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.

DXA-Based Bone Strain Index: A New Tool to Evaluate Bone Quality in Primary Hyperparathyroidism

Context Primary hyperparathyroidism (PHPT) is associated with impaired bone quality and increased fracture risk. Reliable tools for the evaluation of bone quality parameters are not yet clinically available. Bone Strain Index (BSI) is a new metric for bone strength based on Finite Element Analysis from lumbar spine and femoral neck dual X-ray absorptiometry images. Objective To assess the lumbar spine (LS), femoral neck (FN), and total hip (TH) BSI in PHPT compared to controls and to investigate the association of BSI with vertebral fractures (VFs) in PHPT. Design case-control study Setting Outpatient clinic Patients 50 PHPT and 100 age- and sex-matched control subjects. Main Outcome Measures LS-BSI, FN-BSI, TH-BSI. Results FN bone mineral density (BMD) and 1/3 distal radius BMD were lower in the PHPT group than in controls (FN 0.633 ± 0.112 vs 0.666 ± 0.081 p= 0.042; radius 0.566 ± 0.07 vs 0.625 ± 0.06 p<0.001). PHPT group has significant lower TBS score compared to controls (1.24 ± 0.09 vs 1.30 ± 0.10 p <0.001).BSI was significantly higher at LS (2.28±0.59 vs 2.02±0.43, p=0.009), FN (1.72±0.41 vs 1.49±0.35, p=0.001) and TH (1.51±0.33 vs 1.36±0.25, p=0.002) in PHPT. LS-BSI showed moderate accuracy for discriminating VFs (AUC 0.667; 95% CI 0.513-0.820). LS-BSI ≥ 2.2 and was a statistically significant independent predictor of VFs, with an adjusted OR ranging from 5.7 to 15.1. Conclusion BSI, a DXA-derived bone quality index, is impaired in PHPT and may help to identify PHPT subjects at high risk of fractures.

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.

Comparative cranial biomechanics in two lizard species: impact of variation in cranial design

Cranial morphology in lepidosaurs is highly disparate and characterized by the frequent loss or reduction of bony elements. In varanids and geckos, the loss of the postorbital bar is associated with changes in skull shape, but the mechanical principles underlying this variation remain poorly understood. Here, we seek to determine how the overall cranial architecture and the presence of the postorbital bar relate to the loading and deformation of the cranial bones during biting in lepidosaurs. Using computer-based simulation techniques, we compare cranial biomechanics in the varanid Varanus niloticus and the teiid Salvator merianae, two large, active foragers. The overall strain magnitudes and distribution across the cranium is similar in both species, despite lower strain gradients in Varanus niloticus. In Salvator merianae, the postorbital bar is important for the resistance of the cranium to feeding loads. The postorbital ligament, which partially replaces the postorbital bar in varanids, does not affect bone strain. Our results suggest that the reduction of the postorbital bar impaired neither biting performance nor the structural resistance of the cranium to feeding loads in Varanus niloticus. Differences in bone strain between the two species might reflect demands imposed by feeding and non-feeding functions on cranial shape. Beyond variation in cranial bone strain related to species-specific morphological differences, our results reveal that similar mechanical behaviour is shared by lizards with distinct cranial shapes. Contrary to mammals, the morphology of the circumorbital region, calvaria and palate appears to be important for withstanding high feeding loads in these lizards.

Beyond Bone Mineral Density: A New Dual X-Ray Absorptiometry Index of Bone Strength to Predict Fragility Fractures, the Bone Strain Index

For a proper assessment of osteoporotic fragility fracture prediction, all aspects regarding bone mineral density, bone texture, geometry and information about strength are necessary, particularly in endocrinological and rheumatological diseases, where bone quality impairment is relevant. Data regarding bone quantity (density) and, partially, bone quality (structure and geometry) are obtained by the gold standard method of dual X-ray absorptiometry (DXA). Data about bone strength are not yet readily available. To evaluate bone resistance to strain, a new DXA-derived index based on the Finite Element Analysis (FEA) of a greyscale of density distribution measured on spine and femoral scan, namely Bone Strain Index (BSI), has recently been developed. Bone Strain Index includes local information on density distribution, bone geometry and loadings and it differs from bone mineral density (BMD) and other variables of bone quality like trabecular bone score (TBS), which are all based on the quantification of bone mass and distribution averaged over the scanned region. This state of the art review illustrates the methodology of BSI calculation, the findings of its in reproducibility and the preliminary data about its capability to predict fragility fracture and to monitor the follow up of the pharmacological treatment for osteoporosis.