No abstract

No abstract

Four machine learning models were developed and compared to predict the risk of a future major osteoporotic fracture (MOF), defined as hip, wrist, spine and humerus fractures, in patients with a prior fracture. We developed a user-friendly tool for risk calculation of subsequent MOF in osteopenia patients, using the best performing model. Introduction Major osteoporotic fractures (MOFs), defined as hip, wrist, spine and humerus fractures, can have serious consequences regarding morbidity and mortality. Machine learning provides new opportunities for fracture prediction and may aid in targeting preventive interventions to patients at risk of MOF. The primary objective is to develop and compare several models, capable of predicting the risk of MOF as a function of time in patients seen at the fracture and osteoporosis outpatient clinic (FOclinic) after sustaining a fracture. Methods Patients aged > 50 years visiting an FO-clinic were included in this retrospective study. We compared discriminative ability (concordance index) for predicting the risk on MOF with a Cox regression, random survival forests (RSF) and an artificial neural network (ANN)-DeepSurv model. Missing data was imputed using multiple imputations by chained equations (MICE) or RSF's imputation function. Analyses were performed for the total cohort and a subset of osteopenia patients without vertebral fracture. Results A total of 7578 patients were included, 805 (11%) patients sustained a subsequent MOF. The highest concordance-index in the total dataset was 0.697 (0.664-0.730) for Cox regression; no significant difference was determined between the models. In the osteopenia subset, Cox regression outperformed RSF (p = 0.043 and p = 0.023) and ANN-DeepSurv (p = 0.043) with a cindex of 0.625 (0.562-0.689). Cox regression was used to develop a MOF risk calculator on this subset. Conclusion We show that predicting the risk of MOF in patients who already sustained a fracture can be done with adequate discriminative performance. We developed a user-friendly tool for risk calculation of subsequent MOF in patients with osteopenia.

No abstract

In the past 10 years after implementation, the orthogeriatric treatment model led in general to consistent outcomes for 1555 older adults in terms of most of the complications and mortality. Surgery was more often delayed to 24-48 h after arrival at the hospital, while the length of hospital stay shortened. Introduction Since 1 April 2008, patients aged ≥ 70 years presenting themselves with a hip fracture at Ziekenhuisgroep Twente (ZGT) have been treated according to the orthogeriatric treatment model. The aim of this study was to investigate if outcomes of the orthogeriatric treatment model are consistent over the first 10 years after implementation. Methods Between 1 April 2008 and 31 December 2016, patients aged ≥ 70 years who were surgically treated at ZGT for a hip fracture were included and divided into three periods equally distributed in time. Patient characteristics, in-hospital logistics, complications, and mortality data were compared between the three periods. Results A total of 1555 patients were included. There was a shift in the surgical treatment for the fractured neck of femur from dynamic hip screw/cannulated screws to hemiarthroplasty (p < 0.001). Surgery within 24 h after arrival to the hospital decreased (p < 0.001), while surgery within 48 h stayed the same (p = 0.085). Length of hospital stay significantly decreased over time (p < 0.001). Complication rates were consistent except for the number of postoperative anemia, delirium, and urinary tract infections. Mortality rates did not change over the years. Conclusions The orthogeriatric treatment model leads in general to consistent outcomes concerning mortality and most of the complications, except for postoperative anemia, delirium, and urinary tract infections. Inconsistent complication rates were influenced by altered diagnosis and treatment protocols. Length of hospital stay reduced, while time to surgery was more often delayed to 24-48 h. Monitoring clinical outcomes of the orthogeriatric treatment model over time is recommended in order to optimize and maintain the quality of care for this frail patient population.