Information in the electronic health record (EHR), such as diagnoses, vital signs, utilization, medications, and laboratory values, may predict fractures well without the need to verbally ascertain risk factors. In our study, as a proof of concept, we developed and internally validated a fracture risk calculator using only information in the EHR.
OBJECTIVE: Fracture risk calculators, such as the Fracture Risk Assessment Tool, or FRAX, typically lie outside the clinician workflow. Conversely, the electronic health record (EHR) is at the center of the clinical workflow, and many variables in the EHR could predict fractures without having to verbally ascertain FRAX risk factors. We sought to evaluate the utility of EHR variables to predict fractures and, as a proof of concept, to create an EHR-based fracture risk model.
METHODS: Routine clinical data from 24,189 subjects presenting to primary care from 2010 to 2018 was utilized. Major osteoporotic fractures (MOFs) were captured by physician diagnosis codes. Data was split into training (n = 18,141) and test sets (n = 6048). We fit Cox regression models for candidate risk factors in the training set, and then created a global model using a backward stepwise approach. We then applied the model to the test set and compared the discrimination and calibration to FRAX.
RESULTS: We found variables related to vital signs, utilization, diagnoses, medications, and laboratory values to be associated with incident MOF. Our final model included 19 variables, including age, BMI, Parkinson\'s disease, chronic kidney disease, and albumin levels. When applied to the test set, we found the discrimination (AUC 0.73 vs. 0.70, p = 0.08) and calibration were comparable to FRAX.
CONCLUSIONS: Routinely collected data in EHR systems can generate adequate fracture predictions without the need to verbally ascertain fracture risk factors. In the future, this could allow for automated fracture prediction at the point of care to improve osteoporosis screening and treatment rates.

暂无摘要。

UNASSIGNED: People with coeliac disease (CD) are at increased risk of osteoporosis and fractures. Currently, baseline dual-energy X-ray absorptiometry (DXA) is recommended for all patients with newly diagnosed CD. We aimed to determine the prevalence of osteoporosis and the clinical utility of the Fracture Risk Assessment Tool (FRAX) in predicting major osteoporotic fractures (MOF) in patients with biopsy-proven CD.
UNASSIGNED: We retrospectively collected data for consecutive adult patients with biopsy-proven CD between 2001 and 2015 who underwent DXA scanning within 1 year of diagnosis and were followed up for a minimum of 7 years. Fracture risk was assessed using FRAX scores, and the incidence of major osteoporotic fractures during the follow-up period was analysed.
UNASSIGNED: A total of 593 patients (median age 45.0 years, 68.5% female) were included. The prevalence of osteopenia and osteoporosis were 32.3% and 14.5%, respectively. Increasing age (OR 1.06, p < .0001), decreasing BMI (OR 0.90, p = .003), and higher baseline immunoglobulin A-tissue tissue transglutaminase titre (OR 1.04, p = .03) were significantly associated with increased risk of osteoporosis. The sensitivity, specificity, positive and negative predictive values of the FRAX tool to predict MOF were 21.2%, 91.3%, 16.3%, 93.5%, respectively. A higher risk of fractures was associated with ongoing gluten exposure (OR 1.86, p = .02), previous fractures (OR 2.69, p = .005), and older age (OR 1.03, p < .0001).
UNASSIGNED: Osteoporosis is a common finding in patients with CD. The FRAX tool showed high specificity in predicting osteoporotic fractures and could be used to aid with patient selection for DXA scanning in some cases.

UNASSIGNED: FRAX® is a tool used for evaluation of risk of fracture in RA and non-RA patients and to identify those eligible for intervention. One of the limitations of FRAX in RA settings is that it does not consider factors known to contribute to osteoporosis such as autoantibodies. This study analysed the association of anti-mutated citrullinated vimentin antibody (anti-MCV), anti-cyclic citrullinated peptide antibody (anti-CCP), IgM rheumatoid factor (RF), IgA RF with 10-year risk of major osteoporosis and hip fracture.
UNASSIGNED: FRAX® tool was used to estimate 10-year risk of major osteoporosis fracture and hip fracture in 189 RA patients over 40 years of age. Anti-MCV, anti-CCP, IgM RF and IgA RF were tested using enzyme immunoassay and analysed at different levels. Results were adjusted for various confounders including disease activity.
UNASSIGNED: Fifty-one (26.9%) RA patients had high (≥20%) 10-year risk of major osteoporosis fracture and 67 (35.4%) had high (>3%) 10-year risk of hip fracture. Among all the tested autoantibodies, only IgM RF at elevated levels was associated with high 10-year risk of major osteoporosis fracture (adjusted OR = 4.1, 95% CI = 1.5-11.3, p = 0.006) and of hip fracture (adjusted OR = 17.4, 95% CI = 3.7-81.3, p < 0.0001). There was no agreement between FRAX and femoral neck (FN) BMD. None of the autoantibodies tested were associated with FN osteopenia or osteoporosis including IgM RF at high levels.
UNASSIGNED: Our study highlights the importance of quantitative measurement of autoantibodies in assessment of risk for fractures among RA patients. Our preliminary findings need to be assessed in prospective studies to determine the actual predictive value of high IgM RF levels among patients with RA.

暂无摘要。

The SPAH study is a population-based prospective cohort of Brazilian community-dwelling elderlies with higher fracture risk than observed in the studies used to construct the Brazilian FRAX model. In this study, the FRAX tool was a good fracture predictor within this high-risk elderly cohort, especially when calculated without bone density.
OBJECTIVE: To determine the performances of FRAX and age-dependent intervention thresholds according to National Osteoporosis Guideline Group (NOGG) guidelines with and without bone mineral density (BMD) regarding fracture prediction in community-dwelling elderly Brazilians.
METHODS: Seven hundred and five older adults (447 women; 258 men) were followed for 4.3 ± 0.8 years. FRAX risk for hip and major osteoporotic fractures with and without BMD was calculated at baseline. The bivariate analysis investigated the associations between the absolute probability of fracture (FRAX), as well as the age-dependent intervention thresholds (NOGG), and the incidence of vertebral fracture (VF), non-vertebral fracture (NVF), and major osteoporotic fractures (MOF), segregated by sex. Age-adjusted Poisson\'s multiple regression and ROC curves were constructed to determine FRAX and NOGG\'s accuracies as fracture predictors.
RESULTS: Fractures occurred in 22% of women and 15% of men. FRAX with and without BMD was higher in women with all types of fractures (p < 0.001). Only NOGG risk classification without BMD was associated with NVF (p = 0.047) and MOF (p = 0.024). FRAX was associated with NVF in the multiple regression, regardless of BMD. ROC curves of FRAX with and without BMD had AUCs of 0.74, 0.64, and 0.61 for NVF, VF, and MOF, respectively. The most accurate risk cutoffs for FRAX were 8% for MOF and 3% for hip fractures. No statistically significant associations were found in men.
CONCLUSIONS: FRAX predicted NVF more accurately than VF or MOF in elderlies, regardless of BMD. These results reiterate that FRAX may be used without BMD, even considering that Brazilian elderlies have known higher fracture risk.

Fracture prediction is essential in managing patients with osteoporosis, and is an integral component of many fracture prevention guidelines. We aimed to identify the most relevant clinical fracture risk factors in contemporary populations by training and validating short- and long-term fracture risk prediction models in two cohorts. We used traditional and machine learning survival models to predict risks of vertebral, hip and any fractures on the basis of clinical risk factors, T-scores and treatment history among participants in a nationwide Swiss osteoporosis registry (N = 5944 postmenopausal women, median follow-up of 4.1 years between January 2015 and October 2022; a total of 1190 fractures during follow-up). The independent validation cohort comprised 5474 postmenopausal women from the UK Biobank with 290 incident fractures during follow-up. Uno\'s C-index and the time-dependent area under the receiver operating characteristics curve were calculated to evaluate the performance of different machine learning models (Random survival forests and eXtreme Gradient Boosting). In the independent validation set, the C-index was 0.74 [0.58, 0.86] for vertebral fractures, 0.83 [0.7, 0.94] for hip fractures and 0.63 [0.58, 0.69] for any fractures at year 2, and these values further increased for longer estimations of up to 7 years. In comparison, the 10-year fracture probability calculated with FRAX® Switzerland was 0.60 [0.55, 0.64] for major osteoporotic fractures and 0.62 [0.49, 0.74] for hip fractures. The most important variables identified with Shapley additive explanations (SHAP) values were age, T-scores and prior fractures, while number of falls was an important predictor of hip fractures. Performances of both traditional and machine learning models showed similar C-indices. We conclude that fracture risk can be improved by including the lumbar spine T-score, trabecular bone score, numbers of falls and recent fractures, and treatment information has a significant impact on fracture prediction.
Fracture prediction is essential in managing patients with osteoporosis. We developed and validated traditional and machine learning models to predict short- and long-term fracture risk and identify the most relevant clinical fracture risk factors for vertebral, hip, and any fractures in contemporary populations. We used data from 5944 postmenopausal women in a Swiss osteoporosis registry and validated our findings with 5474 women from the UK Biobank. Our machine learning models performed well, with C-index values of 0.74 [0.58, 0.86] for vertebral fractures, 0.83 [0.7, 0.94] for hip fractures and 0.63 [0.58, 0.69] for any fractures at year 2, and these values further increased for longer estimations of up to 7 years. In contrast, FRAX® Switzerland had lower C-index values (0.60 [0.55, 0.64] for major fractures and 0.62 [0.49, 0.74] for hip fracture probabilities over 10 years). Key predictors identified included age, T-scores, prior fractures, and number of falls. We conclude that incorporating a broader range of clinical factors, as well as lumbar spine T-scores, fall history, recent fractures, and treatment information, can improve fracture risk assessments in osteoporosis management. Both traditional and machine learning models showed similar effectiveness in predicting fractures.

OBJECTIVE: To identify risk factors, including FRAX (a tool for assessing osteoporosis) scores, for development of proximal junctional kyphosis (PJK), defined as Type 2 in the Yagi-Boachie classification (bone failure), with vertebral fracture (VF) after surgery for symptomatic adult spinal deformity.
METHODS: This was a retrospective, single institution study of 127 adults who had undergone corrective long spinal fusion of six or more spinal segments for spinal deformity and been followed up for at least 2 years. The main outcome was postoperative development of PJK with VF. Possible predictors of this outcome studied included age at surgery, BMI, selected radiographic measurements, bone mineral density, and 10-year probability of major osteoporotic fracture (MOF) as determined by FRAX. We also analyzed use of medications for osteoporosis. Associations between the selected variables and PJK with VF were assessed by the Mann-Whitney, Fishers exact, and Wilcoxon signed-rank tests, and Kaplan-Meier analysis, as indicated.
RESULTS: Forty patients (31.5%) developed PJK with VF postoperatively,73% of them within 6 months of surgery. Statistical analysis of the selected variables found that only a preoperative estimate by FRAX of a > 15% risk of MOF within 10 years, pelvic tilt > 30° at first standing postoperatively and lower instrumented level (fusion terminating at the pelvis) were significantly associated with development of PJK with VF.
CONCLUSIONS: Preoperative assessment of severity of osteoporosis using FRAX provides an accurate estimate of risk of postoperative PJK with VF after surgery for adult spinal deformity.

This study established FRAX-based age-specific assessment and intervention thresholds for ten Middle Eastern countries where FRAX is currently available, but the lack of specific thresholds has limited its usefulness. The intervention thresholds ranged from 0.6 (Saudi Arabia) to 36.0% (Syria) at the ages of 40 and 90 years, respectively.
BACKGROUND: Developing fracture risk assessment tools allows physicians to select patients for therapy based on their absolute fracture risk instead of relying solely on bone mineral density (BMD). The most widely used tool is FRAX, currently available in ten Middle Eastern countries. This study aimed to set FRAX-derived assessment and intervention thresholds for individuals aged 40 or above in ten Middle Eastern countries.
METHODS: The age-specific 10-year probabilities of a major osteoporotic fracture (MOF) for a woman with a BMI of 25.0 kg/m2, without BMD and clinical risk factors except for prior fracture, were calculated as intervention Threshold (IT). The upper and lower assessment thresholds were set at 1.2 times the IT and an age-specific 10-year probability of a MOF in a woman with a BMI of 25.0 kg/m2, without BMD, prior fracture, and other clinical risk factors, respectively. IT is utilized to determine treatment or reassurance when BMD facilities are unavailable. However, with BMD facilities, assessment thresholds can offer treatment, reassurance, or bone densitometry based on MOF probability.
RESULTS: The age-specific IT varied from 0.9 to 11.0% in Abu Dhabi, 2.9 to 10% in Egypt, 2.7 to 14.0% in Iran, 1.0 to 28.0% in Jordan, 2.7 to 27.0% in Kuwait, 0.9 to 35.0% in Lebanon, 1.0 to 16.0% in Palestine, 4.1 to 14% in Qatar, 0.6 to 3.7% in Saudi Arabia, and 0.9 to 36.0% in Syria at the age of 40 and 90 years, respectively.
CONCLUSIONS: FRAX-based IT in Middle Eastern countries provides an opportunity to identify individuals with high fracture risk.

In the longitudinal, retrospective study, the ability of the FRAX, Garvan, and POL-RISK algorithms to predict osteoporotic fractures was compared in a group of 457 women. Using the rigid threshold of 10% showed a significant discrepancy in sensitivity and specificity of all tools. New thresholds for high risk of fractures were established for each calculator separately: 6.3% for FRAX major fracture, 20.0% for Garvan any fracture, and 18.0% for POL-RISK any fracture. Such thresholds allow for improving the diagnostic accuracy of all three calculators.
BACKGROUND: The aim of the longitudinal, retrospective study was to compare three tools designed to assess fracture risk: FRAX, Garvan, and POL-RISK in their prediction of fracture incidence.
METHODS: The study group consisted of 457 postmenopausal women with a mean age of 64.21 ± 5.94 years from the Gliwice Osteoporosis (GO) Study. Comprehensive data on clinical factors related to fractures were collected for all participants. Bone densitometry was performed at the proximal femur using the Prodigy device (GE, USA). Fracture risk was established using the FRAX, Garvan, and POL-RISK algorithms. Data on the incidence of osteoporotic fractures were collected over the last 10 years.
RESULTS: During the period of observation 72, osteoporotic fractures occurred in 63 subjects. For a preliminary comparison of the predictive value of analyzed diagnostic tools, the fracture risk threshold of 10% was used. For FRAX, the fracture probability exceeding 10% was observed only in 11 subjects who experienced fractures; thus, the fracture was properly predicted only in 22.9% of women. For Garvan, the respective value was 90.5%, and for POL-RISK, it was 98.4%. That gave a very low true positive value for FRAX and a very high false positive value for Garvan and POL-RISK. Based on ROC curves, new thresholds for high risk of fractures were established for each calculator separately: 6.3% for FRAX major fracture, 20.0% for Garvan any fracture, and 18.0% for POL-RISK any fracture. Such thresholds improve the diagnostic accuracy of all compared fracture prediction tools.
CONCLUSIONS: The current study showed that different fracture risk assessment tools, although having similar clinical purposes, require different cut-off thresholds for making therapeutic decisions. Better identification of patients requiring therapy based on such an approach may help reduce the number of new fractures.