[Endoprosthetic treatment of femoral neck fractures in Germany : Cumulative analysis of EPRD registry data from 2013 to 2020]. / Endoprothetische Versorgung von Schenkelhalsfrakturen in Deutschland : Kumulative Analyse der Registerdaten des EPRD von 2013 bis 2020.

ABSTRACT

BACKGROUND: The German Arthroplasty Registry (EPRD) recorded nearly 52,000 femoral neck fractures treated with arthroplasty by 2020. This study aimed to identify survival rates and risk factors for hip prosthesis failure. MATERIAL AND METHODS: The study included all patients with arthroplasty after hip fractures documented in the EPRD. Data were analyzed with focus on failure rate regarding implant, implantation technique, age, BMI, and comorbidities. For more complex analysis of dependencies, the machine learning algorithm (MLA) XGBoost (Extreme Gradient Boosting) was used. RESULTS: The study included 51,938 patients. The failure rate was 3.7% for HEs and 5.6% for THA. The failure rate increased in male patients (p < 0.0001), those with higher BMI, young patients with a high Elixhauser Comorbidity Score (ECS) and a cementless technique. The timepoint of surgery, i.e. ,working day vs. weekend or holiday had no influence on the outcome. The feature importance (FI) generated by MLA demonstrated factors with the highest impact on failure, i.e., survival time (1029), BMI (722), and age (481). CONCLUSION: For younger patients with comorbidities, a cemented implantation technique should be considered. Failure rates of arthroplasties did not differ on workdays compared to weekends or holidays. MLA are suitable to analyze registry data for complex correlations of factors.