Establishment and validation of a nomogram and web calculator for the risk of new vertebral compression fractures and cement leakage after percutaneous vertebroplasty in patients with osteoporotic vertebral compression fractures

Risk factor analysis of adjacent vertebral compression fracture following the surgery of percutaneous kyphoplasty in postmenopausal women

To evaluate the risk factors for adjacent vertebral compression fracture(AVCF) following the surgery of percutaneous kyphoplasty (PKP) in postmenopausal women. Two hundred and ninety-seven postmenopausal female patients had been reviewed, underwent PKP surgery between January 2016 and December 2020, were divided into two groups according to whether or not AVCF. Receiver operating characteristic (ROC) curves were generated to analyze the sensitivity and specificity of the relative risk factors in the identification of AVCF. In this study of 297 postmenopausal women who underwent PKP, 67 developed AVCF during follow-up. There were no significant differences in BMI, surgical method, or cement leakage between the groups. The AVCF group was older, had lower BMD, less bone cement volume per section, higher VHA, and larger VKAC. The non-fracture group had lower postoperative VAS and fewer surgical vertebrae. The model showed good discrimination with age, BMD, postoperative VAS, VHR, and VKAC. ROC analysis indicated that a postoperative with high VHR, high VKAC or VAS score > 2.5 was highly predictive of AVCF in postmenopausal women after PKP. In the context of PKP for OVCF in postmenopausal women, it is crucial to avoid excessive VHR and VKAC. Postoperatively, clinicians should prioritize pain management strategies to ensure optimal patient outcomes.

Similarities in distribution pattern between acute multiple osteoporotic vertebral compression fractures and vertebral fractures cascades

BACKGROUD

Osteoporotic vertebral compression fractures (OVCF) cascades (OVCFcs) repeatedly cause vertebral compression to involve multiple vertebra. This study aimed to introduce an accelerated form of OVCFcs: acute multiple OVCF (amOVCF).

METHODS

OVCF patients with multiple vertebral augmentations in a spine center between June 2016 and October 2020 were retrospectively studied. Demographics, spine trauma, anatomical distribution, and distribution pattern of OVCF in OVCFcs and amOVCF were summarized and compared.

RESULTS

429 patients with multiple vertebral augmentations in 1164 vertebra were included. There were 210 OVCFcs accumulating 622 OVCF and 219 amOVCF simultaneously involving 542 vertebra. The OVCFcs progressed at 0.48 fractures and 0.56 vertebra per year. Both OVCFcs and amOVCF demonstrated asymmetrical bimodal distribution in spine and most frequently involved L1. The incidence of adjacent OVCF was 40.14% in amOVCF with 2 OVCF and 84.72% in amOVCF with ≥ 3 OVCF, and the distribution pattern of OVCF was not significantly different between amOVCF and OVCFcs. The female/male ratio was 5.56 in OVCFcs and not different from that of 4.34 in amOVCF. The age of females (73.41 ± 8.08 and 76.29 ± 8.25 years old) but not males (77.20 ± 10.13 and 79.75 ± 10.21 years old) was significantly increased from initial to last OVCF in OVCFcs. amOVCF had similar age (72.26 ± 10.09 years old) as OVCFcs at initial OVCF (73.99 ± 8.51 years old) and were significantly younger than OVCFcs at last OVCF (76.82 ± 8.64 years old). 54.29% in OVCFcs and 48.4% in amOVCF reported no evident trauma, and the ratio of apparent spine trauma was higher in amOVCF (43.38%) than in OVCFcs (28.54%).

CONCLUSIONS

amOVCF are accelerated form of OVCFcs showing similar anatomical distribution and distribution pattern of OVCF in spine. Both amOVCF and OVCFcs cause multiple fragility fractures without significant spine trauma.

Biomechanical and clinical evaluation of PSO, modified PSO and VCR treating OVCF kyphosis: a finite element analysis

Objective

To confirm the effect of surgery on spinal column biomechanics and to provide theoretical support for the advantages and disadvantages of different surgical methods and their clinical efficacy.

Methods

33 continuous patients with no significant difference in risk factors related to the mechanical complications were enrolled in this retrospective study. Sagittal parameters were measured in the pre-, post-operative and following-up lateral radiograph of spine. An finite element (FE) model was created using CT scanning from a female volunteer with osteoporotic vertebral compression fracture (OVCF) with solely kyphosis. Pedicle subtraction osteotomy (PSO), vertebral column resection (VCR) and modified PSO(mPSO) for OVCF were simulated on FE model. Stress distribution and deformation of the FE model were measured.

Results

Clinical - All differences in preoperative spinal sagittal parameters were not statistically significant. mPSO showed it is superior to PSO and VCR in multiple postoperative and following-up spinal sagittal parameters. The operation duration and intraoperative blood loss of mPSO are less than the other two. For postoperative mechanical complications, no statistically significant differences were observed. Biomechanical - Six operating conditions (flexion, extension, left/right bending, left/right twisting) for each post-operative FE model have been examined. In most conditions, the displacement of mPSO is similar to that of PSO, with both larger than that of VCR. All the maximum equivalent stress on the vertebral body is within the safe range. The stress is mainly distributed on the T10 vertebral body and the fixed vertebral body L2, while the stress of VCR is greater than that of mPSO and PSO. The intervertebral disc pressure is highest in VCR, followed by PSO, and lowest in mPSO under all conditions. The maximum pressure on the intervertebral discs is located between T10 and T11.

Conclusion

The finite element analysis showed that mPSO has a similar spine stability to PSO, and possibly creates a better environment for bone-to-bone fusion and prevents adjacent segments degeneration. Combined with its less surgical risks, we believe that the modified pedicle subtraction osteotomy may be an appropriate strategy for indicated cases of OVCF.

Effect of Robot-Assisted Surgery on Clinical Outcomes in Patients with Osteoporotic Vertebral Compression Fractures after Percutaneous Vertebral Augmentation: a Meta-Analysis and a Validation Cohort

Background

The objective of this study was to investigate the impact of robot-assisted surgery (RA) on the risk of new vertebral compression fracture (NVCF) and bone cement leakage in patients with osteoporotic vertebral compression fractures (OVCF) after percutaneous vertebral augmentation (PVA), including percutaneous kyphoplasty (PKP) and percutaneous vertebroplasty (PVP).

Methods

A meta-analysis was performed to evaluate the clinical outcomes and adverse effects of RA-PVA versus fluoroscopy-assisted (FA)-PVA in patients with OVCF. A validation cohort of 385 patients who underwent PVP or PKP was retrospectively analyzed. In addition, we attempted to create well-calibrated nomograms to estimate the risk of NVCF and bone cement leakage.

Results

The meta-analysis revealed that the incidence of NVCF and bone cement leakage was significantly lower in RA-PVA than in FA-PVA. The validation cohort confirmed that RA-PVA provided better results than FA-PVA in terms of NVCF and bone cement leakage.

Conclusions

The meta-analysis and the validation cohort suggest that RA reduced the risk of NVCF and bone cement leakage in patients with OVCF after PVA. The nomograms are accurate and easy-to-implement methods for clinicians to estimate the risk of NVCF and bone cement leakage after PVA.

Development and validation of nomograms based on the SEER database for the risk factors and prognosis of distant metastasis in gastric signet ring cell carcinoma

Poor prognosis in patients with distant metastasis of gastric signet ring cell carcinoma (GSRC), and there are few studies on the development and validation of the diagnosis and prognosis of distant metastasis of GSRC. The Surveillance, Epidemiology, and End Results database was used to identify patients with GSRC from 2004 to 2019. Univariate and multivariate logistic regression analysis were used to identify independent risk factors for distant metastasis of GSRC, while univariate and multivariate Cox proportional hazard regression analysis were used to determine independent prognostic factors for patients with distant metastasis of GSRC. Two nomograms were established, and model performance was evaluated using receiver operating characteristic curves, calibration plots, and decision curve analysis. A total of 9703 cases with GSRC were enrolled, among which 2307 cases (23.78%) were diagnosed with distant metastasis at the time of diagnosis. Independent risk factors for distant metastasis included age, race, and T stage. Independent prognostic factors included T stage, chemotherapy, and surgery. The receiver operating characteristic curve, calibration curve, decision curve analysis curve, and Kaplan-Meier survival curve of the training set and validation set confirmed that the 2 nomograms could accurately predict the occurrence and prognosis of distant metastasis in GSRC. Two nomograms can serve as effective prediction tools for predicting distant metastasis in GSRC patients and the prognosis of patients with distant metastasis. They have a certain clinical reference value.

Adjacent Vertebral Refracture Prediction Model Based on Imaging Data After Vertebroplasty for Osteoporotic Vertebral Compression Fracture

OBJECTIVES

To establish a predictive model to evaluate the risk of adjacent vertebral refracture (VRF) after percutaneous kyphoplasty (PKP) for osteoporotic vertebral compression fracture (OVCF) based on perioperative imaging data.

METHODS

This study was a retrospective cohort study which established a predictive model of VRF after PKP for OVCF. Patients who underwent PKP for OVCF in our hospital between January 2018 and December 2020 were enrolled and divided into a refracture group and normal group. Perioperative imaging data including preoperative bone mineral density (BMD), fatty infiltration (FI%) of paravertebral muscle, sagittal parameters of the spine and pelvis, and recovery rate of vertebral height were collected. The prediction model is obtained by multifactor logistic regression analysis.

RESULTS

A total of 242 patients were included, including 23 cases in the VRF group and 219 cases in the normal group. There were statistical differences in BMD, FI%, recovery rate of vertebral height, and sagittal imbalance between the 2 groups. Receiver operating characteristic curve analysis of continuous variables showed that BMD ≤-2.80, FI% ≥40%, and recovery rate of vertebral height ≥ 10% were the cutoff values. Logistic regression analysis showed that BMD ≤-2.80, FI% ≥40%, and sagittal imbalance were independent risk factors for VRF. The area under the curve according to the predicted probability was 0.85 (P < 0.05). After simplifying the model, the total point of the model was 7 points, with a cutoff value of 5 points.

CONCLUSIONS

The prediction model obtained in this study can predict refracture after PKP for OVCF early and effectively. It has an excellent predictive effect which is suitable for clinicians.

Deep learning-based multimodal image analysis predicts bone cement leakage during percutaneous kyphoplasty: protocol for model development, and validation by prospective and external datasets

Background

Bone cement leakage (BCL) is one of the most prevalent complications of percutaneous kyphoplasty (PKP) for treating osteoporotic vertebral compression fracture (OVCF), which may result in severe secondary complications and poor outcomes. Previous studies employed several traditional machine learning (ML) models to predict BCL preoperatively, but effective and intelligent methods to bridge the distance between current models and real-life clinical applications remain lacking.

Methods

We will develop a deep learning (DL)-based prediction model that directly analyzes preoperative computed tomography (CT) and magnetic resonance imaging (MRI) of patients with OVCF to accurately predict BCL occurrence and classification during PKP. This retrospective study includes a retrospective internal dataset for DL model training and validation, a prospective internal dataset, and a cross-center external dataset for model testing. We will evaluate not only model's predictive performance, but also its reliability by calculating its consistency with reference standards and comparing it with that of clinician prediction.

Discussion

The model holds an imperative clinical significance. Clinicians can formulate more targeted treatment strategies to minimize the incidence of BCL, thereby improving clinical outcomes by preoperatively identifying patients at high risk for each BCL subtype. In particular, the model holds great potential to be extended and applied in remote areas where medical resources are relatively scarce so that more patients can benefit from quality perioperative evaluation and management strategies. Moreover, the model will efficiently promote information sharing and decision-making between clinicians and patients, thereby increasing the overall quality of healthcare services.

The predictive value of albumin to alkaline phosphatase ratio for vertebral refractures in postmenopausal women

INTRODUCTION

To investigate the clinical value of serum albumin to alkaline phosphatase ratio (AAPR) in predicting the risk of osteoporotic vertebral refractures group (OVRFs) after percutaneous vertebral augmentation (PVA) in postmenopausal women.

MATERIALS AND METHODS

This is a retrospective case-control study including a series of postmenopausal women patients with osteoporotic vertebral fracture (OVF) and underwent PVA. Patients were divided into OVRFs and non-OVRFs. COX model was used to evaluate the correlation between preoperative AAPR and OVRFs after PVA. The receiver operating characteristic (ROC) curve and Kaplan-Meier method were used to analyze the predictive value of AAPR for the incidence of OVRFs.

RESULTS

A total of 305 patients were included in the final study, and the incidence of postoperative OVRFs was 28.9%. Multivariate COX analysis showed that advanced age (HRs = 1.062, p = 0.002), low BMI (HRs = 0.923, p = 0.036), low AAPR (HRs = 0.019, p = 0.001), previous fall history (HRs = 3.503, p = 0.001), denosumab treatment (HRs = 0.409, p = 0.007), low L3 BMD (HRs = 0.977, p = 0.001) and low L3 paravertebral muscle density (PMD)value (HRs = 0.929, p = 0.001)) were closely related to the incidence of OVRFs. The area under the curve (AUC) of AAPR for predicting OVRFs was 0.740 (p < 0.001), and the optimal diagnostic cut-off value was 0.49. Kaplan-Meier curve analysis showed that low AAPR group (< 0.49) was significantly associated with lower OVRFs-free survival (p = 0.001; log-rank test).

CONCLUSION

AAPR is an independent risk factor for OVRFs after PVA in postmenopausal women, and it can be used as an effective index to predict OVRFs.

Risk factors for cement leakage after percutaneous vertebral augmentation for osteoporotic vertebral compression fractures: a meta-analysis

BACKGROUND

Osteoporotic vertebral compression fractures (OVCF) may necessitate percutaneous vertebral augmentation (PVA), a procedure not without its risks. One notable complication is cement leakage (CL), which can cause significant distress in patients. Despite its clinical importance, there remains a paucity of meta-analyses investigating these complications and their management in the existing literature.

MATERIAL AND METHODS

We systematically reviewed PubMed, Cochrane Library, Embase, and Web of Science databases up to February 2024 to identify studies examining CL following PVA treatment in OVCF. We assessed the quality of eligible cohort studies using the Newcastle-Ottawa Scale (NOS), extracted data on incidence, identified risk factors for CL, and conducting meta-analysis with Revman 5.2 software. We calculated odd ratios (OR) and Mean Differences (MD) with 95% confidence interval (CI) applying random effects models.

RESULTS

We identified twelve cohort studies that matched our strict inclusion criteria. These studies included a total of 2388 patients and 3392 vertebrae. CL was identified in 1132 vertebrae. Notable risk factors for CL included compromised cortical bone integrity (OR 5.00, 95% CI 3.01~8.29, P<0.00001), presence of intravertebral vacuum clefts (OR 1.68, 95% CI 1.07~2.65, P=0.03), basivertebral foramen sign (OR 1.77, 95% CI 1.09~2.89, P=0.02), and volume of cement used (MD 0.75, 95% CI 0.41~1.10, P<0.0001).

CONCLUSION

Our findings underscore the significance of cortical bone integrity, intravertebral vacuum cleft, basivertebral foramen sign, and cement volume as principal determinants of CL risk in PVA for OVCF. These insights advocate for tailored surgical strategies to mitigate the risk of CL in this patient population.

Incidence and risk factors of subsequent vertebral fracture following percutaneous vertebral augmentation in postmenopausal women

PURPOSE

Subsequent vertebral fracture (SVF) is a severe advent event of percutaneous vertebral augmentation (PVA). However, the incidence and risk factors of SVF following PVA for OVCF in postmenopausal women remain unclear. This research aims to investigative the incidence and risk factors of SVF after PVA for OVCF in postmenopausal women.

METHODS

Women who underwent initial PVA for OVCF between August 2019 and December 2021 were reviewed. Univariate logistic regression analysis was performed to identify possible risk factors of SVF, and independent risk factors were determined by multivariate logistic regression.

RESULTS

A total of 682 women after menopause were enrolled in the study. Of these women, 100 cases had an SVF after PVA, with the incidence of 14.66%. Univariate logistic regression analysis demonstrated that age (p = 0.001), body mass index (BMI) (p < 0.001), steroid use (p = 0.008), history of previous vertebral fracture (p < 0.001), multiple vertebral fracture (p = 0.033), postoperative wedge angle (p = 0.003), and HU value (p < 0.001) were significantly correlated with SVF following PVA. Furthermore, BMI (OR [95%CI] = 0.892 [0.825 - 0.965]; p = 0.004), steroid use (OR [95%CI] = 3.029 [1.211 - 7.574]; p = 0.018), history of previous vertebral fracture (OR [95%CI] = 1.898 [1.148 - 3.139]; p = 0.013), postoperative wedge angle (OR [95%CI] = 1.036 [1.004 - 1.070]; p = 0.028), and HU value (OR [95%CI] = 0.980 [0.971 - 0.990]; p < 0.001) were identified as independent risk factors of SVF after PVA by multivariate logistic regression analysis.

CONCLUSIONS

The incidence of SVF following PVA for OVCF in postmenopausal women was 14.66%. BMI, steroid use, history of previous vertebral fracture, postoperative wedge angle, and HU value were independent risk factors of SVF after PVA for OVCF in postmenopausal women.

Prediction of new vertebral compression fracture within 3 years after percutaneous vertebroplasty for osteoporotic vertebral compression fracture: Establishment and validation of a nomogram prediction model

New vertebral compression fractures (NVCF) are common in patients with osteoporotic vertebral compression fractures (OVCF) who have undergone percutaneous vertebroplasty (PVP). We sought to develop a nomogram prediction model for better identification and prevention of NVCF within 3 years after PVP in patients with OVCF. The demographic, clinical, and imaging data of patients who underwent PVP for OVCF between January 2010 and December 2019 were reviewed. Multivariate logistic regression analysis was used to screen for risk factors for NVCF within 3 years after PVP. A nomogram prediction model was then developed and validated to visually predict NVCF. The samples in the model were randomly divided into training and validation sets at a ratio of 7:3. Twenty-seven percent of patients experienced NVCF in other segments within 3 years after PVP. Older age, lower bone mineral density (BMD), smoking, lack of anti-osteoporosis therapy, and postoperative trauma were risk factors for NVCF. The area under the receiver operating characteristic curve suggested good discrimination of this model: training set (0.781, 95% confidence interval: 0.731-0.831) and validation set (0.786, 95% confidence interval: 0.708-0.863). The calibration curve suggested good prediction accuracy between the actual and predicted probabilities in the training and validation sets. The DCA results suggested that, when the probability thresholds were 0.0452-08394 and 0.0336-0.7262 in the training and validation set, respectively, patients can benefit from using this model to predict NVCF within 3 years after PVP. In conclusion, this nomogram prediction model that included five risk factors (older age, lower BMD, smoking, postoperative minor trauma, and lack of anti-osteoporosis treatment can effectively predict NVCF within 3 years after PVP. Postoperative smoking cessation, standard anti-osteoporosis treatment, and reduction in incidental minor trauma are necessary and effective means of reducing the incidence of NVCF.

External validation of predictive models for new vertebral fractures following percutaneous vertebroplasty

OBJECTIVE

To investigate the external validation and scalability of four predictive models regarding new vertebral fractures following percutaneous vertebroplasty.

METHODS

Utilizing retrospective data acquired from two centers, compute the area under the curve (AUC), calibration curve, and Kaplan-Meier plot to assess the model's discrimination and calibration.

RESULTS

In the external validation of Zhong et al.'s 2015 predictive model for the probability of new fractures post-vertebroplasty, the AUC for re-fracture at 1, 2, and 3 years postoperatively was 0.570, 0.617, and 0.664, respectively. The AUC for Zhong et al.'s 2016 predictive model for the probability of new fractures in neighboring vertebrae was 0.738. Kaplan-Meier plot results for both models indicated a significantly lower incidence of re-fracture in low-risk patients compared to high-risk patients. Li et al.'s 2021 model had an AUC of 0.518, and its calibration curve suggested an overestimation of the probability of new fractures. Li et al.'s 2022 model had an AUC of 0.556, and its calibration curve suggested an underestimation of the probability of new fractures.

CONCLUSION

The external validation of four models demonstrated that the predictive model proposed by Zhong et al. in 2016 exhibited superior external generalization capabilities.

Risk Factors for New Adjacent and Remote Vertebral Fracture After Percutaneous Vertebroplasty

OBJECTIVE

To analyze the risk factors of new adjacent vertebral fractures (AVF) and remote vertebral fractures (RVF) after percutaneous vertebroplasty (PVP) for osteoporotic vertebral compression fractures (OVCFs).

METHODS

Patients who underwent additional PVP for new OVCFs were enrolled. In addition, we set a 1:1 age-, sex-, surgical segment-, and surgical date-matched control group, in which patients underwent PVP without new OVCFs. Data on body mass index, occurrence time of second PVP, vertebral computed tomography (CT) Hounsfield Unit (HU) at the fracture adjacent segment, and RVF segment were collected.

RESULTS

A total of 44 patients who underwent additional PVP for new OVCFs at our hospital were included. AVF occurred significantly earlier than RVF (13.5 ± 14.1 vs. 30.4 ± 20.1 months, P = 0.007). Compared to the control group, the AVF segment CT HU was significantly lower in patients with AVF (28.7 ± 16.7 vs. 61.3 ± 14.7, P = 0.000), while there was no significant difference between patients with RVF and control group including both adjacent and RVF segment CT HU. Receiver operating characteristic curves identified a cutoff value of 43 for using adjacent segment CT HU to differentiate patients with AVF from controls, with a sensitivity of 80% and a specificity of 88.9%.

CONCLUSIONS

Our study showed that the risk factors for AVF and RVF after PVP surgery were different. The occurrence of AVF was earlier and associated with low adjacent segment CT HU values, whereas the preoperative CT HU in both adjacent and RVF segments was not found to be associated with RVF.

Clinical efficacy and influencing factors of percutaneous kyphoplasty for osteoporotic vertebral compression fractures: a 10-year follow-up study

BACKGROUND

To date, few reports have evaluated the long-term outcome of percutaneous kyphoplasty (PKP) for osteoporotic vertebral compression fractures (OVCFs) and the factors influencing the long-term outcome of this procedure are uncertain.

METHODS

A total of 91 patients underwent PKP for thoracolumbar OVCFs from June 2012 to December 2012. Pain Visual Analogue Scores (VAS) and Oswestry Disability Index (ODI) were recorded preoperatively and after 10-year follow-up. Factors that may affect surgical outcome, such as gender, age, height, weight, hypertension, diabetes, cause of injury, fracture segment, length of hospitalization, history of previous spinal surgery, preoperative bone mineral density (BMD), preoperative VAS and ODI scores, length of surgery, bone cement dosage, postoperative standardized anti-osteoporosis treatment, and other new vertebral fractures, were analyzed by multiple linear regression with VAS and ODI scores at the last follow-up. The correlation factors affecting the efficacy were analyzed.

RESULTS

The preoperative and final follow-up pain VAS was 7.9 ± 1.1 and 2.2 ± 1.1. ODI scores were 30.4 ± 4.2 and 10.7 ± 2.6. The difference was statistically significant (P < 0.05). Most of the patients were females aged 65-75 years who suffered low-energy injuries, with most of the fracture segments in the thoracolumbar region (T11-L2). At the final follow-up visit, 12 cases (13.19%) developed other new vertebral fractures, and 33 cases (36.26%) continued to adhere to anti-osteoporosis treatment after discharge. Multiple linear regression analysis showed that there was a statistical difference between gender and VAS score at the last follow-up (P < 0.05), and between age, cause of injury and postoperative standardized anti-osteoporosis treatment and ODI at the last follow-up (P < 0.05). There were no statistically significant differences between the other factors and the final follow-up VAS and ODI scores (P > 0.05).

CONCLUSION

The long-term outcome after PKP is satisfactory. Age, gender, cause of injury, and standardized postoperative anti-osteoporosis treatment may be factors affecting the long-term outcome.

Interpretable Machine Learning Model to Predict Bone Cement Leakage in Percutaneous Vertebral Augmentation for Osteoporotic Vertebral Compression Fracture Based on SHapley Additive exPlanations

STUDY DESIGN

Retrospective study.

OBJECTIVES

Our objective is to create comprehensible machine learning (ML) models that can forecast bone cement leakage in percutaneous vertebral augmentation (PVA) for individuals with osteoporotic vertebral compression fracture (OVCF) while also identifying the associated risk factors.

METHODS

We incorporated data from patients (n = 425) which underwent PVA. To predict cement leakage, we devised six models based on a variety of parameters. Evaluate and juxtapose the predictive performances relied on measures of discrimination, calibration, and clinical utility. SHapley Additive exPlanations (SHAP) methodology was used to interpret model and evaluate the risk factors associated with cement leakage.

RESULTS

The occurrence rate of cement leakage was established at 50.4%. A binary logistic regression analysis identified cortical disruption (OR 6.880, 95% CI 4.209-11.246), the basivertebral foramen sign (OR 2.142, 95% CI 1.303-3.521), the fracture type (OR 1.683, 95% CI 1.083-2.617), and the volume of bone cement (OR 1.198, 95% CI 1.070-1.341) as independent predictors of cement leakage. The XGBoost model outperformed all others in predicting cement leakage in the testing set, with AUC of .8819, accuracy of .8025, recall score of .7872, F1 score of .8315, and a precision score of .881. Several important factors related to cement leakage were drawn based on the analysis of SHAP values and their clinical significance.

CONCLUSION

The ML based predictive model demonstrated significant accuracy in forecasting bone cement leakage for patients with OVCF undergoing PVA. When combined with SHAP, ML facilitated a personalized prediction and offered a visual interpretation of feature importance.

A nomogram prediction model for refracture in elderly patients with osteoporotic vertebral compression fractures after percutaneous vertebroplasty

BACKGROUND

This study aims to evaluate the risk factors of refracture in elderly patients with osteoporotic vertebral compression fracture (OVCF) patients after percutaneous vertebroplasty (PVP) and construct a predictive nomogram model.

METHODS

Elderly symptomatic OVCF patients undergoing PVP were enrolled and grouped based on the development of refracture within 1 year postoperatively. Univariate and multivariate logistic regression analyses were performed to identify risk factors. Subsequently, a nomogram prediction model was constructed and evaluated based on these risk factors.

RESULTS

A total of 264 elderly OVCF patients were enrolled in the final cohort. Among these, 48 (18.2%) patients had suffered refracture within 1 year after surgery. Older age, lower mean spinal BMD, multiple vertebral fracture, lower albumin/fibrinogen ratio (AFR), no postoperative regular anti-osteoporosis, and exercise were six independent risk factors identified for postoperative refracture. The AUC of the constructed nomogram model based on these six factors was 0.812 with a specificity and sensitivity of 0.787 and 0.750, respectively.

CONCLUSIONS

In summary, the nomogram model based on the six risk factors had clinical efficacy for refracture prediction.

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.

Development and validation of a machine learning-based nomogram for predicting HLA-B27 expression

BACKGROUND

HLA-B27 positivity is normal in patients undergoing rheumatic diseases. The diagnosis of many diseases requires an HLA-B27 examination.

METHODS

This study screened totally 1503 patients who underwent HLA-B27 examination, liver/kidney function tests, and complete blood routine examination in First Affiliated Hospital of Guangxi Medical University. The training cohort included 509 cases with HLA-B27 positivity whereas 611 with HLA-B27 negativity. In addition, validation cohort included 147 cases with HLA-B27 positivity whereas 236 with HLA-B27 negativity. In this study, 3 ML approaches, namely, LASSO, support vector machine (SVM) recursive feature elimination and random forest, were adopted for screening feature variables. Subsequently, to acquire the prediction model, the intersection was selected. Finally, differences among 148 cases with HLA-B27 positivity and negativity suffering from ankylosing spondylitis (AS) were investigated.

RESULTS

Six factors, namely red blood cell count, human major compatibility complex, mean platelet volume, albumin/globulin ratio (ALB/GLB), prealbumin, and bicarbonate radical, were chosen with the aim of constructing the diagnostic nomogram using ML methods. For training queue, nomogram curve exhibited the value of area under the curve (AUC) of 0.8254496, and C-value of the model was 0.825. Moreover, nomogram C-value of the validation queue was 0.853, and the AUC value was 0.852675. Furthermore, a significant decrease in the ALB/GLB was noted among cases with HLA-B27 positivity and AS cases.

CONCLUSION

To conclude, the proposed ML model can effectively predict HLA-B27 and help doctors in the diagnosis of various immune diseases.

Deep convolutional neural network for rib fracture recognition on chest radiographs

Introduction

Rib fractures are a prevalent injury among trauma patients, and accurate and timely diagnosis is crucial to mitigate associated risks. Unfortunately, missed rib fractures are common, leading to heightened morbidity and mortality rates. While more sensitive imaging modalities exist, their practicality is limited due to cost and radiation exposure. Point of care ultrasound offers an alternative but has drawbacks in terms of procedural time and operator expertise. Therefore, this study aims to explore the potential of deep convolutional neural networks (DCNNs) in identifying rib fractures on chest radiographs.

Methods

We assembled a comprehensive retrospective dataset of chest radiographs with formal image reports documenting rib fractures from a single medical center over the last five years. The DCNN models were trained using 2000 region-of-interest (ROI) slices for each category, which included fractured ribs, non-fractured ribs, and background regions. To optimize training of the deep learning models (DLMs), the images were segmented into pixel dimensions of 128 × 128.

Results

The trained DCNN models demonstrated remarkable validation accuracies. Specifically, AlexNet achieved 92.6%, GoogLeNet achieved 92.2%, EfficientNetb3 achieved 92.3%, DenseNet201 achieved 92.4%, and MobileNetV2 achieved 91.2%.

Discussion

By integrating DCNN models capable of rib fracture recognition into clinical decision support systems, the incidence of missed rib fracture diagnoses can be significantly reduced, resulting in tangible decreases in morbidity and mortality rates among trauma patients. This innovative approach holds the potential to revolutionize the diagnosis and treatment of chest trauma, ultimately leading to improved clinical outcomes for individuals affected by these injuries. The utilization of DCNNs in rib fracture detection on chest radiographs addresses the limitations of other imaging modalities, offering a promising and practical solution to improve patient care and management.

A degradome-based prognostic signature that correlates with immune infiltration and tumor mutation burden in breast cancer

Introduction

Female breast cancer is the most common malignancy worldwide, with a high disease burden. The degradome is the most abundant class of cellular enzymes that play an essential role in regulating cellular activity. Dysregulation of the degradome may disrupt cellular homeostasis and trigger carcinogenesis. Thus we attempted to understand the prognostic role of degradome in breast cancer by means of establishing a prognostic signature based on degradome-related genes (DRGs) and assessed its clinical utility in multiple dimensions.

Methods

A total of 625 DRGs were obtained for analysis. Transcriptome data and clinical information of patients with breast cancer from TCGA-BRCA, METABRIC and GSE96058 were collected. NetworkAnalyst and cBioPortal were also utilized for analysis. LASSO regression analysis was employed to construct the degradome signature. Investigations of the degradome signature concerning clinical association, functional characterization, mutation landscape, immune infiltration, immune checkpoint expression and drug priority were orchestrated. Cell phenotype assays including colony formation, CCK8, transwell and wound healing were conducted in MCF-7 and MDA-MB-435S breast cancer cell lines, respectively.

Results

A 10-gene signature was developed and verified as an independent prognostic predictor combined with other clinicopathological parameters in breast cancer. The prognostic nomogram based on risk score (calculated based on the degradome signature) showed favourable capability in survival prediction and advantage in clinical benefit. High risk scores were associated with a higher degree of clinicopathological events (T4 stage and HER2-positive) and mutation frequency. Regulation of toll-like receptors and several cell cycle promoting activities were upregulated in the high-risk group. PIK3CA and TP53 mutations were dominant in the low- and high-risk groups, respectively. A significantly positive correlation was observed between the risk score and tumor mutation burden. The infiltration levels of immune cells and the expressions of immune checkpoints were significantly influenced by the risk score. Additionally, the degradome signature adequately predicted the survival of patients undergoing endocrinotherapy or radiotherapy. Patients in the low-risk group may achieve complete response after the first round of chemotherapy with cyclophosphamide and docetaxel, whereas patients in the high-risk group may benefit from 5-flfluorouracil. Several regulators of the PI3K/AKT/mTOR signaling pathway and the CDK family/PARP family were identified as potential molecular targets in the low- and high-risk groups, respectively. In vitro experiments further revealed that the knockdown of ABHD12 and USP41 significantly inhibit the proliferation, invasion and migration of breast cancer cells.

Conclusion

Multidimensional evaluation verified the clinical utility of the degradome signature in predicting prognosis, risk stratification and guiding treatment for patients with breast cancer.

Establishment and Verification of a Predictive Nomogram for New Vertebral Compression Fracture Occurring after Bone Cement Injection in Middle-Aged and Elderly Patients with Vertebral Compression Fracture

OBJECTIVE

New vertebral compression fracture (NVCF) occurring after bone cement injection in middle-aged and elderly patients with vertebral compression fracture is very common. Preoperative baseline characteristics and surgical treatment parameters have been widely studied as a risk factor, but the importance of the patients' laboratory indicators has not been thoroughly explored. We aimed to explore the relationship between laboratory indicators and NVCF, and attempt to construct a clinical prediction model of NVCF together with other risk factors.

METHODS

Retrospective analysis was performed for 200 patients who underwent bone cement injection (percutaneous kyphoplasty or vertebroplasty) for vertebral compression fractures between January 2019 and January 2020. We consulted the relevant literature and collated the factors affecting the occurrence of NVCF. Feature selection of patients with NVCF was optimized using the least absolute shrinkage and selection operator regression model, which was used to conduct multivariable logistic regression analysis, to create a predictive model incorporating the selected features. The discrimination, calibration, and clinical feasibility of the predictive model were assessed using the concordance index (C-index), calibration plots, and decision curve analysis. Internal validation was performed using Bootstrap resampling verification.

RESULTS

Time from injury to surgery exceeding 7 days, low osteocalcin levels, elevated homocysteine levels, osteoporosis, mode of operation (percutaneous vertebroplasty), lack of postoperative anti-osteoporosis treatment, and poor diffusion of bone cement were independent risk factors for NVCF in middle-aged and elderly patients with vertebral compression fracture after bone cement injection. The C-index of the nomogram constructed using these seven factors was 0.895, indicating good discriminatory ability. The calibration plot showed that the model was well calibrated. Bootstrap resampling verification yielded a significant C-index of 0.866. Decision curve analysis demonstrated that the greatest clinical net benefit for predicting NVCF after bone cement injection could be achieved with a threshold of 1%-91%.

CONCLUSION

This nomogram can effectively predict NVCF incidence after bone cement injection in middle-aged and elderly patients with vertebral compression fracture, thus aiding clinical decision-making and postoperative management, promoting effective postoperative rehabilitation, and improving the quality of life.

Modification to Mirels scoring system location component improves fracture prediction for metastatic disease of the proximal femur

BACKGROUND

Correctly identifying patients at risk of femoral fracture due to metastatic bone disease remains a clinical challenge. Mirels criteria remains the most widely referenced method with the advantage of being easily calculated but it suffers from poor specificity. The purpose of this study was to develop and evaluate a modified Mirels scoring system through scoring modification of the original Mirels location component within the proximal femur.

METHODS

Computational (finite element) experiments were performed to quantify strength reduction in the proximal femur caused by simulated lytic lesions at defined locations. Virtual spherical defects representing lytic lesions were placed at 32 defined locations based on axial (4 axial positions: neck, intertrochanteric, subtrochanteric or diaphyseal) and circumferential (8 circumferential: 45-degree intervals) positions. Finite element meshes were created, material property assignment was based on CT mineral density, and femoral head/greater trochanter loading consistent with stair ascent was applied. The strength of each femur with a simulated lesion divided by the strength of the intact femur was used to calculate the Location-Based Strength Fraction (LBSF). A modified Mirels location score was next defined for each of the 32 lesion locations with an assignment of 1 (LBSF > 75%), 2 (LBSF: 51-75%), and 3 (LBSF: 0-50%). To test the new scoring system, data from 48 patients with metastatic disease to the femur, previously enrolled in a Musculoskeletal Tumor Society (MSTS) cross-sectional study was used. The lesion location was identified for each case based on axial and circumferential location from the CT images and assigned an original (2 or 3) and modified (1,2, or 3) Mirels location score. The total score for each was then calculated. Eight patients had a fracture of the femur and 40 did not over a 4-month follow-up period. Logistic regression and decision curve analysis were used to explore relationships between clinical outcome (Fracture/No Fracture) and the two Mirels scoring methods.

RESULTS

The location-based strength fraction (LBSF) was lowest for lesions in the subtrochanteric and diaphyseal regions on the lateral side of the femur; lesions in these regions would be at greatest risk of fracture. Neck lesions located at the anterior and antero-medial positions were at the lowest risk of fracture. When grouped, neck lesions had the highest LBSF (83%), followed by intertrochanteric (72%), with subtrochanteric (50%) and diaphyseal lesions (49%) having the lowest LBSF. There was a significant difference (p < 0.0001) in LBSF between each axial location, except subtrochanteric and diaphyseal which were not different from each other (p = 0.96). The area under the receiver operator characteristic (ROC) curve using logistic regression was greatest for modified Mirels Score using site specific location of the lesion (Modified Mirels-ss, AUC = 0.950), followed by a modified Mirels Score using axial location of lesion (Modified Mirels-ax, AUC = 0.941). Both were an improvement over the original Mirels score (AUC = 0.853). Decision curve analysis was used to quantify the relative risks of identifying patients that would fracture (TP, true positives) and those erroneously predicted to fracture (FP, false positives) for the original and modified Mirels scoring systems. The net benefit of the scoring system weighed the benefits (TP) and harms (FP) on the same scale. At a threshold probability of fracture of 10%, use of the modified Mirels scoring reduced the number of false positives by 17-20% compared to Mirels scoring.

CONCLUSIONS

A modified Mirels scoring system, informed by detailed analysis of the influence of lesion location, improved the ability to predict impending pathological fractures of the proximal femur for patients with metastatic bone disease. Decision curve analysis is a useful tool to weigh costs and benefits concerning fracture risk and could be combined with other patient/clinical factors that contribute to clinical decision making.

Difference between the blood samples of patients with bone and joint tuberculosis and patients with tuberculosis studied using machine learning

Background

Tuberculosis (TB) is a chronic infectious disease. Bone and joint TB is a common type of extrapulmonary TB and often occurs secondary to TB infection. In this study, we aimed to find the difference in the blood examination results of patients with bone and joint TB and patients with TB by using machine learning (ML) and establish a diagnostic model to help clinicians better diagnose the disease and allow patients to receive timely treatment.

Methods

A total of 1,667 patients were finally enrolled in the study. Patients were randomly assigned to the training and validation cohorts. The training cohort included 1,268 patients: 158 patients with bone and joint TB and 1,110 patients with TB. The validation cohort included 399 patients: 48 patients with bone and joint TB and 351 patients with TB. We used three ML methods, namely logistic regression, LASSO regression, and random forest, to screen the differential variables, obtained the most representative variables by intersection to construct the prediction model, and verified the performance of the proposed prediction model in the validation group.

Results

The results revealed a great difference in the blood examination results of patients with bone and joint TB and those with TB. Infectious markers such as hs-CRP, ESR, WBC, and NEUT were increased in patients with bone and joint TB. Patients with bone and joint TB were found to have higher liver function burden and poorer nutritional status. The factors screened using ML were PDW, LYM, AST/ALT, BUN, and Na, and the nomogram diagnostic model was constructed using these five factors. In the training cohort, the area under the curve (AUC) value of the model was 0.71182, and the C value was 0.712. In the validation cohort, the AUC value of the model was 0.6435779, and the C value was 0.644.

Conclusion

We used ML methods to screen out the blood-specific factors-PDW, LYM, AST/ALT, BUN, and Na⁺-of bone and joint TB and constructed a diagnostic model to help clinicians better diagnose the disease in the future.

A novel nomogram for adult primary perihilar cholangiocarcinoma and considerations concerning lymph node dissection

Objective

To construct a reliable nomogram available online to predict the postoperative survival of patients with perihilar cholangiocarcinoma.

Methods

Data from 1808 patients diagnosed with perihilar cholangiocarcinoma between 2004 and 2015 were extracted from the National Cancer Institute Surveillance, Epidemiology, and End Results (SEER) database. They were randomly divided into training and validation sets. The nomogram was established by machine learning and Cox model. The discriminant ability and prediction accuracy of the nomogram were evaluated by concordance index (C-index), receiver operator characteristic (ROC) curve and calibration curve. Kaplan-Meier curves show the prognostic value of the associated risk factors and classification system.

Results

Machine learning and multivariate Cox risk regression model showed that sex, age, tumor differentiation, primary tumor stage(T), lymph node metastasis(N), TNM stage, surgery, radiation, chemotherapy, lymph node dissection were associated with the prognosis of perihilar cholangiocarcinoma patients relevant factors (P < 0.05). A novel nomogram was established. The calibration plots, C-index and ROC curve for predictions of the 1-, 3-, and 5-year OS were in excellent agreement. In patients with stage T1 and N0 perihilar cholangiocarcinoma, the prognosis of ≥4 lymph nodes dissected was better than that of 1- 3 lymph nodes dissected (P < 0.01).

Conclusion

The nomogram prognostic prediction model can provide a reference for evaluating the prognosis and survival rate of patients with perihilar cholangiocarcinoma. Patients with stage T1 and N0 perihilar cholangiocarcinoma have more benefits by increasing the number of lymph node dissection.

Preoperative systemic immune‐inflammation index as a significant prognostic factor after TURBT in patients with non‐muscle‐invasive bladder cancer: A retrospective study based on propensity score matching analysis

OBJECTIVE

To investigate the association of the preoperative systemic immune-inflammation index (SII) with recurrence-free survival (RFS) after transurethral resection of the bladder tumor (TURBT) of non-muscle-invasive bladder cancer (NMIBC) using propensity score matching (PSM) analysis.

METHODS

The clinicopathological characteristics and follow-up data of NMIBC patients were collected retrospectively from two tertiary medical centers. A 1:1 PSM analysis was carried out using the nearest-neighbor method (caliper size: 0.02). Cox regression analysis was used to identify the risk factors associated with RFS.

RESULTS

A total of 416 NMIBC patients were included in this study. Before and after matching, patients with increased SII had worse RFS (p < 0.0001 and p = 0.027, respectively). Multivariate Cox analysis identified SII as an independent predictor of RFS before (HR [95% CI]: 1.789 [1.232, 2.599], p = 0.002) and after matching (HR [95% CI]: 1.646 [1.077, 2.515], p = 0.021). In the matched subgroup analysis, an elevated SII had a significant association with postoperative worse RFS in the T1 stage (p = 0.025), primary status (p = 0.049), high-grade (p = 0.0015), and multiple lesions (p = 0.043) subgroups.

CONCLUSION

SII could accurately stratify the prognosis of NMIBC patients before and after PSM analysis. An elevated SII was significantly associated with worse RFS in NMIBC patients.

A predictive nomogram for intradiscal cement leakage in percutaneous kyphoplasty for osteoporotic vertebral compression fractures combined with intravertebral cleft

BACKGROUND

For patients with osteoporotic vertebral compression fractures (OVCFs) treated with percutaneous kyphoplasty (PKP), the occurrence and risk factors of intradiscal cement leakage should be characteristic of the presence of intravertebral cleft (IVC). This study aimed to identify risk factors for intradiscal leakage in individuals with OVCFs combined with IVC treated with PKP and build a powered and well-calibrated predictive nomogram.

METHODS

This study retrospectively reviewed consecutive patients who underwent PKP at our center between January 2016 and May 2021. Patients diagnosed with OVCFs combined with IVC were identified, and the incidence of different types of bone cement leakage was recorded. Risk factors for intradiscal leakage among the demographic, perioperative baseline, and radiologic data were identified, following which a nomogram was developed and verified.

RESULTS

A total of 109 eligible patients were included, and the intradiscal leakage rate was 32.1%. Compression rate (odds ratio [OR] 0.025; 95% confidence interval [CI] 0.002-0.264; P = 0.002) and cemented vertebral body fraction (OR 44.122; 95% CI 2.790-697.740; P = 0.007) were identified as independent risk factors. A predictive nomogram with good predictive power (C-statistic = 0.786) and fitness of data (Hosmer-Lemeshow goodness-of-fit test, P = 0.092) was established to build a quantitative relationship between the risk factors and intradiscal leakage.

CONCLUSION

The incidence rate of intradiscal leakage in PKP for OVCFs combined with IVC was 32.1%. Compression rate and cemented vertebral body fraction were identified as independent risk factors. A powered and well-calibrated nomogram was established to accurately predict the probability of intradiscal leakage. Further prospective and multicenter studies are required to verify and calibrate our findings.

Establishment and Validation of a Machine Learning Prediction Model Based on Big Data for Predicting the Risk of Bone Metastasis in Renal Cell Carcinoma Patients

PURPOSE

Since the prognosis of renal cell carcinoma (RCC) patients with bone metastasis (BM) is poor, this study is aimed at using big data to build a machine learning (ML) model to predict the risk of BM in RCC patients.

METHODS

A retrospective study was conducted on 40,355 RCC patients in the SEER database from 2010 to 2017. LASSO regression and multivariate logistic regression analysis was performed to determine independent risk factors of RCC-BM. Six ML algorithm models, including LR, GBM, XGB, RF, DT, and NBC, were used to establish risk models for predicting RCC-BM. The prediction performance of ML models was weighed by 10-fold cross-validation.

RESULTS

The study investigated 40,355 patients diagnosed with RCC in the SEER database, where 1,811 (4.5%) were BM patients. Independent risk factors for BM were tumor grade, T stage, N stage, liver metastasis, lung metastasis, and brain metastasis. Among the RCC-BM risk prediction models established by six ML algorithms, the XGB model showed the best prediction performance (AUC = 0.891). Therefore, a network calculator based on the XGB model was established to individually assess the risk of BM in patients with RCC.

CONCLUSION

The XGB risk prediction model based on the ML algorithm performed a good prediction effect on BM in RCC patients.

Construction and validation of nomograms based on the log odds of positive lymph nodes to predict the prognosis of lung neuroendocrine tumors

Background

This research aimed to investigate the predictive performance of log odds of positive lymph nodes (LODDS) for the long-term prognosis of patients with node-positive lung neuroendocrine tumors (LNETs).

Methods

We collected 506 eligible patients with resected N1/N2 classification LNETs from the Surveillance, Epidemiology, and End Results (SEER) database between 2004 and 2015. The study cohort was split into derivation cohort (n=300) and external validation cohort (n=206) based on different geographic regions. Nomograms were constructed based on the derivation cohort and validated using the external validation cohort to predict the 1-, 3-, and 5-year cancer-specific survival (CSS) and overall survival (OS) of patients with LNETs. The accuracy and clinical practicability of nomograms were tested by Harrell’s concordance index (C-index), integrated discrimination improvement (IDI), net reclassification improvement (NRI), calibration plots, and decision curve analyses.

Results

The Cox proportional-hazards model showed the high LODDS group (-0.79≤LODDS) had significantly higher mortality compared to those in the low LODDS group (LODDS<-0.79) for both CSS and OS. In addition, age at diagnosis, sex, histotype, type of surgery, radiotherapy, and chemotherapy were also chosen as predictors in Cox regression analyses using stepwise Akaike information criterion method and included in the nomograms. The values of C-index, NRI, and IDI proved that the established nomograms were better than the conventional eighth edition of the TNM staging system. The calibration plots for predictions of the 1-, 3-, and 5-year CSS/OS were in excellent agreement. Decision curve analyses showed that the nomograms had value in terms of clinical application.

Conclusions

We created visualized nomograms for CSS and OS of LNET patients, facilitating clinicians to bring individually tailored risk assessment and therapy.

Construction and validation of BRAF mutation diagnostic model based on ultrasound examination and clinical features of patients with thyroid nodules

Introduction: Fine Needle Aspiration (FNA) is currently the most popular method for identifying benign and malignant thyroid nodules. However, its diagnostic sensitivity is sometimes limited, which makes it necessary to apply genetic testing and other modalities as a secondary diagnostic method. The diagnostic accuracy of thyroid nodule can be improved by combining mutations in the B-Raf proto-oncogene serine/threonine kinase (BRAF) with FNA. Thus, this study was conducted to create a nomogram diagnostic model based on the clinical and ultrasonic characteristics of patients with BRAF mutations to aid in the identification of benign and malignant thyroid nodules using FNA.

Methods: From April 2018 to December 2021, 275 patients with thyroid nodules who underwent ultrasonography and BRAF gene testing (137 positive and 138 negative) were included from Xianyang Central Hospital. The clinical and ultrasonic characteristics of the patients were used to develop a nomographic, diagnostic model of BRAF gene mutation, and to validate and evaluate the usefulness of the model.

Results: Independent risk factors for BRAF mutations included: focal strong echogenicity (microcalcifications, OR = 3.04, 95%CI = 1.41–6.58, p = 0.005), hypoechogenicity (OR = 3.8, 95%CI = 1.14–12.61, p = 0.029), lymph node metastases (OR = 3.54, 95%CI = 1.43–8.75, p = 0.006), margin (lobulated, OR = 3.7, 95%CI = 1.66–8.23, p = 0.001; extrathyroidal invasion, OR = 2.81, 95%CI = 1.11–7.06, p = 0.029), and shape (vertical position, OR = 2.7, 95%CI = 1.11–6.59, p = 0.029). The area under the curve (AUC) of the receiver operating characteristic (ROC) curve of the BRAF mutation diagnostic model constructed on these factors was 0.806 (95% CI = 0.754–0.851), and 39.5% was set as the threshold probability of making a clinical decision. The results of the validation and clinical utility evaluation showed that our model had good predictive performance and clinical application value.

Conclusion: Our nomogram diagnostic model based on clinical and ultrasound features of patients accurately predicted the possibility of BRAF gene mutations in patients with thyroid nodules.

Development and validation of a carotid atherosclerosis risk prediction model based on a Chinese population

Purpose

This study aimed to identify independent risk factors for carotid atherosclerosis (CAS) and construct and validate a CAS risk prediction model based on the Chinese population.

Methods

This retrospective study included 4,570 Chinese adults who underwent health checkups (including carotid ultrasound) at the Zhenhai Lianhua Hospital, Ningbo, China, in 2020. All the participants were randomly assigned to the training and validation sets at a ratio of 7:3. Independent risk factors associated with CAS were identified using multivariate logistic regression analysis. The least absolute shrinkage and selection operator combined with 10-fold cross-validation were screened for characteristic variables, and nomograms were plotted to demonstrate the risk prediction model. C-index and receiver operating characteristic curves, calibration plots, and decision curve analysis (DCA) were used to evaluate the risk model’s discrimination, calibration, and clinical applicability.

Results

Age, body mass index, diastolic blood pressure, white blood cell count, mean platelet volume, alanine transaminase, aspartate transaminase, and gamma-glutamyl transferase were identified as independent risk factors for CAS. In the training, internal validation, and external validation sets, the risk model showed good discriminatory power with C-indices of 0.961 (0.953–0.969), 0.953 (0.939–0.967), and 0.930 (0.920–0.940), respectively, and excellent calibration. The results of DCA showed that the prediction model could be beneficial when the risk threshold probabilities were 1–100% in all sets. Finally, a network computer (dynamic nomogram) was developed to facilitate the physicians’ clinical operations. The website is https://nbuhgq.shinyapps.io/DynNomapp/.

Conclusion

The development of risk models contributes to the early identification and prevention of CAS, which is important for preventing and reducing adverse cardiovascular and cerebrovascular events.

Assessment of clinical, imaging, surgical risk factors for subsequent fracture following vertebral augmentation in osteoporotic patients

INTRODUCTION

Currently, the risk factors for subsequent fracture following vertebral augmentation remain incomplete and controversial. To provide clinicians with accurate information for developing a preventive strategy, we carried out a comprehensive evaluation of previously controversial and unexplored risk factors.

METHODS

We retrospectively reviewed patients with osteoporotic vertebral compression fracture in lumbar spine who received vertebral augmentation between January 2019 and December 2020. Based on whether refracture occurred, patients were assigned to refracture and non-refracture group. The clinical characteristics, imaging parameters (severity of vertebral compression, spinal sagittal alignment, degeneration of paraspinal muscles), and surgical indicators (cement distribution and leakage, correction of spinal sagittal alignment) were collected and analyzed.

RESULTS

There were 128 patients and 16 patients in non-refracture and refracture group. The incidence of previous fracture, multiple fractures, and cement leakage were notably higher, relative cross-sectional area of psoas (r-CSA_PS) was significantly smaller, CSA ratio, fatty infiltration of erector spinae plus multifidus (FI_ES+MF), FI_PS, postoperative lumbar lordosis (post-LL), correction of body angel (BA), and LL were significantly greater in refracture group. Binary logistic regression analysis revealed previous fracture, cement leakage, post-LL, and correction of BA were independent risk factors. According to the ROC curve, correction of BA showed the highest prediction accuracy, and the critical value was 3.45°.

CONCLUSIONS

The occurrence of subsequent fracture might be the consequence of multiple factors. Previous fracture, cement leakage, post-LL, and correction of BA were identified as independent risk factors. Furthermore, the correction of BA should not exceed 3.45°, especially in patients with risk factors.

Web-Based Prediction Models for Overall Survival and Cancer-Specific Survival of Patients With Primary Urachal Carcinoma: A Study Based on SEER Database

Objective:

We aimed to establish nomograms to predict the overall survival (OS) and cancer-specific survival (CSS) of patients with primary urachal carcinoma (UrC).

Methods

Information on patients diagnosed with UrC from 1975 to 2018 was collected from the Surveillance, Epidemiology, and End Results (SEER) Program Research Data. The independent prognostic factors were determined using univariate and multivariate Cox regression. Backward variable elimination according to the Akaike information criterion (AIC) identified the most accurate and parsimonious model. Nomograms were built based on regression coefficients. The C-index, calibration plot, Brier score, integrated discrimination improvement (IDI), area under the receiver operating curve (AUC), and decision curve analysis (DCA) curve were used to evaluate the efficiency of models.

Results

In total, 236 patients obtained from SEER were divided randomly into training and validation cohorts in a 70:30 ratio (166 and 70 patients, respectively). In the training cohort, multivariate Cox regression analysis indicated that pTNM/Sheldon/Mayo staging systems (included respectively), age, and tumor grade were independent prognostic factors for OS. A similar result was also found in CSS. While other variables, such as radiotherapy and chemotherapy, did not identify significant correlations. In predicting OS and CSS at 3- and 5- years, the nomograms based on pTNM showed superior discriminative and calibration capabilities in comparison to multiple statistical tools. The C-index values for the training cohort were 0.770 for OS and 0.806 for CSS, and similar outcomes were shown in further internal validation (C-index 0.693 for OS and 0.719 for CSS). We also discovered that the link between age at diagnosis and survival follows a U-shaped curve, indicating that the risk of poor prognosis decreases first and then increases with age.

Conclusion

The efficacy of pTNM in predicting the prognosis of patients with UrC was greater than that of the Sheldon and Mayo staging system. Therefore, we recommend pTNM as the preferred system to stage UrC. The novel constructed nomograms based on pTNM, age, and tumor grade showed high accuracy and specificity and could be applied clinically to predict the prognosis of patients with UrC.

A Visualized Dynamic Prediction Model for Lymphatic Metastasis in Ewing's Sarcoma for Smart Medical Services

Background

This study aims to predict the lymphatic metastasis in Ewing's sarcoma (ES) patients by nomogram. The risk of lymphatic metastasis in patients with ES was predicted by the built model, which provided guidance for the clinical diagnosis and treatment planning.

Methods

A total of 929 patients diagnosed with ES were enrolled from the year of 2010 to 2016 in the Surveillance, Epidemiology, and End Results (SEER) database. The nomogram was established to determine predictive factors of lymphatic metastasis according to univariate and multivariate logistic regression analysis. The validation of the model performed using multicenter data (n = 51). Receiver operating characteristics (ROC) curves and calibration plots were used to evaluate the prediction accuracy of the nomogram. Decision curve analysis (DCA) was implemented to illustrate the practicability of the nomogram clinical application. Based on the nomogram, we established a web calculator to visualize the risk of lymphatic metastases. We further plotted Kaplan-Meier overall survival (OS) curves to compare the survival time of patients with and without lymphatic metastasis.

Results

In this study, the nomogram was established based on six significant factors (survival time, race, T stage, M stage, surgery, and lung metastasis), which were identified for lymphatic metastasis in ES patients. The model showed significant diagnostic accuracy with the value of the area under the curve (AUC) was 0.743 (95%CI: 0.714–0.771) for SEER internal validation and 0.763 (95%CI: 0.623–0.871) for multicenter data external validation. The calibration plot and DCA indicated that the model had vital clinical application value.

Conclusion

In this study, we constructed and developed a nomogram with risk factors to predict lymphatic metastasis in ES patients and validated accuracy of itself. We found T stage (Tx OR = 2.540, 95%CI = 1.433–4.503, P < 0.01), M stage (M1, OR = 2.061, 95%CI = 1.189–3.573, P < 0.05) and survival time (OR = 0.982, 95%CI = 0.972–0.992, P < 0.001) were important independent factors for lymphatic metastasis in ES patients. Furthermore, survival time in patients with lymphatic metastasis or unclear situation (P < 0.0001) was significantly lower. It can help clinicians make better decisions to provide more accurate prognosis and treatment for ES patients.

An External-Validated Prediction Model to Predict Lung Metastasis among Osteosarcoma: A Multicenter Analysis Based on Machine Learning

BACKGROUND

Lung metastasis greatly affects medical therapeutic strategies in osteosarcoma. This study aimed to develop and validate a clinical prediction model to predict the risk of lung metastasis among osteosarcoma patients based on machine learning (ML) algorithms.

METHODS

We retrospectively collected osteosarcoma patients from the Surveillance Epidemiology and End Results (SEER) database and from four hospitals in China. Six ML algorithms, including logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), random forest (RF), decision tree (DT), and multilayer perceptron (MLP), were applied to build predictive models for predicting lung metastasis using patient's demographics, clinical characteristics, and therapeutic variables from the SEER database. The model was internally validated using 10-fold cross-validation to calculate the mean area under the curve (AUC) and the model was externally validated using the Chinese multicenter osteosarcoma data. Relative importance ranking of predictors was plotted to understand the importance of each predictor in different ML algorithms. The correlation heat map of predictors was plotted to understand the correlation of each predictor, selecting the 10-fold cross-validation with the highest AUC value in the external validation ROC curve to build a web calculator.

RESULTS

Of all enrolled patients from the SEER database, 17.73% (194/1094) developed lung metastasis. The multiple logistic regression analysis showed that sex, N stage, T stage, surgery, and bone metastasis were all independent risk factors for lung metastasis. In predicting lung metastasis, the mean AUCs of the six ML algorithms ranged from 0.711 to 0.738 in internal validation and 0.697 to 0.729 in external validation. Among the six ML algorithms, the extreme gradient boosting (XGBoost) model had the highest AUC value with an average internal AUC of 0.738 and an external AUC of 0.729. The best performing ML algorithm model was used to build a web calculator to facilitate clinicians to calculate the risk of lung metastasis for each patient.

CONCLUSIONS

The XGBoost model may have the best prediction effect and the online calculator based on this model can help doctors to determine the lung metastasis risk of osteosarcoma patients and help to make individualized medical strategies.

Development and Internal Validation of Supervised Machine Learning Algorithm for Predicting the Risk of Recollapse Following Minimally Invasive Kyphoplasty in Osteoporotic Vertebral Compression Fractures

Background

The published literatures indicate that patients with osteoporotic vertebral compression fractures (OVCFs) benefit significantly from percutaneous kyphoplasty (PKP), but this surgical technique is associated with frequent postoperative recollapse, a complication that severely limits long-term postoperative functional recovery.

Methods

This study retrospectively analyzed single-segment OVCF patients who underwent bilateral PKP at our academic center from January 1, 2017 to September 30, 2019. Comparing the plain films of patients within 3 days after surgery and at the final follow-up, we classified patients with more than 10% loss of sagittal anterior height as the recollapse group. Univariate and multivariate logistic regression analyses were performed to determine the risk factors affecting recollapse after PKP. Based on the logistic regression results, we constructed one support vector machine (SVM) classifier to predict recollapse using machine learning (ML) algorithm. The predictive performance of this prediction model was validated by the receiver operating characteristic (ROC) curve, 10-fold cross validation, and confusion matrix.

Results

Among the 346 consecutive patients (346 vertebral bodies in total), postoperative recollapse was observed in 40 patients (11.56%). The results of the multivariate logistical regression analysis showed that high body mass index (BMI) (Odds ratio [OR]: 2.08, 95% confidence interval [CI]: 1.58–2.72, p < 0.001), low bone mineral density (BMD) T-scores (OR: 4.27, 95% CI: 1.55–11.75, p = 0.005), presence of intravertebral vacuum cleft (IVC) (OR: 3.10, 95% CI: 1.21–7.99, p = 0.019), separated cement masses (OR: 3.10, 95% CI: 1.21–7.99, p = 0.019), cranial endplate or anterior cortical wall violation (OR: 0.17, 95% CI: 0.04–0.79, p = 0.024), cement-contacted upper endplate alone (OR: 4.39, 95% CI: 1.20–16.08, p = 0.025), and thoracolumbar fracture (OR: 6.17, 95% CI: 1.04–36.71, p = 0.045) were identified as independent risk factors for recollapse after a kyphoplasty surgery. Furthermore, the evaluation indices demonstrated a superior predictive performance of the constructed SVM model, including mean area under receiver operating characteristic curve (AUC) of 0.81, maximum AUC of 0.85, accuracy of 0.81, precision of 0.89, and sensitivity of 0.98.

Conclusions

For patients with OVCFs, the risk factors leading to postoperative recollapse were multidimensional. The predictive model we constructed provided insights into treatment strategies targeting secondary recollapse prevention.

ISSLS PRIZE in Clinical Science 2022: Epidemiology, risk factors and clinical impact of juvenile Modic changes in paediatric patients with low back pain

PURPOSE

It's a long-held belief that Modic changes (MC) occur only in adults, with advanced age, and are highly associated with pain and adverse outcomes. The following study addressed the epidemiology, risk factors and clinical relevance of MC in young paediatric patients.

METHODS

Two hundred and seven consecutive patients with no history of deformities, neoplasms, trauma, or infections were included in this ambispective study. MRIs were utilized to assess MCs and types, and other degenerative disc/endplate abnormalities. Subject demographics, duration of symptoms, clinic visits, conservative management (physical therapy, NSAIDs, opioids, injections) and surgery were noted.

RESULTS

The mean age was 16.5 years old (46.9% males), 14% had MCs and they occurred throughout the spine. Subject baseline demographics were similar between MCs and non-MCs patients (p > 0.05). Modic type 2 (50%) was the most common type (type 1:27.1%; type 3:18.8%; mixed:4.7%). Multivariate analyses noted that endplate damage (OR: 11.36), disc degeneration (OR: 5.81), disc space narrowing (OR: 5.77), Schmorl's nodes (OR: 4.30) and spondylolisthesis (OR: 3.55) to be significantly associated with MCs (p < 0.05). No significant differences in conservative management were noted between Modic and non-MCs patients (p > 0.05). Among surgery patients (n = 44), 21% also had MCs (p = 0.134). Symptom-duration was significantly greater in MC patients (p = 0.049).

CONCLUSION

Contrary to traditional dogma, robust evidence now exists noting that MCs and their types can develop in children. Our findings give credence to the "Juvenile" variant of MCs, whereby its implications throughout the lifespan need to be assessed. Juvenile MCs have prolonged symptoms and related to specific structural spine phenotypes.

A Machine Learning-Based Predictive Model for Predicting Lymph Node Metastasis in Patients With Ewing's Sarcoma

Objective

In order to provide reference for clinicians and bring convenience to clinical work, we seeked to develop and validate a risk prediction model for lymph node metastasis (LNM) of Ewing’s sarcoma (ES) based on machine learning (ML) algorithms.

Methods

Clinicopathological data of 923 ES patients from the Surveillance, Epidemiology, and End Results (SEER) database and 51 ES patients from multi-center external validation set were retrospectively collected. We applied ML algorithms to establish a risk prediction model. Model performance was checked using 10-fold cross-validation in the training set and receiver operating characteristic (ROC) curve analysis in external validation set. After determining the best model, a web-based calculator was made to promote the clinical application.

Results

LNM was confirmed or unable to evaluate in 13.86% (135 out of 974) ES patients. In multivariate logistic regression, race, T stage, M stage and lung metastases were independent predictors for LNM in ES. Six prediction models were established using random forest (RF), naive Bayes classifier (NBC), decision tree (DT), xgboost (XGB), gradient boosting machine (GBM), logistic regression (LR). In 10-fold cross-validation, the average area under curve (AUC) ranked from 0.705 to 0.764. In ROC curve analysis, AUC ranged from 0.612 to 0.727. The performance of the RF model ranked best. Accordingly, a web-based calculator was developed (https://share.streamlit.io/liuwencai2/es_lnm/main/es_lnm.py).

Conclusion

With the help of clinicopathological data, clinicians can better identify LNM in ES patients. Risk prediction models established in this study performed well, especially the RF model.

Association of spinal anomalies with spondylolysis and spina bifida occulta

PURPOSE

To investigate the association of spinal anomalies with lumbar spondylolysis and spina bifida occulta (SBO).

METHODS

A total of 1190 patients with thoracic, abdominal, and pelvic computed tomography scans available were categorized according to the number of presacral (thoracic and lumbar) mobile vertebrae and the presence or absence of lumbosacral transitional vertebrae (LSTV). The prevalence of spondylolysis and SBO and the association of spinal anomalies with these disorders were evaluated.

RESULTS

Normal morphology (17 mobile vertebra with no LSTV) was found in 607 men (86.5%) and 419 women (85.9%) and about 14% of patients had anomalies. Spondylolysis was found in 74 patients (6.2%), comprising 54 men (7.7%) and 20 women (4.1%). SBO involving the lumbar spine was found in 9 men (1.3%) and 2 women (0.4%). Spondylolysis was significantly more common in men with 18 vertebrae without LSTV (21.1%) than in those with 17 vertebrae without LSTV (7.2%) (p = 0.002). The prevalence of spinal anomalies was 55.6% in men and 50.0% in women with SBO that included a lumbar level was significantly higher than in both men (13.5%, p < 0.001) and women (4.8%, p = 0.003) without SBO.

CONCLUSION

These findings indicate that there is a relationship between spinal anomalies and both spondylolysis and SBO, which may lead to elucidation of the mechanism of onset of spondylolysis and improve its treatment and prognosis. Awareness that patients with SBO involving the lumbar spine have an increased likelihood of a spinal anomaly may help to prevent level errors during spinal surgery.

Risk factors of vertebral re-fracture after PVP or PKP for osteoporotic vertebral compression fractures, especially in Eastern Asia: a systematic review and meta-analysis

Objective

Percutaneous vertebroplasty (PVP) and kyphoplasty (PKP) have been widely used to treat osteoporotic vertebral compression fractures (OVCF), but the risk of vertebral re-fracture after PVP/PKP remains controversial. This study aims to investigate the incidence and risk factors of vertebral re-fracture after PVP/PKP.

Methods

Relevant literatures published up to November 2021 were collected from PubMed, Embase and Web of Science. A meta-analysis was performed to extract data associated with risk factors of SVCF following the PRISMA guidelines. Also, pooled odds ratio (OR) or weighted mean difference (WMD) with 95% confidence interval (CI) was calculated.

Results

A total of 23 studies, encompassing 9372 patients with OVCF, met the inclusion criteria. 1255 patients (13.39%) suffered re-fracture after PVP/PKP surgery. A total of 22 studies were from Eastern Asia and only 1 study was from Europe. Female sex (OR = 1.34, 95%CI 1.09–1.64, P = 0.006), older age (WMD = 2.04, 95%CI 0.84–3.24, P = 0.001), lower bone mineral density (BMD, WMD = − 0.38, 95%CI − 0.49–0.26, P < 0.001) and bone cement leakages (OR = 2.05, 95% CI 1.40–3.00, P < 0.001) increased the risk of SVCF. The results of subgroup analysis showed the occurrence of re-fracture was significantly associated with gender (P = 0.002), age (P = 0.001) and BMD (P < 0.001) in Eastern Asia. Compared with the unfractured group, anterior-to-posterior vertebral body height ratio (AP ratio, WMD = 0.06, 95%CI 0.00–0.12, P = 0.037) and visual analog scale score (VAS, WMD = 0.62, 95%CI 0.09–1.15, P = 0.022) were higher in the refracture group, and kyphotic angle correction ratio (Cobb ratio, WMD = − 0.72, 95%CI − 1.26–0.18, P = 0.008) was smaller in Eastern Asia. In addition, anti-osteoporosis treatment (OR = 0.40, 95% CI 0.27–0.60, P < 0.001) could be a protective factor.

Conclusion

The main factors associated with re-fracture after PVP/PKP are sex, age, bone mineral density, AP ratio, Cobb ratio, VAS score, bone cement leakage and anti-osteoporosis treatment, especially in Eastern Asia.

Risk factors of new vertebral compression fracture after percutaneous vertebroplasty or percutaneous kyphoplasty

BACKGROUND

New vertebral compression fracture (VCF) may occur in patients who underwent percutaneous vertebroplasty (PVP) or percutaneous kyphoplasty (PKP) for osteoporotic vertebral compression fracture (OVCF). However, the risk factors of new VCF remain controversial. The research aimed to analyze the risk factors of new VCF after PVP or PKP.

METHODS

From August 2019 to March 2021, we retrospectively analyzed the patients who underwent PVP or PKP for OVCF at our institution. Age, gender, body mass index (BMI), smoking, drinking, hypertension, diabetes, fracture location, surgical method, Hounsfield unit (HU) value, preoperative degree of anterior vertebral compression (DAVC), bisphosphonates, bone cement volume, bone cement leakage, and cement distribution were collected. The risk factors were obtained by univariate and multivariate analysis of the data.

RESULTS

A total of 247 patients were included in the study. There were 23 patients (9.3%) with new VCF after PVP or PKP. Univariate analysis showed that age (p < 0.001), BMI (p = 0.002), fracture location (p = 0.030), and a low HU value (p < 0.001) were significantly associated with new VCF after PVP or PKP. A low HU value was an independent risk factor for new VCF after PVP or PKP obtained by multivariate regression analysis (OR = 0.963; 95% CI, 0.943-0.984, p = 0.001).

CONCLUSIONS

In this study, a low HU value was an independent risk factor of new VCF after PVP or PKP.

Machine Learning Applications for the Prediction of Bone Cement Leakage in Percutaneous Vertebroplasty

Background: Bone cement leakage is a common complication of percutaneous vertebroplasty and it could be life-threatening to some extent. The aim of this study was to develop a machine learning model for predicting the risk of cement leakage in patients with osteoporotic vertebral compression fractures undergoing percutaneous vertebroplasty. Furthermore, we developed an online calculator for clinical application. Methods: This was a retrospective study including 385 patients, who had osteoporotic vertebral compression fracture disease and underwent surgery at the Department of Spine Surgery, Liuzhou People's Hospital from June 2016 to June 2018. Combing the patient's clinical characteristics variables, we applied six machine learning (ML) algorithms to develop the predictive models, including logistic regression (LR), Gradient boosting machine (GBM), Extreme gradient boosting (XGB), Random Forest (RF), Decision Tree (DT) and Multilayer perceptron (MLP), which could predict the risk of bone cement leakage. We tested the results with ten-fold cross-validation, which calculated the Area Under Curve (AUC) of the six models and selected the model with the highest AUC as the excellent performing model to build the web calculator. Results: The results showed that Injection volume of bone cement, Surgery time and Multiple vertebral fracture were all independent predictors of bone cement leakage by using multivariate logistic regression analysis in the 385 observation subjects. Furthermore, Heatmap revealed the relative proportions of the 15 clinical variables. In bone cement leakage prediction, the AUC of the six ML algorithms ranged from 0.633 to 0.898, while the RF model had an AUC of 0.898 and was used as the best performing ML Web calculator (https://share.streamlit.io/liuwencai0/pvp_leakage/main/pvp_leakage) was developed to estimate the risk of bone cement leakage that each patient undergoing vertebroplasty. Conclusion: It achieved a good prediction for the occurrence of bone cement leakage with our ML model. The Web calculator concluded based on RF model can help orthopedist to make more individual and rational clinical strategies.