Risk Factors for Hidden Blood Loss Associated with Vertebroplasty or Kyphoplasty for Osteoporotic Vertebral Compression Fracture: A Systematic Review and Meta-Analysis

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.

Efficacy of lumbar and abdominal muscle rehabilitation training on degree of osteoporosis, pain and anxiety in elderly patients with osteoporotic vertebral compression fracture after PKP and compliance analysis

Purpose

To explore the rehabilitation effect and compliance of lumbar and abdominal muscle rehabilitation training in patients with osteoporotic vertebral compression fracture (OVCF) after percutaneous balloon vertebroplasty (PKP).

Methods

A total 177 elderly patients with OVCF were divided into rehabilitation group (n = 104) and control group (n = 73) according to whether they received psoas and abdominal muscle rehabilitation training for 3 months after PKP. The differences of general data, orthopaedic rehabilitation, prognosis and bone metabolism were compared between the two groups. All the patients were divided into compliance group (68 cases) and non-compliance group (36 cases) according to compliance. Orthopaedic rehabilitation indicators, prognostic indicators of PKP, and bone metabolism-related parameters were collected for analysis of Chi-square test and Logistic regression. ROC curve was used to analyze the predictive value of bone metabolism related indicators in the compliance of lumbar and abdominal muscle rehabilitation training.

Results

There was no significant difference in the general data between the rehabilitation training group and the control group (All p > 0.05). Compared with the control group, the Berg balance scale score was significantly increased, while the Visual Analogue Scale (VAS) score, Oswestry Disability Index (ODI) score and the proportion of new fractures were significantly decreased in the rehabilitation training group (All p < 0.05). Compared with the control group, the bone mineral density (BMD) T value, osteocalcin (OCN) and 25-hydroxyvitamin D (25 (OH) D) levels were significantly increased and the levels of type I N-propeptide (P1NP) and β-isomerized C-terminal telopeptides (β-CTX) were significantly decreased in the rehabilitation training group compared with the control group (All p < 0.05). Chi-square test and Logistic regression analysis showed that age > 75 years, severe anxiety, severe pain and postoperative complications were significantly associated with the compliance of psoas and abdominal muscle rehabilitation training in patients with OVCF after PKP. ROC curve analysis showed that BMD T value, OCN, P1NP, β-CTX, or 25-OH-D levels predicted the AUC of rehabilitation training compliance in patients with OVCF after PKP were 0.821, 0.835, 0.736, 0.715, and 0.748, respectively.

Conclusion

Rehabilitation training of lumbar and abdominal muscles can significantly improve the efficacy of PKP, reduce the degree of osteoporosis and improve the prognosis of patients with OVCF. Age, anxiety, pain and postoperative complications were independent risk factors affecting the compliance of psoas and abdominal rehabilitation training in patients with OVCF after PKP.

The Use of Spiral Cement Injector for Percutaneous Vertebroplasty to Treat Kümmell Disease: A Retrospective Study

BACKGROUND

Percutaneous vertebroplasty (PVP) is a common method used to treat Kümmell disease. In patients without neurologic symptoms, we sought to evaluate whether using the new spiral injectors instead of the traditional push-rod injectors in PVP can result in improved clinical efficacy for the treatment of Kümmell disease.

METHODS

A clinical retrospective study was conducted between August 2018 and December 2020. The study included patients diagnosed with single-level thoracolumbar Kümmell disease who underwent PVP surgery. The patients were divided into 2 groups: an observation group consisting of 53 patients treated with spiral injectors and a control group consisting of 68 patients treated with push-rod injectors.

RESULTS

A 2-year follow-up period was adopted. The bone cement injection volume and occurrence of bone cement leakage were significantly greater in the observation group compared with the control group (P < 0.05). The observation group had significantly shorter operation time and intraoperative fluoroscopy times compared with the control group (P < 0.05). The scores for the visual analog scale and Oswestry Disability Index in both groups were significantly lower at 3 days or 3 months and 2 years after surgery compared with before surgery, with the scores at 2 years after surgery being significantly lower than those at 3 days or 3 months for both groups (P < 0.05). The relative anterior ledge height and Cobb angle showed significant improvement at 3 days and 2 years after surgery compared with before surgery in both groups (P < 0.05), but patients in the observation group experienced substantial improvement at 3 days and 2 years after surgery compared with those in the control group (P < 0.05). In both groups, the relative anterior ledge height was noticeably lower 2 years after surgery compared with 3 days after surgery (P < 0.05). Concurrently, there was a significant increase in the local Cobb angle over time in both groups (P < 0.05).

CONCLUSIONS

The implementation of both spiral injectors and traditional push-rod injectors in PVP surgery yields effective pain relief, improved function, partially restored vertebral height, and corrected kyphosis in treating Kümmell disease. Compared with the push-rod injector, the spiral injector is highly efficient in restoring vertebral height, correcting kyphosis, and minimizing fluoroscopy use and operation time, but it carries a greater risk of bone cement leakage.