Machine-learning-based approach for nonunion prediction following osteoporotic vertebral fractures

Artificial Intelligence in Spine Surgery: Imaging-Based Applications for Diagnosis and Surgical Techniques

PURPOSE OF REVIEW

Artificial intelligence (AI) has rapidly proliferated though medicine with many novel applications to improve patient care and optimize healthcare delivery. This review investigates recent literature surrounding the influence of AI imaging technologies on spine surgical practice and diagnosis.

RECENT FINDINGS

Robotic-assisted pedicle screw placement has been shown to increase the rate of clinically acceptable screw placement while increasing operative time. AI technologies have also shown promise in creating 3D spine imaging while reducing patient radiation exposure. Several models using various imaging modalities have been shown to reliably identify vertebral osteoporotic fractures, stenosis and spine cancers. Complex spinal anatomy and pathology as well as integration of robotics make spine surgery a promising field for the deployment of AI-based imaging technologies. Imaging-based AI projects show potential to enhance diagnostic and surgical efficiency, facilitate trainee learning and improve operative outcomes.

Deep Learning in Scaphoid Nonunion Treatment

Background/Objectives: Scaphoid fractures are notorious for a high rate of nonunion, resulting in chronic pain and impaired wrist function. The decision for surgical intervention often involves extensive imaging and prolonged conservative management, leading to delays in definitive treatment. The effectiveness of such treatment remains a subject of ongoing clinical debate, with no universally accepted predictive tool for surgical success. The objective of this study was to train a deep learning algorithm to reliably identify cases of nonunion with a high probability of subsequent union following operative revision. Methods: This study utilized a comprehensive database of 346 patients diagnosed with scaphoid nonunions, with preoperative and postoperative X-rays available for analysis. A classical logistic regression for clinical parameters was used, as well as a TensorFlow deep learning algorithm on X-rays. The latter was developed and applied to these imaging datasets to predict the likelihood of surgical success based solely on the preoperative anteroposterior (AP) X-ray view. The model was trained and validated over six epochs to optimize its predictive accuracy. Results: The logistic regression yielded an accuracy of 66.3% in predicting the surgical outcome based on patient parameters. The deep learning model demonstrated remarkable predictive accuracy, achieving a success rate of 93.6%, suggesting its potential as a reliable tool for guiding clinical decision-making in scaphoid nonunion management. Conclusions: The findings of this study indicate that the preoperative AP X-ray of a scaphoid nonunion provides sufficient information to predict the likelihood of surgical success when analyzed using our deep learning model. This approach has the potential to streamline decision-making and reduce reliance on extensive imaging and prolonged conservative treatment.

Machine learning can predict surgical indication: new clustering model from a large adult spine deformity database

PURPOSE

The choice of the best management for Adult Spine Deformity (ASD) is challenging. Health-related quality of life (HRQoL), comorbidities, symptoms and spine geometry, along with surgical risk and potential residual disability play a role, and a definite algorithm for patient management is lacking. Machine learning allows to analyse complex settings more efficiently than other available statistical tools. Aim of this study was to develop a machine-learning algorithm that, based on baseline data, would be able to predict whether an ASD patient would undergo surgery or not.

METHODS

Retrospective evaluation of prospectively collected data. Demographic data, HRQoL and radiographic parameters were collected. Two clustering methods were performed to differentiate groups of patients with similar characteristics. Three models were then used to identify the most relevant variables for management prediction.

RESULTS

Data from 1319 patients were available. Three clusters were identified: older subjects with sagittal imbalance and high PI, younger patients with greater coronal deformity and no sagittal imbalance, older patients with moderate sagittal imbalance and lower PI. The group of younger patients showed the highest error rate for the prediction (37%), which was lower for the other two groups (20-27%). For all groups, quality of life parameters such as the ODI and the SRS 22 and the Cobb angle of the major curve were the strongest predictors of surgical indication, albeit with different odds ratios in each group.

CONCLUSION

Three clusters could be identified along with the variables that, in each, are most likely to drive the choice of management.

Predictive Model Development to Identify Failed Healing in Patients after Non-Union Fracture Surgery

Bone non-union is among the most severe complications associated with trauma surgery, occurring in 10-30 % of cases after long bone fractures. Treating non-unions requires a high level of surgical expertise and often involves multiple revision surgeries, sometimes even leading to amputation. Thus, more accurate prognosis is crucial for patient well-being.Recent advances in machine learning (ML) hold promise for developing models to predict non-union healing, even when working with smaller datasets, a commonly encountered challenge in clinical domains. To demonstrate the effectiveness of ML in identifying candidates at risk of failed non-union healing, we applied three ML models-logistic regression, support vector machine, and XGBoost-to the clinical dataset TRUFFLE, which includes 797 patients with long bone non-union.The models provided prediction results with 70% sensitivity, and the specificities of 66 % (XGBoost), 49 % (support vector machine), and 43 % (logistic regression). These findings offer valuable clinical insights because they enable early identification of patients at risk of failed non-union healing after the initial surgical revision treatment protocol.

Assessment of Hidden Blood Loss in Spinal Metastasis Surgery: A Comprehensive Approach with MRI-Based Radiomics Models

BACKGROUND

Patients undergoing surgery for spinal metastasis are predisposed to hidden blood loss (HBL), which is associated with poor surgical outcomes but unpredictable.

PURPOSE

To evaluate the role of MRI-based radiomics models for assess the risk of HBL in patients undergoing spinal metastasis surgery.

STUDY TYPE

Retrospective.

SUBJECTS

202 patients (42.6% female) operated on for spinal metastasis with a mean age of 58 ± 11 years were divided into a training (n = 162) and a validation cohort (n = 40).

FIELD STRENGTH/SEQUENCE

1.5T or 3.0T scanners. Sagittal T1-weighted and fat-suppressed T2-weighted imaging sequences.

ASSESSMENT

HBL was calculated using the Gross formula. Patients were classified as low and high HBL group, with 1000 mL as the threshold. Radiomics models were constructed with radiomics features. The radiomics score (Radscore) was obtained from the optimal radiomics model. Clinical variables were accessed using univariate and multivariate logistic regression analyses. Independent risk variables were used to build a clinical model. Clinical variables combined with Radscore were used to establish a combined model.

STATISTICAL TESTS

Predictive performance was evaluated using area under the curve (AUC), accuracy, sensitivity, specificity, and F1 score. Calibration curves and decision curves analyses were produced to evaluate the accuracy and clinical utility.

RESULTS

Among the radiomics models, the fusion (T1WI + FS-T2WI) model demonstrated the highest predictive efficacy (AUC: 0.744, 95% confidence interval [CI]: 0.576-0.914). The Radscore model (AUC: 0.809, 95% CI: 0.664-0.954) performs slightly better than the clinical model (AUC: 0.721, 95% CI: 0.524-0.918; P = 0.418) and the combined model (AUC: 0.752, 95% CI: 0.593-0.911; P = 0.178).

DATA CONCLUSION

A radiomics model may serve as a promising assessment tool for the risk of HBL in patients undergoing spinal metastasis surgery, and guide perioperative planning to improve surgical outcomes.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Machine Learning and Deep Learning in Spinal Injury: A Narrative Review of Algorithms in Diagnosis and Prognosis

Spinal injuries, including cervical and thoracolumbar fractures, continue to be a major public health concern. Recent advancements in machine learning and deep learning technologies offer exciting prospects for improving both diagnostic and prognostic approaches in spinal injury care. This narrative review systematically explores the practical utility of these computational methods, with a focus on their application in imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI), as well as in structured clinical data. Of the 39 studies included, 34 were focused on diagnostic applications, chiefly using deep learning to carry out tasks like vertebral fracture identification, differentiation between benign and malignant fractures, and AO fracture classification. The remaining five were prognostic, using machine learning to analyze parameters for predicting outcomes such as vertebral collapse and future fracture risk. This review highlights the potential benefit of machine learning and deep learning in spinal injury care, especially their roles in enhancing diagnostic capabilities, detailed fracture characterization, risk assessments, and individualized treatment planning.

Management of Osteoporotic Vertebral Fracture: Review Update 2022

A vertebral fracture is the most common type of osteoporotic fracture. Osteoporotic vertebral fractures (OVFs) cause a variety of morbidities and deaths. There are currently few "gold standard treatments" outlined for the management of OVFs in terms of quantity and quality. Conservative treatment is the primary treatment option for OVFs. The treatment of pain includes short-term bed rest, analgesic medication, anti-osteoporotic medications, exercise, and a brace. Numerous reports have been made on studies for vertebral augmentation (VA), including vertebroplasty and kyphoplasty. There is still debate and controversy about the effectiveness of VA in comparison with conservative treatment. Until more robust data are available, current evidence does not support the routine use of VA for OVF. Despite the fact that the majority of OVFs heal without surgery, 15%-35% of patients with an unstable fracture, persistent intractable back pain, or severely collapsed vertebra that causes a neurologic deficit, kyphosis, or chronic pseudarthrosis frequently require surgery. Because no single approach can guarantee the best surgical outcomes, customized surgical techniques are required. Surgeons must stay current on developments in the osteoporotic spine field and be open to new treatment options. Osteoporosis management and prevention are critical to lowering the risk of future OVFs. Clinical studies on bisphosphonate's effects on fracture healing are lacking. Teriparatide was intermittently administered, which dramatically improved spinal fusion and fracture healing while lowering mortality risk. According to the available literature, there are no standard management methods for OVFs. More multimodal approaches, including conservative and surgical treatment, VA, and medications that treat osteoporosis and promote fracture healing, are required to improve the quality of the majority of guidelines.