operative changes had no influence on function and pain. Using a standard uncemented femoral component, high pre- and post-operative variability of femoral anteversion and neck–shaft angles was found with a significant decrease of the post-operative anteversion and slight increase of the neck–shaft angles, but without any impact on clinical outcome.

Cite this article: Bone Joint J 2015;97-B:1615–22.