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

Development and reporting of artificial intelligence in osteoporosis management

An abundance of medical data and enhanced computational power have led to a surge in artificial intelligence (AI) applications. Published studies involving AI in bone and osteoporosis research have increased exponentially, raising the need for transparent model development and reporting strategies. This review offers a comprehensive overview and systematic quality assessment of AI articles in osteoporosis while highlighting recent advancements. A systematic search in the PubMed database, from December 17, 2020 to February 1, 2023 was conducted to identify AI articles that relate to osteoporosis. The quality assessment of the studies relied on the systematic evaluation of 12 quality items derived from the minimum information about clinical artificial intelligence modeling checklist. The systematic search yielded 97 articles that fell into 5 areas; bone properties assessment (11 articles), osteoporosis classification (26 articles), fracture detection/classification (25 articles), risk prediction (24 articles), and bone segmentation (11 articles). The average quality score for each study area was 8.9 (range: 7-11) for bone properties assessment, 7.8 (range: 5-11) for osteoporosis classification, 8.4 (range: 7-11) for fracture detection, 7.6 (range: 4-11) for risk prediction, and 9.0 (range: 6-11) for bone segmentation. A sixth area, AI-driven clinical decision support, identified the studies from the 5 preceding areas that aimed to improve clinician efficiency, diagnostic accuracy, and patient outcomes through AI-driven models and opportunistic screening by automating or assisting with specific clinical tasks in complex scenarios. The current work highlights disparities in study quality and a lack of standardized reporting practices. Despite these limitations, a wide range of models and examination strategies have shown promising outcomes to aid in the earlier diagnosis and improve clinical decision-making. Through careful consideration of sources of bias in model performance assessment, the field can build confidence in AI-based approaches, ultimately leading to improved clinical workflows and patient outcomes.

Machine learning value in the diagnosis of vertebral fractures: A systematic review and meta-analysis

PURPOSE

To evaluate the diagnostic accuracy of machine learning (ML) in detecting vertebral fractures, considering varying fracture classifications, patient populations, and imaging approaches.

METHOD

A systematic review and meta-analysis were conducted by searching PubMed, Embase, Cochrane Library, and Web of Science up to December 31, 2023, for studies using ML for vertebral fracture diagnosis. Bias risk was assessed using QUADAS-2. A bivariate mixed-effects model was used for the meta-analysis. Meta-analyses were performed according to five task types (vertebral fractures, osteoporotic vertebral fractures, differentiation of benign and malignant vertebral fractures, differentiation of acute and chronic vertebral fractures, and prediction of vertebral fractures). Subgroup analyses were conducted by different ML models (including ML and DL) and modeling methods (including CT, X-ray, MRI, and clinical features).

RESULTS

Eighty-one studies were included. ML demonstrated a diagnostic sensitivity of 0.91 and specificity of 0.95 for vertebral fractures. Subgroup analysis showed that DL (SROC 0.98) and CT (SROC 0.98) performed best overall. For osteoporotic fractures, ML showed a sensitivity of 0.93 and specificity of 0.96, with DL (SROC 0.99) and X-ray (SROC 0.99) performing better. For differentiating benign from malignant fractures, ML achieved a sensitivity of 0.92 and specificity of 0.93, with DL (SROC 0.96) and MRI (SROC 0.97) performing best. For differentiating acute from chronic vertebral fractures, ML showed a sensitivity of 0.92 and specificity of 0.93, with ML (SROC 0.96) and CT (SROC 0.97) performing best. For predicting vertebral fractures, ML had a sensitivity of 0.76 and specificity of 0.87, with ML (SROC 0.80) and clinical features (SROC 0.86) performing better.

CONCLUSIONS

ML, especially DL models applied to CT, MRI, and X-ray, shows high diagnostic accuracy for vertebral fractures. ML also effectively predicts osteoporotic vertebral fractures, aiding in tailored prevention strategies. Further research and validation are required to confirm ML's clinical efficacy.

DXA-derived lumbar bone strain index corrected for kyphosis is associated with vertebral fractures and trabecular bone score in acromegaly

PURPOSE

The bone strain index (BSI) is a marker of bone deformation based on a finite element analysis inferred from dual X-ray absorptiometry (DXA) scans, that has been proposed as a predictor of fractures in osteoporosis (i.e., higher BSI indicates a lower bone's resistance to loads with consequent higher risk of fractures). We aimed to investigate the association between lumbar BSI and vertebral fractures (VFs) in acromegaly.

METHODS

Twenty-three patients with acromegaly (13 males, mean age 58 years; three with active disease) were evaluated for morphometric VFs, trabecular bone score (TBS), bone mineral density (BMD) and BSI at lumbar spine, the latter being corrected for the kyphosis as measured by low-dose X-ray imaging system (EOS®-2D/3D).

RESULTS

Lumbar BSI was significantly higher in patients with VFs as compared to those without fractures (2.90 ± 1.46 vs. 1.78 ± 0.33, p = 0.041). BSI was inversely associated with TBS (rho -0.44; p = 0.034), without significant associations with BMD (p = 0.151), age (p = 0.500), BMI (p = 0.957), serum IGF-I (p = 0.889), duration of active disease (p = 0.434) and sex (p = 0.563).

CONCLUSIONS

Lumbar BSI corrected for kyphosis could be proposed as integrated parameter of spine arthropathy and osteopathy in acromegaly helping the clinicians in identifying patients with skeletal fragility possibly predisposed to VFs.

Long non-coding RNA MIAT serves as a biomarker of fragility fracture and promotes fracture healing

BACKGROUND

Fragility fracture is common in the elderly. Osteoblast differentiation is essential for bone healing and regeneration. Expression pattern of long non-coding RNA MIAT during fracture healing was examined, and its role in osteoblast differentiation was investigated.

METHODS

90 women with simple osteoporosis and 90 women with fragility fractures were included. Another 90 age-matched women were set as the control group. mRNA levels were tested using RT-qPCR. Cell viability was detected via CCK-8, and osteoblastic biomarkers, including ALP, OCN, Collagen I, and RUNX2 were tested via ELISA. The downstream miRNAs and genes targeted by MIAT were predicted by bioinformatics analysis, whose functions and pathways were annotated via GO and KEGG analysis.

RESULTS

Serum MIAT was upregulated in osteoporosis women with high accuracy of diagnostic efficacy. Serum MIAT was even elevated in the fragility fracture group, but decreased in a time manner after operation. MIAT knockdown promoted osteogenic proliferation and differentiation of MC3T3-E1, but the influences were reversed by miR-181a-5p inhibitor. A total of 137 overlapping target genes of miR-181a-5p were predicted based on the miRDB, TargetScan and microT datasets, which were mainly enriched for terms related to signaling pathways regulating pluripotency of stem cells, cellular senescence, and osteoclast differentiation.

CONCLUSIONS

LncRNA MIAT serves as a promising biomarker for osteoporosis, and promotes osteogenic differentiation via targeting miR-181a-5p.

Hypopituitarism and bone disease: pathophysiology, diagnosis and treatment outcomes

Hypopituitarism is a rare but significant endocrine disorder characterized by the inadequate secretion of one or more pituitary hormones. The intricate relationship between hypopituitarism and bone health is a topic of growing interest in the medical community. In this review the authors explore associations between hypopituitarism and bone health, with specific examination of the impact of growth hormone deficiency, central hypogonadism, central hypocortisolism, and central hypothyroidism. Pathogenesis, diagnosis, and treatment options as well as challenges posed by osteopenia, osteoporosis, and fractures in hypopituitarism are discussed.

New Horizons: Artificial Intelligence Tools for Managing Osteoporosis

Osteoporosis is a disease characterized by low bone mass and microarchitectural deterioration leading to increased bone fragility and fracture risk. Typically, osteoporotic fractures occur at the spine, hip, distal forearm, and proximal humerus, but other skeletal sites may be affected as well. One of the major challenges in the management of osteoporosis lies in the fact that although the operational diagnosis is based on bone mineral density (BMD) as measured by dual x-ray absorptiometry, the majority of fractures occur at nonosteoporotic BMD values. Furthermore, osteoporosis often remains undiagnosed regardless of the low severity of the underlying trauma. Also, there is only weak consensus among the major guidelines worldwide, when to treat, whom to treat, and which drug to use. Against this background, increasing efforts have been undertaken in the past few years by artificial intelligence (AI) developers to support and improve the management of this disease. The performance of many of these newly developed AI algorithms have been shown to be at least comparable to that of physician experts, or even superior. However, even if study results appear promising at a first glance, they should always be interpreted with caution. Use of inadequate reference standards or selection of variables that are of little or no value in clinical practice are limitations not infrequently found. Consequently, there is a clear need for high-quality clinical research in this field of AI. This could, eg, be achieved by establishing an internationally consented "best practice framework" that considers all relevant stakeholders.

Use of artificial neural networks in the prognosis of musculoskeletal diseases-a scoping review

To determine the current evidence on artificial neural network (ANN) in prognostic studies of musculoskeletal diseases (MSD) and to assess the accuracy of ANN in predicting the prognosis of patients with MSD. The scoping review was reported under the Preferred Items for Systematic Reviews and the Meta-Analyses extension for Scope Reviews (PRISMA-ScR). Cochrane Library, Embase, Pubmed, and Web of science core collection were searched from inception to January 2023. Studies were eligible if they used ANN to make predictions about MSD prognosis. Variables, model prediction accuracy, and disease type used in the ANN model were extracted and charted, then presented as a table along with narrative synthesis. Eighteen Studies were included in this scoping review, with 16 different types of musculoskeletal diseases. The accuracy of the ANN model predictions ranged from 0.542 to 0.947. ANN models were more accurate compared to traditional logistic regression models. This scoping review suggests that ANN can predict the prognosis of musculoskeletal diseases, which has the potential to be applied to different types of MSD.

Predicting the risk of osteoporosis in older Vietnamese women using machine learning approaches

Osteoporosis contributes significantly to health and economic burdens worldwide. However, the development of osteoporosis-related prediction tools has been limited for lower-middle-income countries, especially Vietnam. This study aims to develop prediction models for the Vietnamese population as well as evaluate the existing tools to forecast the risk of osteoporosis and evaluate the contribution of covariates that previous studies have determined to be risk factors for osteoporosis. The prediction models were developed to predict the risk of osteoporosis using machine learning algorithms. The performance of the included prediction models was evaluated based on two scenarios; in the first one, the original test parameters were directly modeled, and in the second the original test parameters were transformed into binary covariates. The area under the receiver operating characteristic curve, the Brier score, precision, recall and F1-score were calculated to evaluate the models' performance in both scenarios. The contribution of the covariates was estimated using the Permutation Feature Importance estimation. Four models, namely, Logistic Regression, Support Vector Machine, Random Forest and Neural Network, were developed through two scenarios. During the validation phase, these four models performed competitively against the reference models, with the areas under the curve above 0.81. Age, height and weight contributed the most to the risk of osteoporosis, while the correlation of the other covariates with the outcome was minor. Machine learning algorithms have a proven advantage in predicting the risk of osteoporosis among Vietnamese women over 50 years old. Additional research is required to more deeply evaluate the performance of the models on other high-risk populations.

Artificial neural networks reveal sex differences in gene methylation, and connections between maternal risk factors and symptom severity in autism spectrum disorder

Aim and methods: Artificial neural networks were used to unravel connections among blood gene methylation levels, sex, maternal risk factors and symptom severity evaluated using the Autism Diagnostic Observation Schedule 2 (ADOS-2) score in 58 children with autism spectrum disorder (ASD). Results: Methylation levels of MECP2, HTR1A and OXTR genes were connected to females, and those of EN2, BCL2 and RELN genes to males. High gestational weight gain, lack of folic acid supplements, advanced maternal age, preterm birth, low birthweight and living in rural context were the best predictors of a high ADOS-2 score. Conclusion: Artificial neural networks revealed links among ASD maternal risk factors, symptom severity, gene methylation levels and sex differences in methylation that warrant further investigation in ASD.

The Bone Strain Index: An Innovative Dual X-ray Absorptiometry Bone Strength Index and Its Helpfulness in Clinical Medicine

Bone strain Index (BSI) is an innovative index of bone strength that provides information about skeletal resistance to loads not considered by existing indexes (Bone Mineral Density, BMD. Trabecular Bone Score, TBS. Hip Structural Analysis, HSA. Hip Axis Length, HAL), and, thus, improves the predictability of fragility fractures in osteoporotic patients. This improved predictability of fracture facilitates the possibility of timely intervention with appropriate therapies to reduce the risk of fracture. The development of the index was the result of combining clinical, radiographical and construction-engineering skills. In fact, from a physical point of view, primary and secondary osteoporosis, leading to bone fracture, are determined by an impairment of the physical properties of bone strength: density, internal structure, deformation and fatigue. Dual X-ray absorptiometry (DXA) is the gold standard for assessing bone properties, and it allows measurement of the BMD, which is reduced mainly in primary osteoporosis, the structural texture TBS, which can be particularly degraded in secondary osteoporosis, and the bone geometry (HSA, HAL). The authors recently conceived and developed a new bone deformation index named Bone Strain Index (BSI) that assesses the resistance of bone to loads. If the skeletal structure is equated to engineering construction, these three indexes are all considered to determine the load resistance of the construct. In particular, BSI allows clinicians to detect critical information that BMD and TBS cannot explain, and this information is essential for an accurate definition of a patient’s fracture risk. The literature demonstrates that both lumbar and femoral BSI discriminate fractured osteoporotic people, that they predict the first fragility fracture, and further fragility fractures, monitor anabolic treatment efficacy and detect patients affected by secondary osteoporosis. BSI is a new diagnostic tool that offers a unique perspective to clinical medicine to identify patients affected by primary and, specially, secondary osteoporosis. This literature review illustrates BSI’s state of the art and its ratio in clinical medicine.

The bone strain index predicts fragility fractures. The OFELY study

Recently, the bone strain index (BSI), a new index of bone strength based on a finite element model (FEA) from dual X-ray absorptiometry (DXA), has been developed. BSI represents the average equivalent strain inside the bone, assuming that a higher strain level (high BSI) indicates a condition of higher risk. Our study aimed to analyze the relationship between BSI and age, BMI and areal BMD in pre- and postmenopausal women and to prospectively investigate fracture prediction (Fx) by BSI in postmenopausal women. Methods. At the 14th annual follow-up of the OFELY study, BSI was measured at spine (Spine BSI) and femoral scans (Neck and Total Hip BSI), in addition to areal BMD with DXA (Hologic QDR 4500) in 846 women, mean (SD) age 60 yr (15). The FRAX® (fracture risk assessment tool) for major osteoporotic fractures (MOF) was calculated with FN areal BMD (aBMD) at baseline; incident fragility fractures were annually registered until January 2016. Results. In premenopausal women (n = 261), Neck and Total Hip BSI were slightly negatively correlated with age (Spearman r = -0.13 and -0.15 respectively, p = 0.03), whereas all BSIs were positively correlated with BMI (r = +0.20 to 0.37, p < 0.01) and negatively with BMD (r = -0.69 to -0.37, p < 0.0001). In postmenopausal women (n = 585), Neck and Total Hip BSI were positively correlated with age (Spearman r = +0.26 and +0.31 respectively, p < 0.0001), whereas Spine BSI was positively correlated with BMI (r = +0.22, p < 0.0001) and all BSIs were negatively correlated with BMD (r = -0.81 to -0.60, p < 0.0001). During a median [IQ] 9.3 [1.0] years of follow-up, 133 postmenopausal women reported an incident fragility Fx, including 80 women with a major osteoporotic Fx (MOF) and 26 women with clinical vertebral Fx (VFx). Each SD increase of BSI value was associated with a significant increase of the risk of all fragility Fx with an age-adjusted HR of 1.23 for Neck BSI (p = 0.02); 1.27 for Total Hip BSI (p = 0.004) and 1.35 for Spine BSI (p < 0.0001). After adjustment for FRAX®, the association remained statistically significant for Total Hip BSI (HR 1.24, p = 0.02 for all fragility Fx; 1.31, p = 0.01 for MOF) and Spine BSI (HR 1.33, p < 0.0001 for all fragility Fx; 1.33, p = 0.005 for MOF; 1.67, p = 0.002 for clinical VFx). In conclusion, spine and femur BSI, an FEA DXA derived index, predict incident fragility fracture in postmenopausal women, regardless of FRAX®.

An Evolution Gaining Momentum—The Growing Role of Artificial Intelligence in the Diagnosis and Treatment of Spinal Diseases

In recent years, applications using artificial intelligence have been gaining importance in the diagnosis and treatment of spinal diseases. In our review, we describe the basic features of artificial intelligence which are currently applied in the field of spine diagnosis and treatment, and we provide an orientation of the recent technical developments and their applications. Furthermore, we point out the possible limitations and challenges in dealing with such technological advances. Despite the momentary limitations in practical application, artificial intelligence is gaining ground in the field of spine treatment. As an applying physician, it is therefore necessary to engage with it in order to benefit from those advances in the interest of the patient and to prevent these applications being misused by non-medical partners.