To develop prediction models using machine-learning (ML) algorithms for 90-day and one-year mortality prediction in femoral neck fracture (FNF) patients aged 50 years or older based on the Hip fracture Evaluation with Alternatives of Total Hip arthroplasty versus Hemiarthroplasty (HEALTH) and Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trials. This study included 2,388 patients from the HEALTH and FAITH trials, with 90-day and one-year mortality proportions of 3.0% (71/2,388) and 6.4% (153/2,388), respectively. The mean age was 75.9 years (SD 10.8) and 65.9% of patients (1,574/2,388) were female. The algorithms included patient and injury characteristics. Six algorithms were developed, internally validated and evaluated across discrimination (c-statistic; discriminative ability between those with risk of mortality and those without), calibration (observed outcome compared to the predicted probability), and the Brier score (composite of discrimination and calibration).Aims
Methods
Patients with FNF may be treated by either total hip arthroplasty (THA) or hemiarthroplasty (HA). Utilizing American Joint Replacement Registry (AJRR) data, we aimed to evaluate outcomes in FNF treatment. Medicare patients with FNF treated with HA or THA reported to the AJRR database from 2012–2019 and CMS claims data from 2012–2017 were analyzed in this retrospective cohort study. “Early” was defined as less than 90 days from index procedure. A logistic regression model, including index arthroplasty, age, sex, stem fixation method, hospital size1, hospital teaching affiliation1, and Charlson comorbidity index (CCI), was utilized to determine associations between index procedure and revision rates.Introduction
Methods
Obesity is known to influence surgical risk in total hip replacement (THR), with increased Body Mass Index (BMI) leading to elevated risk of complications and poorer outcome scores. Using a multinational trial data of a single implant, we assess the impact of BMI and regional variations on Harris Hip scores (HHS). We assessed BMI in 11 regional centres and associations with HHS at one year. Data were collected from 744 patients prospectively from 11 centres in the UK, Germany, Switzerland, Austria, New Zealand and Netherlands as part of a multicentre outcome trial. All Arthroplasties used RM Pressfit vitamys components (Mathys, Switzerland). Demographic, operative data and HHS were analysed with General Linear Model Anova, Minitab 16 (Minitab Inc, Pennsylvania).Introduction
Method
