New Insights in the Pathophysiology, Epidemiology, and Response to Treatment of Osteoporotic Vertebral Fractures

Constructing a Deep Learning Radiomics Model Based on X-ray Images and Clinical Data for Predicting and Distinguishing Acute and Chronic Osteoporotic Vertebral Fractures: A Multicenter Study

RATIONALE AND OBJECTIVES

To construct and validate a deep learning radiomics (DLR) model based on X-ray images for predicting and distinguishing acute and chronic osteoporotic vertebral fractures (OVFs).

METHODS

A total of 942 cases (1076 vertebral bodies) with both vertebral X-ray examination and MRI scans were included in this study from three hospitals. They were divided into a training cohort (n = 712), an internal validation cohort (n = 178), an external validation cohort (n = 111), and a prospective validation cohort (n = 75). The ResNet-50 model architecture was used for deep transfer learning (DTL), with pre-training performed on RadImageNet and ImageNet datasets. DTL features and radiomics features were extracted from lateral X-ray images of OVFs patients and fused together. A logistic regression model with the least absolute shrinkage and selection operator was established, with MRI showing bone marrow edema as the gold standard for acute OVFs. The performance of the model was evaluated using receiver operating characteristic curves. Eight machine learning classification models were evaluated for their ability to distinguish between acute and chronic OVFs. The Nomogram was constructed by combining clinical baseline data to achieve visualized classification assessment. The predictive performance of the best RadImageNet model and ImageNet model was compared using the Delong test. The clinical value of the Nomogram was evaluated using decision curve analysis (DCA).

RESULTS

Pre-training resulted in 34 and 39 fused features after feature selection and fusion. The most effective machine learning algorithm in both DLR models was Light Gradient Boosting Machine. Using the Delong test, the area under the curve (AUC) for distinguishing between acute and chronic OVFs in the training cohort was 0.979 and 0.972 for the RadImageNet and ImageNet models, respectively, with no statistically significant difference between them (P = 0.235). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.629, 0.886 vs 0.817, and 0.933 vs 0.661, respectively, with statistically significant differences in all comparisons (P < 0.05). The deep learning radiomics nomogram (DLRN) was constructed by combining the predictive model of RadImageNet with clinical baseline features, resulting in AUCs of 0.981, 0.974, 0.895, and 0.902 in the training cohort, internal validation cohort, external validation cohort, and prospective validation cohort, respectively. Using the Delong test, the AUCs for the fused feature model and the DLRN in the training cohort were 0.979 and 0.981, respectively, with no statistically significant difference between them (P = 0.169). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.974, 0.886 vs 0.895, and 0.933 vs 0.902, respectively, with statistically significant differences in all comparisons (P < 0.05). The Nomogram showed a slight improvement in predictive performance in the internal and external validation cohort, but a slight decrease in the prospective validation cohort (0.933 vs 0.902). DCA showed that the Nomogram provided more benefits to patients compared to the DLR models.

CONCLUSION

Compared to the ImageNet model, the RadImageNet model has higher diagnostic value in distinguishing between acute and chronic OVFs. Furthermore, the diagnostic performance of the model is further improved when combined with clinical baseline features to construct the Nomogram.

Advances in exosome modulation of ferroptosis for the treatment of orthopedic diseases

Current treatments for orthopaedic illnesses frequently result in poor prognosis, treatment failure, numerous relapses, and other unpleasant outcomes that have a significant impact on patients' quality of life. Cell-free therapy has emerged as one of the most promising options in recent decades for improving the status quo. As a result, using exosomes produced from various cells to modulate ferroptosis has been proposed as a therapeutic method for the condition. Exosomes are extracellular vesicles that secrete various bioactive chemicals that influence disease treatment and play a role in the genesis and progression of orthopaedic illnesses. Ferroptosis is a recently defined kind of controlled cell death typified by large iron ion buildup and lipid peroxidation. An increasing number of studies indicate that ferroptosis plays a significant role in orthopaedic illnesses. Exosomes, as intercellular information transfer channels, have been found to play a significant role in the regulation of ferroptosis processes. Furthermore, accumulating research suggests that exosomes can influence the course of many diseases by regulating ferroptosis in injured cells. In order to better understand the processes by which exosomes govern ferroptosis in the therapy of orthopaedic illnesses. This review discusses the biogenesis, secretion, and uptake of exosomes, as well as the mechanisms of ferroptosis and exosomes in the therapy of orthopaedic illnesses. It focuses on recent research advances and exosome mechanisms in regulating iron death for the therapy of orthopaedic illnesses. The present state of review conducted both domestically and internationally is elucidated and anticipated as a viable avenue for future therapy in the field of orthopaedics.

Exploring deep learning radiomics for classifying osteoporotic vertebral fractures in X-ray images

Purpose

To develop and validate a deep learning radiomics (DLR) model that uses X-ray images to predict the classification of osteoporotic vertebral fractures (OVFs).

Material and methods

The study encompassed a cohort of 942 patients, involving examinations of 1076 vertebrae through X-ray, CT, and MRI across three distinct hospitals. The OVFs were categorized as class 0, 1, or 2 based on the Assessment System of Thoracolumbar Osteoporotic Fracture. The dataset was divided randomly into four distinct subsets: a training set comprising 712 samples, an internal validation set with 178 samples, an external validation set containing 111 samples, and a prospective validation set consisting of 75 samples. The ResNet-50 architectural model was used to implement deep transfer learning (DTL), undergoing -pre-training separately on the RadImageNet and ImageNet datasets. Features from DTL and radiomics were extracted and integrated using X-ray images. The optimal fusion feature model was identified through least absolute shrinkage and selection operator logistic regression. Evaluation of the predictive capabilities for OVFs classification involved eight machine learning models, assessed through receiver operating characteristic curves employing the "One-vs-Rest" strategy. The Delong test was applied to compare the predictive performance of the superior RadImageNet model against the ImageNet model.

Results

Following pre-training separately on RadImageNet and ImageNet datasets, feature selection and fusion yielded 17 and 12 fusion features, respectively. Logistic regression emerged as the optimal machine learning algorithm for both DLR models. Across the training set, internal validation set, external validation set, and prospective validation set, the macro-average Area Under the Curve (AUC) based on the RadImageNet dataset surpassed those based on the ImageNet dataset, with statistically significant differences observed (P<0.05). Utilizing the binary "One-vs-Rest" strategy, the model based on the RadImageNet dataset demonstrated superior efficacy in predicting Class 0, achieving an AUC of 0.969 and accuracy of 0.863. Predicting Class 1 yielded an AUC of 0.945 and accuracy of 0.875, while for Class 2, the AUC and accuracy were 0.809 and 0.692, respectively.

Conclusion

The DLR model, based on the RadImageNet dataset, outperformed the ImageNet model in predicting the classification of OVFs, with generalizability confirmed in the prospective validation set.

The Influence of Hyponatremia and Hypokalemia on the Risk of Fractures in Various Anatomical Regions among Adult Trauma Patients: A Propensity Score-Matched Analysis

BACKGROUND

Hyponatremia and hypokalemia are common electrolyte imbalances in trauma patients and have been identified to be risk factors for a fall. In addition, hyponatremia was reported to be related to osteoporosis and fragility fractures, while the association between hypokalemia and osteoporosis has only been reported in rare case reports. This study investigated the impact of hyponatremia and hypokalemia on the incidence of fractures in various body regions of adult trauma patients, using the propensity score-matched patient cohort to reduce the influence of patients' baseline characteristics.

METHODS

The study analyzed data from 11,173 hospitalized adult trauma patients treated from 1 January 1998, to 31 December 2022. The study included 1968 patients with hyponatremia and 9205 without, and 1986 with hypokalemia and 9187 without. Different 1:1 propensity score-matched cohorts were generated to create the 1903 pairings of patients with or without hyponatremia, 1977 pairings of patients with or without hypokalemia, and 380 pairing of patients with both hyponatremia and hypokalemia vs. normal control patients. Analysis was conducted on the incidence of fracture in various anatomic regions.

RESULTS

Hyponatremic patients had increased odds of thoracic vertebral fracture [odds ratio (95% confidence interval) 1.63 (1.10-2.42), p = 0.014], pelvic fracture [2.29 (1.12-4.67), p = 0.019], and femoral fracture [1.28 (1.13-1.45), p < 0.001] but decreased odds of radial and patella fractures. Hypokalemic patients showed no significant differences in fracture risk except for a decreased likelihood of radial fractures. The patients with both hyponatremia and hypokalemia showed a decreased likelihood of radial fractures and patella fractures.

CONCLUSION

Hyponatremia may have a greater impact on the occurrence of bone fractures than hypokalemia in trauma patients who have suffered a fall. Electrolyte abnormalities should be taken into account while assessing the risk of fractures in trauma patients.

Osteoporosis and major fragility fractures (MOF) in sarcoidosis patients: association with disease severity

BACKGROUND

The reports on bone mineral loss or major osteoporosis fracture (MOF) in sarcoidosis are scarce and have conflicting outcomes. This study aimed to evaluate the prevalence and risk factors of MOF in sarcoidosis patients.

METHODS

In a single-center cohort of 382 patients with sarcoidosis (55.8 ± 11.6 years) we evaluated bone mineral density at lumbar spine, at femoral neck and at total hip and the presence of MOF. Lung function measurements including diffusion capacity for carbon monoxide (DLCO) were assessed. Chest X-rays were performed and radiological staging was done by Scadding score.

RESULTS

Ninety patients (23.6%) with sarcoidosis have history of a MOF. BMD T-scores were lower in sarcoidosis with MOF with respect to those without MOF, but the difference was statistically significant only for BMD at femoral neck (p < 0.05). Moreover, BMD values at total hip was positively correlated with DLCO (%) (p < 0.001). Prevalence of MOF was higher in patients with sarcoidosis with lung parenchymal involvement (radiological stages 2-4) than in patients with sarcoidosis in chest X-ray stages 0 and 1 (28.3 vs 19.2% respectively, p < 0.05). Moreover, multiple regression analyses showed that X-ray Scadding score was positively associated with MOF.

CONCLUSIONS

This study shows that MOF represent a common and important complication in patients with moderate/severe sarcoidosis. The chest X-ray evaluation and the pulmonary function test could allow to define the risk of MOF in sarcoidosis patients.