An overview of the use of the fracture risk assessment tool (FRAX) in osteoporosis.

FRAX®, a simple-to-use fracture risk calculator, was first released in 2008 and since then has been used increasingly worldwide. By calculating the 10-year probabilities of a major osteoporotic fracture and hip fracture, it assists clinicians when deciding whether further investigation, for example a bone mineral density measurement (BMD), and/or treatment is needed to prevent future fractures. In this review, we explore the literature around osteoporosis and how FRAX has changed its management. We present the characteristics of this tool and describe the use of thresholds (diagnostic and therapeutic). We also present arguments as to why screening with FRAX should be considered. FRAX has several limitations which are described in this review. This review coincides with the release of a version, FRAXplus, which addresses some of these limitations.

Clinical Use of Trabecular Bone Score: The 2023 ISCD Official Positions.

Osteoporosis can currently be diagnosed by applying the WHO classification to bone mineral density (BMD) assessed by dual-energy x-ray absorptiometry (DXA). However, skeletal factors other than BMD contribute to bone strength and fracture risk. Lumbar spine TBS, a grey-level texture measure which is derived from DXA images has been extensively studied, enhances fracture prediction independent of BMD and can be used to adjust fracture probability from FRAX® to improve risk stratification. The purpose of this International Society for Clinical Densitometry task force was to review the existing evidence and develop recommendations to assist clinicians regarding when and how to perform, report and utilize TBS. Our review concluded that TBS is most likely to alter clinical management in patients aged ≥ 40 years who are close to the pharmacologic intervention threshold by FRAX. The TBS value from L1-L4 vertebral levels, without vertebral exclusions, should be used to calculate adjusted FRAX probabilities. L1-L4 vertebral levels can be used in the presence of degenerative changes and lumbar compression fractures. It is recommended not to report TBS if extreme structural or pathological artifacts are present. Monitoring and reporting TBS change is unlikely to be helpful with the current version of the TBS algorithm. The next version of TBS software will include an adjustment based upon directly measured tissue thickness. This is expected to improve performance and address some of the technical factors that affect the current algorithm which may require modifications to these Official Positions as experience is acquired with this new algorithm.

Prediction of subsequent fragility fractures: application of machine learning.

BACKGROUND: Machine learning (ML) has shown exceptional promise in various domains of medical research. However, its application in predicting subsequent fragility fractures is still largely unknown. In this study, we aim to evaluate the predictive power of different ML algorithms in this area and identify key features associated with the risk of subsequent fragility fractures in osteoporotic patients. METHODS: We retrospectively analyzed data from patients presented with fragility fractures at our Fracture Liaison Service, categorizing them into index fragility fracture (n = 905) and subsequent fragility fracture groups (n = 195). We independently trained ML models using 27 features for both male and female cohorts. The algorithms tested include Random Forest, XGBoost, CatBoost, Logistic Regression, LightGBM, AdaBoost, Multi-Layer Perceptron, and Support Vector Machine. Model performance was evaluated through 10-fold cross-validation. RESULTS: The CatBoost model outperformed other models, achieving 87% accuracy and an AUC of 0.951 for females, and 93.4% accuracy with an AUC of 0.990 for males. The most significant predictors for females included age, serum C-reactive protein (CRP), 25(OH)D, creatinine, blood urea nitrogen (BUN), parathyroid hormone (PTH), femoral neck Z-score, menopause age, number of pregnancies, phosphorus, calcium, and body mass index (BMI); for males, the predictors were serum CRP, femoral neck T-score, PTH, hip T-score, BMI, BUN, creatinine, alkaline phosphatase, and spinal Z-score. CONCLUSION: ML models, especially CatBoost, offer a valuable approach for predicting subsequent fragility fractures in osteoporotic patients. These models hold the potential to enhance clinical decision-making by supporting the development of personalized preventative strategies.

Bone metabolism factors in predicting the risk of osteoporosis fracture in the elderly.

OBJECTIVE: Osteoporosis (OS) is a systemic bone disease characterized by low bone mass and bone microstructure damage. This study. METHODS: According to the T value, 88 elderly fracture patients were grouped as the control group (without OS, 43 cases) and observation group (with T value <-2.5, which could be diagnosed as OS, 45 cases). The content of boney containing protein (BGP), total type 1 collagen amino terminal extender peptide (TPINP), ß-Crosslaps (ß-CTX), parathyroid hormone (PTH) and insulin-like growth factors-1 (IGF-1) was compared. Multivariate logistic regression was adopted to analyze the correlation between biochemical indexes and the occurrence of senile OS fracture and the related risk factors. The diagnostic value in the elderly was analyzed by receiver operating characteristic (ROC) curve. RESULTS: The levels of BGP, TPINP, ß-CTX, PTH and IGF-1 were elevated, and the level of IGF-1 was decreased in the observation group compared with the control group (P < 0.05). The elevated content of BGP, TPINP, ß-CTX and PTH, and the decreased expression of IGF-1 were influencing factors for OS fractures in the elderly (P < 0.05). The sensitivity and specificity to predict the occurrence of OS fractures in the elderly were 91.70% and 90.50%, respectively. The AUC of combined detection was 0.976 (95% CI: 0.952-1.000), which was memorably higher than single indicator detection (P < 0.05). Among 45 patients, 32 cases had good prognosis and 13 had poor prognosis. In comparison with the good prognosis group, the content of BGP, TPINP, ß-CTX and PTH were sensibly higher, the level of IGF-1 was prominently lower, and the proportion of fracture history was much higher in poor prognosis group (P < 0.05). Fracture history, BGP, TPINP, ß-CTX, PTH and IGF-1 were independent risk factors for poor prognosis of elderly OS fractures (P < 0.05). CONCLUSION: Bone metabolism factors were associated with poor prognosis of OS in the elderly. The combined detection had higher diagnostic value in calculating the risk of OS fracture in the elderly than single indicator detection.

Predicting osteoporotic fractures post-vertebroplasty: a machine learning approach with a web-based calculator.

PURPOSE: The aim of this study was to develop and validate a machine learning (ML) model for predicting the risk of new osteoporotic vertebral compression fracture (OVCF) in patients who underwent percutaneous vertebroplasty (PVP) and to create a user-friendly web-based calculator for clinical use. METHODS: A retrospective analysis of patients undergoing percutaneous vertebroplasty: A retrospective analysis of patients treated with PVP between June 2016 and June 2018 at Liuzhou People's Hospital was performed. The independent variables of the model were screened using Boruta and modelled using 9 algorithms. Model performance was assessed using the area under the receiver operating characteristic curve (ROC_AUC), and clinical utility was assessed by clinical decision curve analysis (DCA). The best models were analysed for interpretability using SHapley Additive exPlanations (SHAP) and the models were deployed visually using a web calculator. RESULTS: Training and test groups were split using time. The SVM model performed best in both the training group tenfold cross-validation (CV) and validation group AUC, with an AUC of 0.77. DCA showed that the model was beneficial to patients in both the training and test sets. A network calculator developed based on the SHAP-based SVM model can be used for clinical risk assessment ( https://nicolazhang.shinyapps.io/refracture_shap/ ). CONCLUSIONS: The SVM-based ML model was effective in predicting the risk of new-onset OVCF after PVP, and the network calculator provides a practical tool for clinical decision-making. This study contributes to personalised care in spinal surgery.

[Update on the DVO Guideline 2023 "Prophylaxis, diagnosis and treatment of osteoporosis in postmenopausal women and in men aged over 50"-What's new for rheumatology?] / Update DVO-Leitlinie 2023 "Prophylaxe, Diagnostik und Therapie der Osteoporose bei postmenopausalen Frauen und bei Männern ab dem 50. Lebensjahr" ­ Was ist neu für die Rheumatologie?

In October 2023, the organization of the German-speaking scientific osteological societies (DVO) published the revised guideline on the "Prophylaxis, diagnosis and treatment of osteoporosis in postmenopausal women and in men aged over 50." This review article reflects the new features of the guideline and their relevance in the care of patients with inflammatory rheumatic diseases.A key innovation is the change from the 10-year fracture risk to the 3­year fracture risk. Basic diagnostics are currently performed without a defined fracture threshold. Treatment thresholds for specific osteological therapy constitute another key innovation, defined as 3% to < 5%, 5% to < 10%, and from 10% for vertebral body and femoral neck fractures. If the 3­year fracture risk is > 10%, osteoanabolic therapy should primarily be carried out and antiresorptive therapy is initiated following osteoanabolic therapy. In addition, patients with osteoporosis and prolonged glucocorticoid therapy should primarily be treated osteoanabolically with teriparatide. In summary, the changes to the DVO guideline reflect the latest scientific study findings in osteology and lead to detailed differential therapy for osteoporosis.

[Fragility Fractures: Preoperative assessment and optimisation]. / Fragilitätsfraktur beim geriatrischen Patienten: Präoperative Abklärung und Optimierung.

Fragility fractures are associated with high morbidity and mortality. An interdisciplinary collaboration and an individualized, patient-centered approach are essential to ensure an optimized preoperative period and to improve perioperative safety. Preoperative responsibilities of trauma surgery include in the first step the identification of fragility fractures and the necessity for geriatric involvement. Orthogeriatric co-management (OCM) focuses on the identification of the medical, functional and social needs of the patient. In the preoperative period attention is focussed on acute diseases in need of treatment that have a negative impact on the course of further treatment and the prevention of delirium.

[Conservative fracture treatment in old people]. / Konservative Frakturversorgung bei alten Menschen.

The numbers of osteoporotic fractures will increase due to the demographic change, which particularly affects the proximal femur, pelvis, proximal humerus, wrist and vertebral column. Surgical treatment is superior to conservative treatment of proximal femoral fractures. Non-dislocated fractures of the wrist can also be treated with a plaster cast but studies suggest that the results in the first 12 months are better after surgical treatment. The situation is similar for fractures of the proximal humerus and non-dislocated fractures in particular can also be treated conservatively. A score and classification were recently developed for making decisions on the treatment of osteoporotic vertebral fractures. Fractures of the anterior and posterior pelvic ring can be treated conservatively with the patient under sufficient analgesia as long as there is no substantial dislocation. The highest priority in geriatric traumatology is fast remobilization.

The need to distinguish intervention thresholds and diagnostic thresholds in the management of osteoporosis.

This position paper of the International Osteoporosis Foundation (IOF) and the European Society for Clinical and Economic Aspects of Osteoporosis, Osteoarthritis and Musculoskeletal Diseases (ESCEO) addresses the rationale for separate diagnostic and intervention thresholds in osteoporosis. We conclude that the current BMD-based diagnostic criteria for osteoporosis be retained whilst clarity is brought to bear on the distinction between diagnostic and intervention thresholds.

Fracture liaison service model: project design and accreditation.

Frailty fractures place a significant socioeconomic burden on the health care system. The Italian Society of Orthopaedics and Traumatology (SIOT) is proceeding to fracture liaison service (FLS) model accreditation in several Italian Fracture Units (FUs), which provides a multidisciplinary approach for the management of the fragility fracture patient. INTRODUCTION: Osteoporosis and the resulting fragility fractures, particularly femoral fractures, place significant socioeconomic burdens on the health care system globally. In addition, there is a general lack of awareness of osteoporosis, resulting in underestimation of the associated risks and suboptimal treatment of the disease. The fracture liaison service (FLS) represents an exemplary model of post-fracture care that involves a multidisciplinary approach to the frail patient through the collaboration of multiple specialists. The purpose of this article is to highlight the path undertaken by the Italian Society of Orthopaedics and Traumatology (SIOT) for the purpose of certification of numerous FLS centers throughout Italy. METHODS: SIOT is proceeding with international FLS accreditation in several Italian Fracture Units (FUs), following the creation of a model that provides specific operational and procedural steps for the management of fragility fractures throughout the country. FUs that decide to join the project and implement this model within their facility are then audited by an ACCREDIA-accredited medical certification body. RESULTS: The drafted FLS model, thanks to the active involvement of a panel of experts appointed by SIOT, outlines a reference operational model that describes a fluid and articulated process that identifies the procedure of identification, description of diagnostic framing, and subsequent initiation of appropriate secondary prevention programs for fractures of individuals who have presented with a recent fragility fracture of the femur. CONCLUSION: Accreditation of this prevention model will enable many facilities to take advantage of this dedicated diagnostic-therapeutic pathway for the purpose of fracture prevention and reduction of associated health and social costs.

Should vertebral fracture assessment be performed in Fracture Liaison Service patients with non-vertebral fracture?

Prior non-vertebral fractures, except of the ankle, are associated with increased likelihood of vertebral fracture. As knowledge of vertebral fracture presence may alter care, vertebral fracture assessment (VFA) is indicated in patients with prior fracture. INTRODUCTION: Vertebral fractures are often unappreciated. It was recently advocated that all Fracture Liaison Service (FLS) patients have densitometric VFA performed. We evaluated the likelihood of vertebral fracture identification with VFA in patients with prior fracture using the Manitoba Bone Density database. METHODS : VFA was performed in patients with T-scores below - 1.5 and age 70 + (or younger with height loss or glucocorticoid use) obtaining bone densitometry in Manitoba from 2010 to 2018. Those with prior clinical vertebral fracture, pathologic fracture, or uninterpretable VFA were excluded. Vertebral fractures were identified using the modified ABQ method. Health records were assessed for non-vertebral fracture (excluding head, neck, hand, foot) diagnosis codes unassociated with trauma prior to DXA. Multivariable odds ratios (ORs) for vertebral fracture were estimated without and with adjustment for age, sex, body mass index, ethnicity, area of residence, income level, comorbidity score, diabetes mellitus, falls in the last year, glucocorticoid use, and lowest BMD T-score. RESULTS: The study cohort consisted of 12,756 patients (94.4% women) with mean (SD) age 75.9 (6.8) years. Vertebral fractures were identified in 1925 (15.1%) overall. Vertebral fractures were significantly more likely (descending order) in those with prior pelvis, hip, humerus, other sites, and forearm, but not ankle fracture. There was modest attenuation with covariate adjustment but statistical significance was maintained. CONCLUSIONS: Prior hip, humerus, pelvis, forearm, and other fractures are associated with an increased likelihood of previously undiagnosed vertebral fracture, information useful for risk stratification and monitoring. These data support recommending VFA in FLS patients who are age 70 + with low BMD.

Electronic Health Records (EHRs) Can Identify Patients at High Risk of Fracture but Require Substantial Race Adjustments to Currently Available Fracture Risk Calculators.

BACKGROUND: Osteoporotic fracture prediction calculators are poorly utilized in primary care, leading to underdiagnosis and undertreatment of those at risk for fracture. The use of these calculators could be improved if predictions were automated using the electronic health record (EHR). However, this approach is not well validated in multi-ethnic populations, and it is not clear if the adjustments for race or ethnicity made by calculators are appropriate. OBJECTIVE: To investigate EHR-generated fracture predictions in a multi-ethnic population. DESIGN: Retrospective cohort study using data from the EHR. SETTING: An urban, academic medical center in Philadelphia, PA. PARTICIPANTS: 12,758 White, 7,844 Black, and 3,587 Hispanic patients seeking routine care from 2010 to 2018 with mean 3.8 years follow-up. INTERVENTIONS: None. MEASUREMENTS: FRAX and QFracture, two of the most used fracture prediction tools, were studied. Risk for major osteoporotic fracture (MOF) and hip fracture were calculated using data from the EHR at baseline and compared to the number of fractures that occurred during follow-up. RESULTS: MOF rates varied from 3.2 per 1000 patient-years in Black men to 7.6 in White women. FRAX and QFracture had similar discrimination for MOF prediction (area under the curve, AUC, 0.69 vs. 0.70, p=0.08) and for hip fracture prediction (AUC 0.77 vs 0.79, p=0.21) and were similar by race or ethnicity. FRAX had superior calibration than QFracture (calibration-in-the-large for FRAX 0.97 versus QFracture 2.02). The adjustment factors used in MOF prediction were generally accurate in Black women, but underestimated risk in Black men, Hispanic women, and Hispanic men. LIMITATIONS: Single center design. CONCLUSIONS: Fracture predictions using only EHR inputs can discriminate between high and low risk patients, even in Black and Hispanic patients, and could help primary care physicians identify patients who need screening or treatment. However, further refinements to the calculators may better adjust for race-ethnicity.

Validation of the clinical consensus recommendations on the management of fracture risk in postmenopausal women with type 2 diabetes.

BACKGROUND AND AIMS: Bone fragility is recognized as a complication of type 2 diabetes (T2D). However, the fracture risk in T2D is underestimated using the classical assessment tools. An expert panel suggested the diagnostic approaches for the detection of T2D patients worthy of bone-active treatment. The aim of the study was to apply these algorithms to a cohort of T2D women to validate them in clinical practice. METHODS AND RESULTS: The presence of T2D-specific fracture risk factors (T2D ≥ 10 years, ≥1 T2D complications, insulin or thiazolidinedione use, poor glycaemic control) was assessed at baseline in 107 postmenopausal T2D women. In all patients at baseline and in 34 patients after a median follow-up of 60.2 months we retrospectively evaluated bone mineral density and clinical and morphometric vertebral fractures. No patient was treated with bone-active drug. Following the protocols, 34 (31.8%) and 73 (68.2%) patients would have been pharmacologically and conservatively treated, respectively. Among 49 patients without both clinical fractures and major T2D-related risk factors, who would have been, therefore, conservatively followed-up without vertebral fracture assessment, only one showed a prevalent vertebral fracture (sensitivity 90%, negative predictive value 98%). The two patients who experienced an incident fracture would have been pharmacologically treated at baseline. CONCLUSIONS: The clinical consensus recommendations showed a very good sensitivity in identifying T2D postmenopausal women at high fracture risk. Among those with treatment indication as many as 13% of patients experienced an incident fracture, and, conversely, among those without treatment indication no incident fractures were observed.

A systematic review on the performance of fracture risk assessment tools: FRAX, DeFRA, FRA-HS.

PURPOSE: Preventing fragility fractures by treating osteoporosis may reduce disability and mortality worldwide. Algorithms combining clinical risk factors with bone mineral density have been developed to better estimate fracture risk and possible treatment thresholds. This systematic review supported panel members of the Italian Fragility Fracture Guidelines in recommending the use of best-performant tool. The clinical performance of the three most used fracture risk assessment tools (DeFRA, FRAX, and FRA-HS) was assessed in at-risk patients. METHODS: PubMed, Embase, and Cochrane Library were searched till December 2020 for studies investigating risk assessment tools for predicting major osteoporotic or hip fractures in patients with osteoporosis or fragility fractures. Sensitivity (Sn), specificity (Sp), and areas under the curve (AUCs) were evaluated for all tools at different thresholds. Quality assessment was performed using the Quality Assessment of Diagnostic Accuracy Studies-2; certainty of evidence (CoE) was evaluated using the Grading of Recommendations Assessment, Development and Evaluation approach. RESULTS: Forty-three articles were considered (40, 1, and 2 for FRAX, FRA-HS, and DeFRA, respectively), with the CoE ranging from very low to high quality. A reduction of Sn and increase of Sp for major osteoporotic fractures were observed among women and the entire population with cut-off augmentation. No significant differences were found on comparing FRAX to DeFRA in women (AUC 59-88% vs. 74%) and diabetics (AUC 73% vs. 89%). FRAX demonstrated non-significantly better discriminatory power than FRA-HS among men. CONCLUSION: The task force formulated appropriate recommendations on the use of any fracture risk assessment tools in patients with or at risk of fragility fractures, since no statistically significant differences emerged across different prediction tools.

Research for correlation between heart rate variability parameters and bone mineral density in patients of type 2 diabetes mellitus.

PURPOSE: The relationship of CAN and BMD, fracture risk is still unclear in T2DM. The aim of the present study is to investigate the correlation between heart rate variability (HRV) and BMD in T2DM. METHODS: The study included 276 patients with T2DM aged ≥ 50 years, and Cardiovascular Autonomic Reflex Tests (CARTs) were applied to divide patients into two groups: CAN ( ±). 24 h Ambulatory ECG was assessed for HRV, BMD was measured by dual-energy X-ray bone densitometry, and FRAX scores were calculated for 10-year hip fracture risk (HF1) and major osteoporotic fracture risk (MOF). Adjusted regression analysis was performed to investigate influence factors for BMD and fracture risk. ROC curve was used to analyze the optimal cut-off point of LF/HF for screening osteoporosis. RESULTS: Baseline data showed significant differences in the duration of T2DM, insulin resistance index (HOMA-IR), 25-hydroxyvitamin D[25(OH)D], femoral neck BMD, hip BMD, lumbar BMD, HF1, and MOF between the CAN ( +) and CAN (-) groups. The proportion of patients with osteoporosis increased as the degree of CAN lesion increased. Correlation analysis showed that LF/HF was significantly correlated with BMD, especially with hip (r = - 0.534, p < 0.001). Regression analysis showed that LF/HF was a risk factor for reduced BMD and increased fracture risk. The optimal cut-point value for LF/HF to predict osteoporosis by ROC curve analysis was 3.17. CONCLUSIONS: CAN is associated with reduced BMD and increased fracture risk in patients with T2DM, and LF/HF may have the potential to be a predictor of diabetic osteoporosis and have some clinical value in early diagnosis of diabetic osteoporosis and non-traumatic fractures in T2DM.

Body composition, trabecular bone score and vertebral fractures in subjects with Klinefelter syndrome.

BACKGROUND: Klinefelter syndrome (KS) frequently causes skeletal fragility characterized by profound alterations in bone microstructure with increased risk of fractures. Increased body fat mass associated with decreased body lean mass are frequent features of KS with possible detrimental effects on skeletal health. In this cross-sectional study, we evaluated the associations between body composition parameters, vertebral fractures (VFs) and trabecular bone score (TBS) in adult subjects with KS. METHODS: Seventy-one adult males (median age 41 years, range 18-64) with 47, XXY KS were consecutively enrolled by two Endocrinology and Andrology Units (IRCCS Humanitas Research Hospital in Milan and ASST Spedali Civili in Brescia). Dual-energy X-ray absorptiometry (DXA) was performed to assess bone mineral density (BMD) at lumbar spine, femoral neck and total hip, TBS and body composition. Prevalence of VFs was assessed by quantitative morphometry on lateral spine X-rays. RESULTS: VFs were detected in 14 patients (19.7%), without significant association with low BMD (p = 0.912). In univariate logistic regression analysis, VFs were significantly associated with truncal/leg fat ratio (OR 2.32 per tertile; 95% CI 1.05-5.15; p = 0.038), whereas impaired TBS (detected in 23.4% of subjects) was associated with older age at study entry (p = 0.001) and at diagnosis of disease (p = 0.015), body mass index (BMI; p = 0.001), waist circumference (p = 0.007), fat mass index (FMI; p < 0.001), FMI/lean mass index (LMI) ratio (p = 0.001). Prevalence of VFs was not significantly different between subjects with impaired TBS as compared to those with normal TBS (26.7 vs. 18.4%; p = 0.485). Skeletal end-points were not significantly associated with duration of testosterone replacement therapy and serum testosterone and 25hydroxyvitamin D values. CONCLUSION: Body composition might influence bone quality and risk of VFs in subjects with KS.

Age-dependent gender differences in the diagnosis and treatment of osteoporosis during hospitalization in patients with fragility fractures.

BACKGROUND: There is a gender difference in the acceptance of osteoporosis diagnosis and treatment in patients after fragility fractures, but this difference is rarely assessed during hospitalization, and it is unclear whether these differences are age-dependent. This study aimed to evaluate the differences between male and female fragility fracture patients of different age groups who received the diagnosis and treatment of osteoporosis during hospitalization. METHODS: 31,265 fragility fracture patients aged ≥ 50 years from the Fragility Fracture Management Database in a high-volume orthopedic hospital from December 2019 to February 2023 were included in this study. We compared the differences in the rates of men and women with fragility fracture who received the measurement of bone mineral density (BMD) and bone metabolism biochemical markers (BMBMs) and treatment with anti-osteoporosis medications (AOMs), and follow-up to the internal medicine clinic within 3 months after discharge, across all age groups and across different age stages (50-59, 60-69, 70-79, and ≥ 80 years). RESULTS: The detection rates of female patients receiving BMD and BMBMs during hospitalization were 31.88% and 5.30%, respectively, compared with 22.23% and 2.69% for men. The rate of receiving any AOMs treatment was 44.63% for women and 31.60% for men. The follow-up rate of returning to the internal medicine clinic within 3 months after discharge was 9.79% for women compared to 3.00% for men. There was a significant difference between males compared to females (P < 0.0001). Analysis of patients by different age group revealed that differences in the diagnosis and treatment of osteoporosis were found only in patients under 80 years of age, while gender differences in the return to the internal medicine clinic for follow-up after discharge were present in all age groups. CONCLUSIONS: Gender differences present in osteoporosis management in patients with fragility fracture during hospitalization, especially for patients under 80 years of age. This finding suggests that orthopedic surgeons neglect to manage osteoporosis in male patients with fragility fracture during hospitalization.

Differentiation of benign and malignant vertebral fractures using a convolutional neural network to extract CT-based texture features.

PURPOSE: To assess the diagnostic performance of three-dimensional (3D) CT-based texture features (TFs) using a convolutional neural network (CNN)-based framework to differentiate benign (osteoporotic) and malignant vertebral fractures (VFs). METHODS: A total of 409 patients who underwent routine thoracolumbar spine CT at two institutions were included. VFs were categorized as benign or malignant using either biopsy or imaging follow-up of at least three months as standard of reference. Automated detection, labelling, and segmentation of the vertebrae were performed using a CNN-based framework ( https://anduin.bonescreen.de ). Eight TFs were extracted: Varianceglobal, Skewnessglobal, energy, entropy, short-run emphasis (SRE), long-run emphasis (LRE), run-length non-uniformity (RLN), and run percentage (RP). Multivariate regression models adjusted for age and sex were used to compare TFs between benign and malignant VFs. RESULTS: Skewnessglobal showed a significant difference between the two groups when analyzing fractured vertebrae from T1 to L6 (benign fracture group: 0.70 [0.64-0.76]; malignant fracture group: 0.59 [0.56-0.63]; and p = 0.017), suggesting a higher skewness in benign VFs compared to malignant VFs. CONCLUSION: Three-dimensional CT-based global TF skewness assessed using a CNN-based framework showed significant difference between benign and malignant thoracolumbar VFs and may therefore contribute to the clinical diagnostic work-up of patients with VFs.

Gastrointestinal disease is an important influencing factor of osteoporosis fracture:a retrospective study in chinese postmenopausal women.

BACKGROUD: The influencing factors of osteoporosis are complex, the incidence of osteoporosis is higher in middle-aged and elderly women, and osteoporotic fractures (OF) can seriously affect quality of life. Currently, the correlation analysis between gastrointestinal diseases and OF focuses more on diseases such as gastric cancer and inflammatory bowel disease (IBD). This study analyzed the risk factors for osteoporosis and osteoporotic fractures in 1567 postmenopausal women in Fuzhou, China. The purpose is to explore the potential influence of gastrointestinal diseases on the occurrence of OF. METHODS: According to inclusion and exclusion criteria, a total of 1567 subjects were included in the analysis of OP risk factors, including 647 in the OP group and 920 in the NOP group. A total of 616 subjects were included in the analysis of correlation between OF and gastrointestinal diseases, including 132 in OF group and 484 in NF group. Statistical analysis shows that age (OR = 1.062, 95% CI = 1.045-1.080), height (OR = 0.089, 95% CI = 0.009-0.857), weight (OR = 0.981,95% CI = 0.967-0.995) and nature of work (P = 0.010) are the main risk factors for osteoporosis in postmenopausal women in southeast China, and gastrointestinal diseases (OR = 1.583, 95% CI = 1.070-2.343) and height (OR = 0.003, 95% CI = 0.000-0.104) are the main risk factors of OF. CONCLUSIONS: The main factors affecting the occurrence of OP in postmenopausal women in southeast China are individual characteristic. Gastrointestinal diseases that do not directly affect BMD increase the risk of OF in osteoporotic patients.

The Impact of Persistent Low Weight Status on the Occurrence of Vertebral Fractures: A Nationwide Population-Based Cohort Study.

BACKGROUND: Although, being underweight is commonly associated with osteoporosis and sarcopenia, its association with vertebral fractures (VFs), is less well researched. We investigated the influence of cumulative, chronic periods of low weight and changes in body weight on VF development. METHODS: We used a nationwide, population-based database with data on people (> 40 years) who attended three health screenings between January 1, 2007, and December 31, 2009 to assess the incidence of new VFs. Cox proportional hazard analyses were used to establish the hazard ratios (HRs) for new VFs based on the degree of body mass index (BMI), the cumulative numbers of underweight participants, and temporal change in weight. RESULTS: Of the 561,779 individuals in this analysis, 5,354 (1.0%) people were diagnosed three times, 3,672 (0.7%) were diagnosed twice, and 6,929 (1.2%) were diagnosed once. The fully adjusted HR for VFs in underweight individuals was 1.213. Underweight individuals diagnosed only once, twice, or three times had an adjusted HR of 0.904, 1.443, and 1.256, respectively. Although the adjusted HR was higher in adults who were consistently underweight, there was no difference in those who experienced a temporal change in body weight. BMI, age, sex, and household income were significantly associated with VF incidence. CONCLUSION: Low weight is a risk factor for VFs in the general population. Given the significant correlation between cumulative periods of low weight and the risk of VFs, it is necessary to treat underweight patients before a VF to prevent its development and other osteoporotic fractures.