Bone Strain Index predicts fragility fracture in osteoporotic women: an artificial intelligence-based study.

BACKGROUND: We applied an artificial intelligence-based model to predict fragility fractures in postmenopausal women, using different dual-energy x-ray absorptiometry (DXA) parameters. METHODS: One hundred seventy-four postmenopausal women without vertebral fractures (VFs) at baseline (mean age 66.3 ± 9.8) were retrospectively evaluated. Data has been collected from September 2010 to August 2018. All subjects performed a spine x-ray to assess VFs, together with lumbar and femoral DXA for bone mineral density (BMD) and the bone strain index (BSI) evaluation. Follow-up exams were performed after 3.34 ± 1.91 years. Considering the occurrence of new VFs at follow-up, two groups were created: fractured versus not-fractured. We applied an artificial neural network (ANN) analysis with a predictive tool (TWIST system) to select relevant input data from a list of 13 variables including BMD and BSI. A semantic connectivity map was built to analyse the connections among variables within the groups. For group comparisons, an independent-samples t-test was used; variables were expressed as mean ± standard deviation. RESULTS: For each patient, we evaluated a total of n = 6 exams. At follow-up, n = 69 (39.6%) women developed a VF. ANNs reached a predictive accuracy of 79.56% within the training testing procedure, with a sensitivity of 80.93% and a specificity of 78.18%. The semantic connectivity map showed that a low BSI at the total femur is connected to the absence of VFs. CONCLUSION: We found a high performance of ANN analysis in predicting the occurrence of VFs. Femoral BSI appears as a useful DXA index to identify patients at lower risk for lumbar VFs.

Bone strain index as a predictor of further vertebral fracture in osteoporotic women: An artificial intelligence-based analysis.

BACKGROUND: Osteoporosis is an asymptomatic disease of high prevalence and incidence, leading to bone fractures burdened by high mortality and disability, mainly when several subsequent fractures occur. A fragility fracture predictive model, Artificial Intelligence-based, to identify dual X-ray absorptiometry (DXA) variables able to characterise those patients who are prone to further fractures called Bone Strain Index, was evaluated in this study. METHODS: In a prospective, longitudinal, multicentric study 172 female outpatients with at least one vertebral fracture at the first observation were enrolled. They performed a spine X-ray to calculate spine deformity index (SDI) and a lumbar and femoral DXA scan to assess bone mineral density (BMD) and bone strain index (BSI) at baseline and after a follow-up period of 3 years in average. At the end of the follow-up, 93 women developed a further vertebral fracture. The further vertebral fracture was considered as one unit increase of SDI. We assessed the predictive capacity of supervised Artificial Neural Networks (ANNs) to distinguish women who developed a further fracture from those without it, and to detect those variables providing the maximal amount of relevant information to discriminate the two groups. ANNs choose appropriate input data automatically (TWIST-system, Training With Input Selection and Testing). Moreover, we built a semantic connectivity map usingthe Auto Contractive Map to provide further insights about the convoluted connections between the osteoporotic variables under consideration and the two scenarios (further fracture vs no further fracture). RESULTS: TWIST system selected 5 out of 13 available variables: age, menopause age, BMI, FTot BMC, FTot BSI. With training testing procedure, ANNs reached predictive accuracy of 79.36%, with a sensitivity of 75% and a specificity of 83.72%. The semantic connectivity map highlighted the role of BSI in predicting the risk of a further fracture. CONCLUSIONS: Artificial Intelligence is a useful method to analyse a complex system like that regarding osteoporosis, able to identify patients prone to a further fragility fracture. BSI appears to be a useful DXA index in identifying those patients who are at risk of further vertebral fractures.

Usefulness of Dual X-ray Absorptiometry-Derived Bone Geometry and Structural Indexes in Mastocytosis.

Reduced bone mass with or without fragility fractures is a common feature of mastocytosis, particularly in adult males. However, bone mineral density does not account for all the fragility fractures, being a part of them attributable to impairment in bone quality. Aim of this study is to assess the usefulness of DXA-derived geometry and structural indexes in the assessment of bone status in mastocytosis. Ninety-six consecutive patients (46 women and 50 men) affected by cutaneous (CM) or systemic (SM) mastocytosis were studied. Mean age (± SD) was 53.3 ± 14.23. Spine lateral X-rays for Genant's scale, DXA for lumbar (L) and femoral (F) bone mineral density (BMD), bone strain index (BSI), lumbar trabecular bone score (TBS), and hip structural analysis (HSA) were performed. Among the laboratory variables, data of serum tryptase were reported. Tryptase was higher in SM (p = 0.035), inversely correlated with LBMD (r = - 0.232; p = 0.022) and TBS (r = - 0.280; p = 0.005), and directly with L-BSI (r = 0.276; p = 0.006). L-BSI remained statistically significant (p = 0.006; adjusted R2 = 0.101) together with mastocytosis (SM or CM: p = 0.034) in the multivariate regression model with tryptase as dependent variable, being LBMD and TBS not statistically significant (p = 0.887, and p = 0.245, respectively). Tryptase increased about 22 units for each unit increase of L-BSI and about 18 units for SM against CM. L-BSI was lower (p = 0.012), while FN-BSI and FT-BSI were higher in women (p < 0.001) than in men. HSA indexes were significantly higher in men, particularly with SM. SM is a risk factor for reduced bone mass, texture and strength. Since mean L-BSI and Z-modulus of all the femoral sites are statistically higher in men than in female, it could be argued that men have a better femoral bone resistance to bending forces than women, but a worse lumbar bone resistance to compressive loads. DXA indexes of bone quality are useful in mastocytosis' bone assessment and its clinical management.

Bone strain index in the prediction of vertebral fragility refracture.

Dual-energy x-ray absorptiometry (DXA) can provide quantitative (bone mineral density, BMD) and qualitative (trabecular bone score, TBS) indexes of bone status, able to predict fragility fractures in most osteoporotic patients. A new qualitative index of bone strength, based on finite element analysis and named bone strain index (BSI), has been recently developed from lumbar DXA scan. We present the preliminary results about the BSI ability to predict a refracture in patients with fragility fractures. A total of 143 consecutive fractured patients with primary osteoporosis (121 females) performed a spine x-ray examination for the calculation of spine deformity index (SDI) and a DXA densitometry for BMD, TBS, and BSI at basal time and in the follow-up. A refracture was considered as a one-unit increase in SDI. For each unit increase of the investigated indexes, the hazard ratio of refracture, 95% confidence interval, p value, and proportionality test p value were for BSI 1.201, 0.982-1.468, 0.074, and 0.218; for lumbar BMD 0.231, 0.028-1.877, 0.170, and 0.305; and for TBS 0.034, 0.001-2.579, 0.126, and 0.518, respectively. BSI was the index predictive of refracture nearest to statistical significance. If confirmed, it may be used for a better risk assessment of osteoporotic patients.

Artificial neural network analysis of bone quality DXA parameters response to teriparatide in fractured osteoporotic patients.

Teriparatide is a bone-forming therapy for osteoporosis that increases bone quantity and texture, with uncertain action on bone geometry. No data are available regarding its influence on bone strain. To investigate teriparatide action on parameters of bone quantity and quality and on Bone Strain Index (BSI), also derived from DXA lumbar scan, based on the mathematical model finite element method. Forty osteoporotic patients with fractures were studied before and after two years of daily subcutaneous 20 mcg of teriparatide with dual X-ray photon absorptiometry to assess bone mineral density (BMD), hip structural analysis (HSA), trabecular bone score (TBS), BSI. Spine deformity index (SDI) was calculated from spine X-ray. Shapiro-Wilks, Wilcoxon and Student's t test were used for classical statistical analysis. Auto Contractive Map was used for Artificial Neural Network Analysis (ANNs). In the entire population, the ameliorations after therapy regarded BSI (-13.9%), TBS (5.08%), BMD (8.36%). HSA parameters of femoral shaft showed a worsening. Dividing patients into responders (BMD increase >10%) and non-responders, the first presented TBS and BSI ameliorations (11.87% and -25.46%, respectively). Non-responders presented an amelioration of BSI only, but less than in the other subgroup (-6.57%). ANNs maps reflect the mentioned bone quality improvements. Teriparatide appears to ameliorate not only BMD and TBS, but also BSI, suggesting an increase of bone strength that may explain the known reduction in fracture risk, not simply justified by BMD increase. BSI appears to be a sensitive index of TPD effect. ANNs appears to be a valid tool to investigate complex clinical systems.

Reproducibility of DXA-based bone strain index and the influence of body mass: an in vivo study.

OBJECTIVES: Bone strain index (BSI) is a dual-energy X-ray absorptiometry (DXA)-derived index of bone strength obtained from lumbar densitometric scan. We estimated the reproducibility of BSI in healthy women with different body mass index. METHODS: We enrolled postmenopausal women (mean age ± SD: 66 ± 10 years) divided into three groups (A, B and C) according to body mass index (BMI: < 25; 25-29.9; ≥ 30 kg/m2) and two groups (D and E) according to waist circumference (WC: ≤ 88; > 88 cm), each of 30 subjects. They underwent two DXA examinations with in-between repositioning, according to the International Society for Clinical Densitometry guidelines for precision estimation. Bone mineral density (BMD) and BSI were expressed as g/cm2 and absolute value, respectively. The coefficient of variation (CoV) was calculated as the ratio between root-mean-square standard deviation and mean; least significant change percentage (LSC%) as 2.77 × CoV; reproducibility as the complement to 100% LSC. RESULTS: BSI increased proportionally to BMI and WC and significantly in group C compared to B and A (p = 0.032 and 0.006, respectively). BSI was significantly higher in E compared to D (p = 0.017), whereas no differences were observed in BMD. Although BSI reproducibility was slightly lower in group C (89%), the differences were not significant between all groups. BMD reproducibility did not significantly differ between all groups. CONCLUSIONS: BSI reproducibility was significantly lower than that of BMD and decreased proportionally to BMI and WC increase. This reduction of BSI reproducibility was more pronounced in patients with BMI ≥ 30 and WC > 88, as expected, being BSI a parameter sensible to weight.

Usefulness of bone microarchitectural and geometric DXA-derived parameters in haemophilic patients.

INTRODUCTION: Haemophilia is a recessive X-linked inherited bleeding disorder, whose typical symptom is spontaneous intra-articular haemorrhage leading to joint damage, which can be quantified by the Haemophilia Joint Health Score (HJHS). Arthropathy and other characteristics of haemophilic patients may reduce bone mineral density (BMD), increasing the risk for fragility fractures, which also may occur due to bone quality impairment. AIM: To evaluate bone quantity by BMD and bone quality by Trabecular Bone Score (TBS), bone strain (BS) and hip structural analysis (HSA) in a haemophilic population, and to relate these parameters to general and specific risk factors for osteoporosis and to HJHS. METHODS: Seventy haemophilic patients ≥18 years were enrolled. Densitometric derived lumbar spine and femoral BMD with TBS, BS and HSA were performed. Data regarding risk factors for osteoporosis, presence of arthroprosthesis or arthrodesis were collected, and HJHS was calculated. A Z-score ≤-2.0 defined a low bone mass. RESULTS: Overall, a reduced bone mass was present in 52 patients at the femur and in 38 at the lumbar spine. Lumbar spine BMD, TBS and BS did not correlate with HJHS. HSA bone geometric parameters correlated negatively with HJHS. BMD and HSA correlated with some risk factors for osteoporosis, namely HIV and its therapy, hepatitis C and smoking. CONCLUSIONS: Haemophilic patients showed a reduced BMD at lumbar spine and/or femur. Femoral bone density and geometry correlated with HJHS. The microarchitecture of the trabecular vertebral bone seemed to be not influenced by the haemophilic joint damage.

Pediatric dual-energy X-ray absorptiometry in clinical practice: What the clinicians need to know.

The importance of childhood and adolescence for bone development and mineral accrual is increasingly accepted, leading to a need of suitable methods for monitoring bone health even in pediatric setting. Among the several different imaging methods available for clinical measurement of bone mineral density (BMD) in children, dual-energy X-ray absorptiometry (DXA) is the most widely available and commonly used due to its reproducibility, negligible radiation dose and reliable pediatric reference data. Nevertheless, DXA in children has some technical specific features that should be known by those physicians who interpret and report this examination. We provide recommendations for optimal DXA scan reporting in pediatric setting, including indications, skeletal sites to be examined, parameters to be measured, timing of follow-up BMD measurements. Adequate report and analysis of DXA examinations are essential to prevent over- and underdiagnosis of bone mineral impairment in pediatric patients. In conclusion, a complete and exhaustive DXA report in children and adolescents is mandatory for an accurate diagnosis and a precise monitoring of pediatric bone status.

Increasing soft tissue thickness does not affect trabecular bone score reproducibility: a phantom study.

PURPOSE: Trabecular Bone Score (TBS) provides an indirect score of trabecular microarchitecture from lumbar spine (LS) dual energy X-ray absorptiometry. Increasing soft tissue thickness artifactually reduces TBS values; we evaluated the effect of a fictitious increase of soft tissue thickness on TBS and bone mineral density (BMD) reproducibility on a phantom model. METHODS: A Hologic spine phantom was scanned with a QDR-Discovery W Hologic densitometer. Fresh pork rind layers of 5 mm were used to simulate the in-vivo soft tissues. For each scan mode (fast array [FA], array, high definition [HD]), 25 scans were consecutively performed without phantom repositioning, at 0 (no layers), 1 cm, 3 cm, and 6 cm of thickness. BMD and TBS reproducibility was calculated as the complement to 100% of least significant change. RESULTS: Both BMD and TBS reproducibility slightly decreased with increasing soft tissue; this difference was statistically significant only for BMD using HD modality (reproducibility decreased from 99.4% at baseline to 98.4% at 6-cm of thickness). TBS reproducibility was slightly lower compared to that of BMD, and ranged between 98.8% (array, 0 cm) and 97.4% (FA, 6 cm). Without taking into account manufacturer BMI optimization, we found a progressive decrease of TBS mean values with increasing soft tissue thickness. The highest TBS difference between baseline scan and 6 cm was -0.179 (-14.27%) using HD. CONCLUSIONS: Despite being slightly lower than that of BMD, TBS reproducibility was not affected up to 6 cm of increasing soft tissue thickness, and was even less influenced by fat than BMD reproducibility.

Managing osteoporosis in ulcerative colitis: something new?

The authors revise the latest evidence in the literature regarding managing of osteoporosis in ulcerative colitis (UC), paying particular attention to the latest tendency of the research concerning the management of bone damage in the patient affected by UC. It is wise to assess vitamin D status in ulcerative colitis patients to recognize who is predisposed to low levels of vitamin D, whose deficiency has to be treated with oral or parenteral vitamin D supplementation. An adequate dietary calcium intake or supplementation and physical activity, if possible, should be guaranteed. Osteoporotic risk factors, such as smoking and excessive alcohol intake, must be avoided. Steroid has to be prescribed at the lowest possible dosage and for the shortest possible time. Moreover, conditions favoring falling have to been minimized, like carpets, low illumination, sedatives assumption, vitamin D deficiency. It is advisable to assess the fracture risk in all UC patient by the fracture assessment risk tool (FRAX(®) tool), that calculates the ten years risk of fracture for the population aged from 40 to 90 years in many countries of the world. A high risk value could indicate the necessity of treatment, whereas a low risk value suggests a follow-up only. An intermediate risk supports the decision to prescribe bone mineral density (BMD) assessment and a subsequent patient revaluation for treatment. Dual energy X-ray absorptiometry bone densitometry can be used not only for BMD measurement, but also to collect data about bone quality by the means of trabecular bone score and hip structural analysis assessment. These two indices could represent a method of interesting perspectives in evaluating bone status in patients affected by diseases like UC, which may present an impairment of bone quality as well as of bone quantity. In literature there is no strong evidence for instituting pharmacological therapy of bone impairment in UC patients for clinical indications other than those that are also applied to the patients with osteoporosis. Therefore, a reasonable advice is to consider pharmacological treatment for osteoporosis in those UC patients who already present fragility fractures, which bring a high risk of subsequent fractures. Therapy has also to be considered in patients with a high risk of fracture even if it did not yet happen, and particularly when they had long periods of corticosteroid therapy or cumulative high dosages. In patients without fragility fractures or steroid treatment, a medical decision about treatment could be guided by the FRAX tool to determine the intervention threshold. Among drugs for osteoporosis treatment, the bisphosphonates are the most studied ones, with the best and longest evidence of efficacy and safety. Despite this, several questions are still open, such as the duration of treatment, the necessity to discontinue it, the indication of therapy in young patients, particularly in those without previous fractures. Further, it has to be mentioned that a long-term bisphosphonates use in primary osteoporosis has been associated with an increased incidence of dramatic side-effects, even if uncommon, like osteonecrosis of the jaw and atypical sub-trochanteric and diaphyseal femoral fractures. UC is a long-lasting disease and the majority of patients is relatively young. In this scenario primary prevention of fragility fracture is the best cost-effective strategy. Vitamin D supplementation, adequate calcium intake, suitable physical activity (when possible), removing of risk factors for osteoporosis like smoking, and avoiding falling are the best medical acts.

Dose absorption in lumbar and femoral dual energy X-ray absorptiometry examinations using three different scan modalities: an anthropomorphic phantom study.

The aim of this study was to measure the effective dose on an anthropomorphic phantom undergoing lumbar and femoral dual energy X-ray absorption (DXA) examinations, using 3 different scan modalities (fast-array [FA], array [A], high-definition [HD]), and assess the differences in the lifetime attributable risk (LAR) of cancer due to radiation. An anthropomorphic phantom was used. Thermoluminescent dosimeters were placed over 12 anatomic phantom regions and outside the room (to measure background radiation). Fifty scans on the femur and spine were performed for each mode. The dose relative to a single DXA scan for each dosimeter was measured (mean over the 50 scans) and the background radiation was then subtracted. The equivalent dose per organ was obtained. The total body effective dose was calculated by adding the equivalent doses. We estimated the lifetime dose absorption and LAR for cancer for a male and a female patient undergoing 36 DXA studies (18 lumbar, 18 femoral) every 21 months for 32 years. The effective dose for lumbar scans was FA = 17.79 µSv, A = 32.88 µSv, HD = 31.08 µSv; for femoral scans, FA = 5.29 µSv, A = 9.55 µSv, HD = 7.54 µSv. LAR estimation showed a minimal increase in cancer risk (range 4.55 × 10⁻4% [FA, femoral, male] to 4.02 × 10⁻³% [A, lumbar, female]). The lifetime dose absorption and LAR for cancer for a male and a female patient undergoing 36 DXA studies (18 lumbar, 18 femoral) every 21 months for 32 years were 0.756 mSv, 3.82 × 10(-3)% and 0.756 mSv, 5.11 × 10⁻³%, respectively. DXA examinations cause radiation levels that are comparable to the background radiation. Regardless of the scan modality or the anatomic site, a patient undergoing DXA scans for a lifetime has a negligible increased risk of developing cancer.