Development and validation of a predictive model for vertebral fracture risk in osteoporosis patients.

OBJECTIVE: This study aimed to develop and validate a predictive model for osteoporotic vertebral fractures (OVFs) risk by integrating demographic, bone mineral density (BMD), CT imaging, and deep learning radiomics features from CT images. METHODS: A total of 169 osteoporosis-diagnosed patients from three hospitals were randomly split into OVFs (n = 77) and Non-OVFs (n = 92) groups for training (n = 135) and test (n = 34). Demographic data, BMD, and CT imaging details were collected. Deep transfer learning (DTL) using ResNet-50 and radiomics features were fused, with the best model chosen via logistic regression. Cox proportional hazards models identified clinical factors. Three models were constructed: clinical, radiomics-DTL, and fusion (clinical-radiomics-DTL). Performance was assessed using AUC, C-index, Kaplan-Meier, and calibration curves. The best model was depicted as a nomogram, and clinical utility was evaluated using decision curve analysis (DCA). RESULTS: BMD, CT values of paravertebral muscles (PVM), and paravertebral muscles' cross-sectional area (CSA) significantly differed between OVFs and Non-OVFs groups (P < 0.05). No significant differences were found between training and test cohort. Multivariate Cox models identified BMD, CT values of PVM, and CSAPS reduction as independent OVFs risk factors (P < 0.05). The fusion model exhibited the highest predictive performance (C-index: 0.839 in training, 0.795 in test). DCA confirmed the nomogram's utility in OVFs risk prediction. CONCLUSION: This study presents a robust predictive model for OVFs risk, integrating BMD, CT data, and radiomics-DTL features, offering high sensitivity and specificity. The model's visualizations can inform OVFs prevention and treatment strategies.

Retrospective Cohort Study of Early versus Delayed Ballon Kyphoplasty Intervention for Osteoporotic Vertebral Fracture Treatment.

Objectives: To investigate the outcomes of early balloon kyphoplasty (BKP) intervention compared with late intervention for osteoporotic vertebral fracture (OVF). Background: Osteoporotic vertebral fracture can lead to kyphotic deformity, severe back pain, depression, and disturbances in activities of daily living (ADL). Balloon kyphoplasty has been widely utilized to treat symptomatic OVFs and has proven to be a very effective surgical option for this condition. Furthermore, BKP is relatively a safe and effective method due to its reduced acrylic cement leakage and greater kyphosis correction. Materials and Methods: A retrospective cohort study was conducted at our hospital for patients who underwent BKP for osteoporotic vertebral fractures in the time frame between January 2020 and December 2022. Ninety-nine patients were included in this study, and they were classified into two groups: in total, 36 patients underwent early BKP intervention (EI) at <4 weeks, and 63 patients underwent late BKP intervention (LI) at ≥4 weeks. We performed a clinical, radiological and statistical comparative evaluation for the both groups with a mean follow-up of one year. Results: Adjacent segmental fractures were more frequently observed in the LI group compared to the EI group (33.3% vs. 13.9%, p = 0.034). There was a significant improvement in postoperative vertebral angles in both groups (p = 0.036). The cement volume injected was 7.42 mL in the EI, compared with 6.3 mL in the LI (p = 0.007). The mean surgery time was shorter in the EI, at 30.2 min, compared with 37.1 min for the LI, presenting a significant difference (p = 0.0004). There was no statistical difference in the pain visual analog scale (VAS) between the two groups (p = 0.711), and there was no statistical difference in cement leakage (p = 0.192). Conclusions/Level of Evidence: Early BKP for OVF treatment may achieve better outcomes and fewer adjacent segmental fractures than delayed intervention.

Osteoporotic vertebral fractures: Natural history and impact. / Fracturas vertebrales osteoporóticas: historia natural e impacto.

Osteoporosis, and the consequences derived from it, such as fragility fractures, constitute a growing public health problem. Suffering from a fracture of this nature is the main risk factor for suffering a new fracture. It is documented that vertebral compression fractures lead to significant morbidity and mortality, in the short and long term, as well as other complications, such as sagittal imbalance and hyperkyphosis of the segment. However, we have not found documentation that analyzes the medium and long-term consequences of these injuries, assessing the type of treatment used, and the economic impact they represent. The purpose of this review is to analyze the main recent literature on the subject and make a breakdown of the consequences of these fractures in various spheres, such as economic, quality of life, sagittal balance and radiographic parameters, pain or mortality; as well as a brief analysis of epidemiology and natural history. CONCLUSION: Osteoporotic fractures constitute an emerging problem, both in the medical and economic fields. The consequences and sequelae on the patient are multiple and although surgical options offer good long-term results, it is necessary to properly select the patient, through multidisciplinary teams, to try to minimize potential complications.

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.

Posterolateral Instrumented Fusion in Elderly Patients With a Single Osteoporotic Vertebral Fracture: Evaluation of Health-Related Quality of Life.

Introduction Treatment of osteoporotic vertebral fractures (OVFs) is a factor that affects the quality of life and should be considered during management. In patients with a single OVF and neurologic deficit, surgical procedures aiming at neural decompression with instrumented fusion should be considered in elderly individuals. Posterolateral instrumented fusion (PLF) constitutes a largely performed fusion surgery for patients featuring indications for fusion surgery. The aim of this study was to determine the safety, effectiveness, and impact on health-related quality of life (HRQoL) of PLF surgery in elderly patients diagnosed with a single OVF. Methods This study was conducted at Interbalkan European Medical Center, Thessaloniki, Greece. Eighty (80) consecutive individuals with OVFs were subjected to PLF and recruited in this prospectively designed non-randomized study. Clinical evaluation was performed preoperatively and postoperatively at particular chronic intervals at one, three, six, and 12 months and two years. The assessment was conducted via the standardized Visual Analogue Scale (VAS) and Short-Form 36 (SF-36) Medical Health Survey Questionnaire for pain and HRQoL, respectively. Results No major perioperative complications were observed. All parameters of SF-36 presented significant improvement over the entire follow-up period with VAS scores reaching a plateau at six months. Depicted improvement of these parameters proves the beneficial role of PLF in elderly patients who suffered from a single OVF with or without referable neurological deficit. Conclusion OVFs have a significant impact on the quality of life of elderly patients, and surgical treatment with PLF with or without decompression can lead to functional recovery, pain relief, and HRQoL amelioration. Our results demonstrated that the outcomes of PLF in the surgical treatment of these patients are remarkably favorable, demonstrating the safety and efficacy of the technique.

Application of Piezosurgery in Revision Surgery through Posterior Approach for Infection after Percutaneous Vertebral Augmentation: Technique Note with Case Series.

OBJECTIVES: Pyogenic spondylitis after vertebral augmentation (PSVA) is a severe complication and even threatens the life of patients. How to deal with infectious bone cement is a big problem for surgeons. The application of piezosurgery has advantages in removal the infectious bone cement in limb bone and spinal laminectomy, but it is rarely used in PSVA. So, the present study aimed to introduce the application of piezosurgery in revision surgery for PSVA and report the preliminary radiological and clinical results. METHODS: The data of nine patients with PSVA who had undergone revision surgery were retrospectively reviewed between May 2017 and January 2023 in our hospital. The technique of removal of infectious bone cement and lesion by piezosurgery and the reconstruction of the spinal stability were described, and the operation time and intraoperative blood loss were recorded. Postoperatively, radiographs and computed tomography scans were reviewed to evaluate the condition of bone cement removal, control of infection, and bone fusion. Oswestry disability index (ODI) and visual analog scale (VAS) were assessed pre- and postoperatively, and clinical outcomes were assessed using Odom's criteria. RESULTS: All patients achieved satisfactory tainted bone cement cleaning and restoration of spinal alignment. The surgical time was 258.8 ± 63.2 (160-360) min, and the intraoperative blood loss was 613.3 ± 223.8 (300-900) mL. The VAS score decreased from 7.0 (6-8) points preoperatively to 2.4 (1-4) points postoperatively. The ODI index decreased from 71% (65%-80%) preoperatively to 20% (10%-30%) postoperatively. The patient's VAS and NDI scores after operation were significantly improved compared with those before surgery (p ≤ 0.05). Odom's outcomes were good for all patients in the last follow-up, and all patients reported satisfactory results. CONCLUSIONS: Piezosurgery can effectively remove large blocks of infectious bone cement through a posterior approach while avoiding nerve and spinal cord damage. We cautiously suggest that a one-stage posterior approach using piezosurgery is an alternative option for surgical treatment of PSVA.

Hidden blood loss in minimally invasive surgery for osteoporotic vertebral fractures. / [Artículo traducido] Sangrado oculto intraoperatorio en cirugía mínimamente invasiva de fracturas vertebrales osteoporóticas.

INTRODUCTION AND AIM: Minimally invasive surgery (MIS) of the spine prevents the collapse of osteoporotic vertebral fractures (OVF) with lower complication and bleeding rates than open surgery. However, the possibility of hidden blood loss (HBL) has been recently described, referring to the loss of blood diffused into tissues and lost through hemolysis. This study aimed to estimate the postoperative impact of HBL in patients undergoing MIS for OVF. MATERIALS AND METHODS: This was a retrospective study of a series of patients who had MIS for OVF. A descriptive analysis of recorded variables was performed, and total blood volume, total bleeding, HBL, and hemoglobine drop were calculated. This was followed by a comparative analysis between HBL (<500ml vs. ≥500ml) and the variables of hospital stay and postoperative evolution. Binary logistic regression models were performed to rule out confounding factors. RESULTS: A total of 40 patients were included, 8 men and 32 women, with a mean age of 76.6 years. The mean HBL was 682.5ml. An HBL greater than 500ml is found to be an independent risk factor for torpid postoperative evolution (P=0.035), while it does not predict a longer hospital stay (P=0.116). In addition, a higher HBL was observed in surgeries of greater technical complexity and longer surgical time. CONCLUSIONS: Although MIS techniques have shown less intraoperative bleeding than open surgery, HBL should be diagnosed because it is associated with a torpid evolution. The use of a diagnostic and therapeutic algorithm may help minimize its impact.

Comparison of the Fixation Strengths of Screws between the Traditional Trajectory and the Single and Double Endplate Penetrating Screw Trajectories Using Osteoporotic Vertebral Body Models Based on the Finite Element Method.

STUDY DESIGN: This is a finite element (FE) study. PURPOSE: To compare the fixation strength of traditional trajectory (TT) and single and double endplate penetrating screw trajectories (SEPST/DEPST) to the osteoporotic vertebral body model based on the FE method. OVERVIEW OF LITERATURE: SEPST/DEPST have been developed to enhance the fixation strength in patients with diffuse idiopathic hyperostosis (DISH). This technique was also applied to patients with osteoporosis. However, determining the superiority of SEPST/ DEPST is difficult because of the heterogeneous patient backgrounds. METHODS: Twenty vertebrae (T12 and L1) from 10 patients with osteoporosis (two males and eight females; mean age, 74.7 years) were obtained to create the 10 FE models. First, a single screw was placed with TT and SEPST/DEPST, and the fixation strength was compared by axial pullout strength (POS) and multidirectional loading tests. Second, two screws were placed on the bilateral pedicles with TT and SEPST/DEPST, and the fixation force of the vertebrae in the constructs in flexion, extension, lateral flexion, and axial rotation was examined. RESULTS: SEPST and DEPST had 140% and 171% higher POS values than TT, respectively, and the DEPST result was statistically significant (p =0.007). The multidirectional fixation strength was significantly higher in DEPST and SEPST than in TT in the cranial, caudal, and medial directions (p <0.05) but not in the lateral direction (p =0.05). The vertebral fracture strength at the lower instrumented vertebra of the DEPST tended to be higher than that of TT. The vertebral motion angles in SEPST and DEPST were significantly smaller in lateral bending (p =0.02) and tended to be smaller in flexion and extension than in TT (p =0.13). CONCLUSIONS: This study may provide useful information for spine surgeons in deciding whether to choose the SEPS or DEPS technique for augmenting fixation in osteoporotic vertebral fracture surgery.

Short-Term Risk Factors for Distal Junctional Kyphosis after Spinal Reconstruction Surgery in Patients with Osteoporotic Vertebrae.

STUDY DESIGN: Level 3 retrospective cohort case-control study. PURPOSE: This study aimed to investigate the risk factors for distal junctional kyphosis (DJK) caused by osteoporotic vertebral fractures following spinal reconstruction surgery, with a focus on the sagittal stable vertebra. OVERVIEW OF LITERATURE: Despite the rarity of reports on DJK in this setting, DJK was reported to reduce when the lower instrumented vertebra (LIV) was extended to the sagittal stable vertebra in the posterior corrective fixation for Scheuermann's disease. METHODS: This study included 46 patients who underwent spinal reconstruction surgery for thoracolumbar osteoporotic vertebral fractures and kyphosis and were followed up for 1 year postoperatively. DJK was defined as an advanced kyphosis angle >10° between the LIV and one lower vertebra. The patients were divided into groups with and without DJK. The risk factors of the two groups, such as patient background, surgery-related factors, radiographic parameters, and clinical outcomes, were analyzed. RESULTS: The DJK and non-DJK groups included 14 and 32 patients, respectively, without significant differences in patient background. Those with instability in the distal adjacent LIV disc had a significantly higher risk of DJK occurrence (28.6% vs. 3.2%, p=0.027). DJK occurrence significantly increased in those with the sagittal stable vertebra not included in the fixation range (57.1% vs. 18.8%, p=0.020). Other preoperative radiographic parameters were not significantly different. Instability in the distal adjacent LIV disc (adjusted odds ratio, 14.50; p=0.029) and the exclusion of the sagittal stable vertebra from the fixation range (adjusted odds ratio, 5.29; p=0.020) were significant risk factors for DJK occurrence. CONCLUSIONS: Regarding spinal reconstruction surgery in patients with osteoporotic vertebral fractures, instability in the distal adjacent LIV disc and the exclusion of the sagittal stable vertebra from the fixation range were risk factors for DJK occurrence in the short term.

Establishment of a risk prediction model for residual low back pain in thoracolumbar osteoporotic vertebral compression fractures after percutaneous kyphoplasty.

OBJECTIVE: This study aims to identify potential independent risk factors for residual low back pain (LBP) in patients with thoracolumbar osteoporotic vertebral compression fractures (OVCFs) following percutaneous kyphoplasty (PKP) treatment. Additionally, we aim to develop a nomogram that can accurately predict the occurrence of residual LBP. METHODS: We conducted a retrospective review of the medical records of thoracolumbar OVCFs patients who underwent PKP treatment at our hospital between July 2021 and December 2022. Residual LBP was defined as the presence of moderate or greater pain (VAS score ≥ 4) in the low back one day after surgery, and patients were divided into two groups: the LBP group and the non-LBP group. These patients were then randomly allocated to either a training or a validation set in the ratio of 7:3. To identify potential risk factors for residual LBP, we employed lasso regression for multivariate analysis, and from this, we constructed a nomogram. Subsequently, the predictive accuracy and practical clinical application of the nomogram were evaluated through a receiver operating characteristic (ROC) curve, a calibration curve, and a decision curve analysis (DCA). RESULTS: Our predictive model revealed that five variables-posterior fascial oedema, intravertebral vacuum cleft, time from fracture to surgery, sarcopenia, and interspinous ligament degeneration-were correlated with the presence of residual LBP. In the training set, the area under the ROC was 0.844 (95% CI 0.772-0.917), and in the validation set, it was 0.842 (95% CI 0.744-0.940), indicating that the model demonstrated strong discriminative performance. Furthermore, the predictions closely matched actual observations in both the training and validation sets. The decision curve analysis (DCA) curve suggested that the model provides a substantial net clinical benefit. CONCLUSIONS: We have created a novel numerical model capable of accurately predicting the potential risk factors associated with the occurrence of residual LBP following PKP in thoracolumbar OVCFs patients. This model serves as a valuable tool for guiding specific clinical decisions for patients with OVCFs.

Osteoporotic vertebral fractures localized in the lumbar area significantly impact sagittal alignment.

Lumbar fractures and/or multiple fractures at the lumbar or thoracolumbar regions are risk factors for sagittal malalignment in patients older than 70 years old. Although patients with OVF show a huge capacity to compensate after the fractures, lumbar and TL lumbar fractures require closer monitoring. PURPOSE: To assess the impact of osteoporotic vertebral fractures on the sagittal alignment of the elderly and identify risk factors for sagittal malalignment. METHODS: We performed a retrospective study on a cohort of 249 patients older than 70 years old and diagnosed with osteoporosis who suffered chronic vertebral fractures. Demographic and radiological data were collected. Full-spine lateral X-rays were obtained to analyze the sagittal plane. Patients were classified according to the number and location of the fractures. Pearson's correlation coefficient was used to assess the relationships between the type of fractures and sagittal alignment. RESULTS: A total of 673 chronic fractures were detected in 249 patients with a mean number of vertebral fractures per patient of 2.7 ± 1.9. Patients were divided into 9 subgroups according to the location and the number of fractures. Surprisingly, any of the aggregated parameters used to assess sagittal alignment exceeded the threshold defined for malalignment. In the second part of the analysis, 41 patients with sagittal malalignment were identified. In this subpopulation, an overrepresentation of patients with lumbar fractures (34% vs. 11%) and an under-representation of thoracic fractures (9% vs. 34%) were reported. We also observed that patients with 3 or more lumbar or thoracolumbar fractures had an increased risk of sagittal malalignment. CONCLUSIONS: Lumbar fractures and/or multiple fractures at the lumbar or thoracolumbar regions are risk factors for sagittal malalignment in patients older than 70 years old. Although patients show a remarkable capacity to compensate, fractures at the lumbar and thoracolumbar regions need closer monitoring.

Hidden blood loss in minimally invasive surgery for osteoporotic vertebral fractures.

INTRODUCTION AND AIM: Minimally invasive surgery (MIS) of the spine prevents the collapse of osteoporotic vertebral fractures (OVF) with lower complication and bleeding rates than open surgery. However, the possibility of hidden blood loss (HBL) has been recently described, referring to the loss of blood diffused into tissues and lost through hemolysis. This study aimed to estimate the postoperative impact of HBL in patients undergoing MIS for OVF. MATERIALS AND METHODS: This was a retrospective study of a series of patients who had MIS for OVF. A descriptive analysis of recorded variables was performed, and total blood volume (TBV), total bleeding (TB), HBL, and Hb drop were calculated. This was followed by a comparative analysis between HBL (<500mL vs. ≥500mL) and the variables of hospital stay and postoperative evolution. Binary logistic regression models were performed to rule out confounding factors. RESULTS: A total of 40 patients were included, 8 men and 32 women, with a mean age of 76.6 years. The mean HBL was 682.5mL. An HBL greater than 500mL is found to be an independent risk factor for torpid postoperative evolution (p=0.035), while it does not predict a longer hospital stay (p=0.116). In addition, a higher HBL was observed in surgeries of greater technical complexity and longer surgical time. CONCLUSIONS: Although MIS techniques have shown less intraoperative bleeding than open surgery, HBL should be diagnosed because it is associated with a torpid evolution. The use of a diagnostic and therapeutic algorithm may help minimize its impact.

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.

Percutaneous Functional Spinal Unit Cementoplasty versus Posterior Spinal Fixation with Vertebroplasty for Symptomatic Chronic Osteoporotic Vertebral Fractures: A Retrospective Study with a 2-Year Follow up.

PURPOSE: To compare the clinical efficacy of percutaneous functional spinal unit cementoplasty (PFSUP) and posterior spinal fixation combined with vertebroplasty (PSF + VP) for the treatment of symptomatic chronic osteoporotic vertebral fractures (SCOVFs). METHOD: Thirty-one patients with SCOVFs were included in this retrospective study and divided into PFSUP (n = 14) and PSF + VP (n = 17) groups. Visual analog scores (VAS) and Oswestry Disability Index (ODI) were recorded before and after surgery and at the last follow-up. Besides, the local kyphosis angle (LKA) and sagittal vertical axis (SVA) were measured. The operation duration, number of X-ray exposures, amount of blood loss, bed rest duration, hospitalization duration, and presence of complications were recorded. RESULT: The VAS, ODI, LKA, and SVA after surgery and at the last follow-up were significantly improved in both groups compared to preoperative measurements. The PFSUP group experienced shorter operation duration (78.2 ± 13.1 vs. 124.7 ± 14.7, p < 0.001), less blood loss (31.1 ± 8.1 vs. 334.7 ± 70.9, p < 0.001), more X-ray exposures (92.1 ± 14.3 vs. 29.4 ± 5.5, p < 0.001), shorter bed rest duration (12.4 ± 3.8 vs. 43.4 ± 10.0, p < 0.001), shorter hospitalization (6.6 ± 2.4 vs. 10.9 ± 2.7, p < 0.001), lower complication rate (28.5% vs. 64.7%, p < 0.05), and higher cement leakage rate (42.9% vs. 5.8%, p < 0.05) than the PSF + VP group. CONCLUSION: During the treatment of SCOVFs, the combination of PFSUP and PSF + VP can restore spinal stability, improve kyphosis, and relieve pain. PFSUP can reduce blood loss and complications, early mobilization, and shorten the hospital stay, but it is associated with a higher cement leakage rate and more radiation exposure.

A Deep Learning-Based Model for Classifying Osteoporotic Lumbar Vertebral Fractures on Radiographs: A Retrospective Model Development and Validation Study.

Early diagnosis and initiation of treatment for fresh osteoporotic lumbar vertebral fractures (OLVF) are crucial. Magnetic resonance imaging (MRI) is generally performed to differentiate between fresh and old OLVF. However, MRIs can be intolerable for patients with severe back pain. Furthermore, it is difficult to perform in an emergency. MRI should therefore only be performed in appropriately selected patients with a high suspicion of fresh fractures. As radiography is the first-choice imaging examination for the diagnosis of OLVF, improving screening accuracy with radiographs will optimize the decision of whether an MRI is necessary. This study aimed to develop a method to automatically classify lumbar vertebrae (LV) conditions such as normal, old, or fresh OLVF using deep learning methods with radiography. A total of 3481 LV images for training, validation, and testing and 662 LV images for external validation were collected. Visual evaluation by two radiologists determined the ground truth of LV diagnoses. Three convolutional neural networks were ensembled. The accuracy, sensitivity, and specificity were 0.89, 0.83, and 0.92 in the test and 0.84, 0.76, and 0.89 in the external validation, respectively. The results suggest that the proposed method can contribute to the accurate automatic classification of LV conditions on radiography.

Risk Factors for Cage Subsidence in Minimally Invasive Lateral Corpectomy for Osteoporotic Vertebral Fractures.

Introduction: This study aims to investigate risk factors for cage subsidence following minimally invasive lateral corpectomy for osteoporotic vertebral fractures. Methods: Eight males and 13 females (77.2±6.0 years old) with osteoporotic vertebral fractures who underwent single corpectomy using a wide-footprint expandable cage with at least a 1-year follow-up were retrospectively included. The endplate cage (EC) angle was defined as the angle between the vertebral body's endplate and the cage's base on the cranial and caudal sides. A sagittal computed tomography scan was performed immediately after surgery and at the final follow-up, with cage subsidence defined as subsidence of ≥2 mm on the cranial or caudal side. Risk factors were analyzed by dividing cases into groups with (n=6) and without (n=15) cage subsidence. Results: No significant differences were noted in age, bone mineral density, number of fixed vertebrae, sagittal parameters, preoperative and final kyphosis angle, amount of kyphosis angle correction, bone union, screw loosening, and number of other vertebral fractures preoperatively and 1-year postoperatively between the two groups. No difference was noted in cranial EC angle, but a significant difference was noted in caudal EC angle in the group with (10.7±4.1°) and without (4.7±4.2°) subsidence (P=0.008). Logistic regression analysis with the dependent variable as presence or absence of subsidence showed that caudal EC angle (>7.5°) was a significant factor (odds ratio: 20, 95% confidence interval: 1.655-241.7, P=0.018). Conclusions: In minimally invasive lateral corpectomy for osteoporotic vertebral fractures, a cage tilted more than 7.5° to the caudal vertebral endplate is a risk factor for cage subsidence. The cage should be placed as perpendicular to the endplate as possible, especially to the caudal vertebral body, to avoid cage subsidence.

Using Artificial Intelligence to Diagnose Osteoporotic Vertebral Fractures on Plain Radiographs.

Osteoporotic vertebral fracture (OVF) is a risk factor for morbidity and mortality in elderly population, and accurate diagnosis is important for improving treatment outcomes. OVF diagnosis suffers from high misdiagnosis and underdiagnosis rates, as well as high workload. Deep learning methods applied to plain radiographs, a simple, fast, and inexpensive examination, might solve this problem. We developed and validated a deep-learning-based vertebral fracture diagnostic system using area loss ratio, which assisted a multitasking network to perform skeletal position detection and segmentation and identify and grade vertebral fractures. As the training set and internal validation set, we used 11,397 plain radiographs from six community centers in Shanghai. For the external validation set, 1276 participants were recruited from the outpatient clinic of the Shanghai Sixth People's Hospital (1276 plain radiographs). Radiologists performed all X-ray images and used the Genant semiquantitative tool for fracture diagnosis and grading as the ground truth data. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were used to evaluate diagnostic performance. The AI_OVF_SH system demonstrated high accuracy and computational speed in skeletal position detection and segmentation. In the internal validation set, the accuracy, sensitivity, and specificity with the AI_OVF_SH model were 97.41%, 84.08%, and 97.25%, respectively, for all fractures. The sensitivity and specificity for moderate fractures were 88.55% and 99.74%, respectively, and for severe fractures, they were 92.30% and 99.92%. In the external validation set, the accuracy, sensitivity, and specificity for all fractures were 96.85%, 83.35%, and 94.70%, respectively. For moderate fractures, the sensitivity and specificity were 85.61% and 99.85%, respectively, and 93.46% and 99.92% for severe fractures. Therefore, the AI_OVF_SH system is an efficient tool to assist radiologists and clinicians to improve the diagnosing of vertebral fractures. © 2023 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).

Lower ratio of adjacent to injured vertebral bone quality scores can predict augmented vertebrae recompression following percutaneous kyphoplasty for osteoporotic vertebral fractures with intravertebral clefts.

BACKGROUND: Despite the favorable clinical outcome of percutaneous kyphoplasty (PKP) in symptomatic osteoporotic vertebral fractures (OVFs) patients with intravertebral clefts (IVCs), previous studies have demonstrated a high incidence of augmented vertebrae recompression (AVR). We aim to evaluate the usefulness of the adjacent and injured vertebral bone quality scores (VBQS) based on T1-weighted MRI images in AVR after PKP for OVFs with IVCs. METHODS: Patients who underwent PKP for single OVFs with IVCs between January 2014 and September 2020 were reviewed and met the inclusion criteria. The follow-up period was at least 2 years. Relevant data affecting AVR were collected. Pearson and Spearman correlation coefficients were used to calculate the correlation between the injured and adjacent VBQS and BMD T-score. We determined independent risk factors and critical values using binary logistic regression analysis and receiver operating characteristic curves (ROC). RESULTS: A total of 165 patients were included. Recompression group was found in 42 (25.5%) patients. The independent risk factors for AVR were lumbar BMD T-score (OR = 2.53, p = 0.003), the adjacent VBQS (OR = 0.79, p = 0.016), the injured VBQS (OR = 1.27, p = 0.048), the ratio of adjacent to injured VBQS (OR = 0.32, p < 0.001), and cement distribution pattern. Among these independent significant risk factors, the prediction accuracy of the ratio of adjacent to injured VBQS was the highest (Cutoff = 1.41, AUC = 0.753). Additionally, adjacent and injured VBQS were negatively correlated with lumbar BMD T-scores. CONCLUSION: For the patients after PKP treatment for OVFs with IVCs, the ratio of adjacent to injured VBQS had the best prediction accuracy in predicting recompression and when the ratio of adjacent to injured VBQS was <1.41, the augmented vertebrae were more likely to have recompression in the future.

Prediction of subsequent vertebral compression fractures after thoracolumbar kyphoplasty: a multicenter retrospective analysis.

OBJECTIVE: Second fractures at the cemented vertebrae (SFCV) are often seen after percutaneous kyphoplasty, especially at the thoracolumbar junction. Our study aimed to develop and validate a preoperative clinical prediction model for predicting SFCV. METHODS: A cohort of 224 patients with single-level thoracolumbar osteoporotic vertebral fractures (T11-L2) from 3 medical centers was analyzed between January 2017 and June 2020 to derive a preoperative clinical prediction model for SFCV. Backward-stepwise selection was used to select preoperative predictors. We assigned a score to each selected variable and developed the SFCV scoring system. Internal validation and calibration were conducted for the SFCV score. RESULTS: Among the 224 patients included, 58 had postoperative SFCV (25.9%). The following preoperative measures on multivariable analysis were summarized in the 5-point SFCV score: bone mineral density (≤-3.05), serum 25-hydroxy vitamin D3 (≤17.55 ng/mL), standardized signal intensity of fractured vertebra on T1-weighted images (≤59.52%), C7-S1 sagittal vertical axis (≥3.25 cm), and intravertebral cleft. Internal validation showed a corrected area under the curve of 0.794. A cutoff of ≤1 point was chosen to classify a low risk of SFCV, for which only 6 of 100 patients (6%) had SFCV. A cutoff of ≥4 points was chosen to classify a high risk of SFCV, for which 28 of 41 (68.3%) had SFCV. CONCLUSION: The SFCV score was found to be a simple preoperative method for identification of patients at low and high risk of postoperative SFCV. This model could be applied to individual patients and aid in the decision-making before percutaneous kyphoplasty.

Establishment of a novel risk prediction model for recompression of augmented vertebrae at the thoracolumbar junction and modified puncture technique for prevention: a multicenter retrospective study.

OBJECTIVE: Recompression of augmented vertebrae (RCAV) is often seen after percutaneous kyphoplasty (PKP), especially at the thoracolumbar junction. The authors aimed to develop and validate a risk prediction model (nomogram) for RCAV and to evaluate the efficacy of a modified puncture technique for RCAV prevention after PKP for thoracolumbar osteoporotic vertebral fractures (OVFs). METHODS: Patients who underwent PKP for single thoracolumbar OVFs (T10-L2) between January 2016 and October 2020 were reviewed and followed up for at least 2 years. All patients were randomly divided into a training group (70%) and a validation group (30%). Relevant potential data affecting recompression were collected. Predictors were screened by using binary logistic regression analysis to construct the nomogram. Calibration and receiver operating characteristic curves were used to evaluate the consistency of the prediction models. Finally, the efficacy of the modified puncture technique for prevention of RCAV in OVF patients with a preoperative intravertebral cleft (IVC) was further demonstrated through binary logistic regression analysis. RESULTS: Overall, 394 patients were included and 116 of them (29.4%) sustained RCAV. The independent risk factors included decreased bone mineral density, lower level of serum 25-hydroxy vitamin D3, larger C7-S1 sagittal vertical axis (SVA), preoperative IVC, and solid-lump cement distribution. The area under the curve (AUC) of the prediction model was 0.824 in the training group and 0.875 in the validation group patients. The calibration curve indicated the predictive power of this nomogram, with the preoperative IVC having the highest prediction accuracy (AUC 0.705). The modified puncture technique significantly reduced the incidence of RCAV by enhancing bone cement distribution into a sufficiently diffused distribution in OVF patients with preoperative IVC. CONCLUSIONS: The nomogram prediction model had satisfactory accuracy and clinical utility for identification of patients at low and high risk of postoperative RCAV. Patients at high risk of postoperative RCAV might benefit from the target puncture technique and vitamin D supplementation as well as effective antiosteoporotic therapies.