Aims. This study was designed to develop a model for predicting bone mineral density (BMD) loss of the femur after total hip arthroplasty (THA) using artificial intelligence (AI), and to identify factors that influence the prediction. Additionally, we virtually examined the efficacy of administration of bisphosphonate for cases with severe BMD loss based on the predictive model. Methods. The study included 538 joints that underwent primary THA. The patients were divided into groups using unsupervised time series clustering for five-year BMD loss of Gruen zone 7 postoperatively, and a machine-learning model to predict the BMD loss was developed. Additionally, the predictor for BMD loss was extracted using SHapley Additive exPlanations (SHAP). The patient-specific efficacy of bisphosphonate, which is the most important categorical predictor for BMD loss, was examined by calculating the change in predictive probability when hypothetically switching between the inclusion and exclusion of bisphosphonate. Results. Time series clustering allowed us to divide the patients into two groups, and the predictive factors were identified including patient- and operation-related factors. The area under the receiver operating characteristic (ROC) curve (AUC) for the BMD loss prediction averaged 0.734. Virtual administration of bisphosphonate showed on average 14% efficacy in preventing BMD loss of zone 7. Additionally, stem types and preoperative triglyceride (TG), creatinine (Cr), estimated glomerular filtration rate (eGFR), and creatine kinase (CK) showed significant association with the estimated patient-specific efficacy of bisphosphonate. Conclusion.
Objectives. Our primary aim was to describe migration of the Exeter stem with a 32 mm head on highly crosslinked polyethylene and whether this is influenced by age. Our secondary aims were to assess functional outcome, satisfaction, activity, and bone mineral density (BMD) according to age. Patients and Methods. A prospective cohort study was conducted. Patients were recruited into three age groups: less than 65 years (n = 65), 65 to 74 years (n = 68), and 75 years and older (n = 67). There were 200 patients enrolled in the study, of whom 115 were female and 85 were male, with a mean age of 69.9 years (sd 9.5, 42 to 92). They were assessed preoperatively, and at three, 12 and, 24 months postoperatively. Stem migration was assessed using Einzel-Bild-Röntgen-Analyse (EBRA). Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), Harris Hip Score (HHS), Hip Disability and Osteoarthritis Outcome Score (HOOS), EuroQol-5 domains questionnaire (EQ-5D), short form-36 questionnaire (SF-36,) and patient satisfaction were used to assess outcome. The Lower Extremity Activity Scale (LEAS), Timed Up and Go (TUG) test, and activPAL monitor (energy expelled, time lying/standing/walking and step count) were used to assess activity. The BMD was assessed in Gruen and Charnley zones. Results. Mean varus/valgus tilt was -0.77⁰ and axial subsidence was -1.20 mm. No significant difference was observed between age groups (p ⩾ 0.07). There was no difference according to age group for postoperative WOMAC (p ⩾ 0.11), HHS (p ⩾ 0.06), HOOS (p ⩾ 0.46), EQ-5D (p ⩾ 0.38), patient satisfaction (p ⩾ 0.05), or activPAL (p ⩾ 0.06). Patients 75 years and older had a worse SF-36 physical function (p = 0.01) and physical role (p = 0.03), LEAS score (p < 0.001), a shorter TUG (p = 0.01), and a lower BMD in Charnley zone 1 (p = 0.02). Conclusion. Exeter stem migration is within normal limits and is not influenced by age group. Functional outcome, patient satisfaction, activity level, and
