Computer-Aided Detection of Incidental Lumbar Spine Fractures from Routine Dual-Energy X-Ray Absorptiometry (DEXA) Studies Using a Support Vector Machine (SVM) Classifier

Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade

This article will provide a perspective review of the most extensively investigated deep learning (DL) applications for musculoskeletal disease detection that have the best potential to translate into routine clinical practice over the next decade. Deep learning methods for detecting fractures, estimating pediatric bone age, calculating bone measurements such as lower extremity alignment and Cobb angle, and grading osteoarthritis on radiographs have been shown to have high diagnostic performance with many of these applications now commercially available for use in clinical practice. Many studies have also documented the feasibility of using DL methods for detecting joint pathology and characterizing bone tumors on magnetic resonance imaging (MRI). However, musculoskeletal disease detection on MRI is difficult as it requires multi-task, multi-class detection of complex abnormalities on multiple image slices with different tissue contrasts. The generalizability of DL methods for musculoskeletal disease detection on MRI is also challenging due to fluctuations in image quality caused by the wide variety of scanners and pulse sequences used in routine MRI protocols. The diagnostic performance of current DL methods for musculoskeletal disease detection must be further evaluated in well-designed prospective studies using large image datasets acquired at different institutions with different imaging parameters and imaging hardware before they can be fully implemented in clinical practice. Future studies must also investigate the true clinical benefits of current DL methods and determine whether they could enhance quality, reduce error rates, improve workflow, and decrease radiologist fatigue and burnout with all of this weighed against the costs.

Machine learning value in the diagnosis of vertebral fractures: A systematic review and meta-analysis

PURPOSE

To evaluate the diagnostic accuracy of machine learning (ML) in detecting vertebral fractures, considering varying fracture classifications, patient populations, and imaging approaches.

METHOD

A systematic review and meta-analysis were conducted by searching PubMed, Embase, Cochrane Library, and Web of Science up to December 31, 2023, for studies using ML for vertebral fracture diagnosis. Bias risk was assessed using QUADAS-2. A bivariate mixed-effects model was used for the meta-analysis. Meta-analyses were performed according to five task types (vertebral fractures, osteoporotic vertebral fractures, differentiation of benign and malignant vertebral fractures, differentiation of acute and chronic vertebral fractures, and prediction of vertebral fractures). Subgroup analyses were conducted by different ML models (including ML and DL) and modeling methods (including CT, X-ray, MRI, and clinical features).

RESULTS

Eighty-one studies were included. ML demonstrated a diagnostic sensitivity of 0.91 and specificity of 0.95 for vertebral fractures. Subgroup analysis showed that DL (SROC 0.98) and CT (SROC 0.98) performed best overall. For osteoporotic fractures, ML showed a sensitivity of 0.93 and specificity of 0.96, with DL (SROC 0.99) and X-ray (SROC 0.99) performing better. For differentiating benign from malignant fractures, ML achieved a sensitivity of 0.92 and specificity of 0.93, with DL (SROC 0.96) and MRI (SROC 0.97) performing best. For differentiating acute from chronic vertebral fractures, ML showed a sensitivity of 0.92 and specificity of 0.93, with ML (SROC 0.96) and CT (SROC 0.97) performing best. For predicting vertebral fractures, ML had a sensitivity of 0.76 and specificity of 0.87, with ML (SROC 0.80) and clinical features (SROC 0.86) performing better.

CONCLUSIONS

ML, especially DL models applied to CT, MRI, and X-ray, shows high diagnostic accuracy for vertebral fractures. ML also effectively predicts osteoporotic vertebral fractures, aiding in tailored prevention strategies. Further research and validation are required to confirm ML's clinical efficacy.

Can we screen opportunistically for low bone mineral density using CT scans of the shoulder and artificial intelligence?

OBJECTIVE

To evaluate whether the CT attenuation of bones seen on shoulder CT scans could be used to predict low bone mineral density (BMD) (osteopenia/osteoporosis), and to compare the performance of two machine learning models to predict low BMD.

METHODS

In this study, we evaluated 194 patients aged 50 years or greater (69.2 ± 9.1 years; 170 females) who underwent unenhanced shoulder CT scans and dual-energy X-ray absorptiometry within 1 year of each other between January 1, 2010, and December 31, 2021. The CT attenuation of the humerus, glenoid, coracoid, acromion, clavicle, first, second, and third ribs was obtained using 3D-Slicer. Support vector machines (SVMs) and k-nearest neighbours (kNN) were used to predict low BMD. DeLong test was used to compare the areas under the curve (AUCs).

RESULTS

A CT attenuation of 195.4 Hounsfield Units of the clavicle had a sensitivity of 0.577, specificity of 0.781, and AUC of 0.701 to predict low BMD. In the test dataset, the SVM had sensitivity of 0.686, specificity of 1.00, and AUC of 0.857, while the kNN model had sensitivity of 0.966, specificity of 0.200, and AUC of 0.583. The SVM was superior to the CT attenuation of the clavicle (P = .003) but not better than the kNN model (P = .098).

CONCLUSION

The CT attenuation of the clavicle was best for predicting low BMD; however, a multivariable SVM was superior for predicting low BMD.

ADVANCES IN KNOWLEDGE

SVM utilizing the CT attenuations at many sites was best for predicting low BMD.

Optimizing the Clinical Direction of Artificial Intelligence With Health Policy: A Narrative Review of the Literature

Artificial intelligence (AI) has the ability to completely transform the healthcare industry by enhancing diagnosis, treatment, and resource allocation. To ensure patient safety and equitable access to healthcare, it also presents ethical and practical issues that need to be carefully addressed. Its integration into healthcare is a crucial topic. To realize its full potential, however, the ethical issues around data privacy, prejudice, and transparency, as well as the practical difficulties posed by workforce adaptability and statutory frameworks, must be addressed. While there is growing knowledge about the advantages of AI in healthcare, there is a significant lack of knowledge about the moral and practical issues that come with its application, particularly in the setting of emergency and critical care. The majority of current research tends to concentrate on the benefits of AI, but thorough studies that investigate the potential disadvantages and ethical issues are scarce. The purpose of our article is to identify and examine the ethical and practical difficulties that arise when implementing AI in emergency medicine and critical care, to provide solutions to these issues, and to give suggestions to healthcare professionals and policymakers. In order to responsibly and successfully integrate AI in these important healthcare domains, policymakers and healthcare professionals must collaborate to create strong regulatory frameworks, safeguard data privacy, remove prejudice, and give healthcare workers the necessary training.

Applied Artificial Intelligence in Healthcare: A Review of Computer Vision Technology Application in Hospital Settings

Computer vision (CV), a type of artificial intelligence (AI) that uses digital videos or a sequence of images to recognize content, has been used extensively across industries in recent years. However, in the healthcare industry, its applications are limited by factors like privacy, safety, and ethical concerns. Despite this, CV has the potential to improve patient monitoring, and system efficiencies, while reducing workload. In contrast to previous reviews, we focus on the end-user applications of CV. First, we briefly review and categorize CV applications in other industries (job enhancement, surveillance and monitoring, automation, and augmented reality). We then review the developments of CV in the hospital setting, outpatient, and community settings. The recent advances in monitoring delirium, pain and sedation, patient deterioration, mechanical ventilation, mobility, patient safety, surgical applications, quantification of workload in the hospital, and monitoring for patient events outside the hospital are highlighted. To identify opportunities for future applications, we also completed journey mapping at different system levels. Lastly, we discuss the privacy, safety, and ethical considerations associated with CV and outline processes in algorithm development and testing that limit CV expansion in healthcare. This comprehensive review highlights CV applications and ideas for its expanded use in healthcare.

Efficient 18F-fluorodeoxyglucose positron emission tomography/computed tomography-based machine learning model for predicting epidermal growth factor receptor mutations in non-small cell lung cancer

BACKGROUND

Beyond the human eye's limitations, radiomics provides more information that can be used for diagnosis. We develop a personalized and efficient model based on 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) to predict epidermal growth factor receptor (EGFR) mutations to help identify which non-small cell cancer (NSCLC) patients are candidates for EGFR-tyrosine kinase inhibitors (TKIs) therapy.

METHODS

We retrospectively included 100 patients with NSCLC and randomized them according to 70 patients in the training group and 30 patients in the validation group. The least absolute shrinkage and selection operator logistic regression (LLR) algorithm and support vector machine (SVM) classifier were used to build the models and predict whether EGFR is mutated or not. The predictive efficacy of the LLR algorithm-based model and the SVM classifier-based model was evaluated by plotting the receiver operating characteristic (ROC) curves and calculating the area under the curve (AUC).

RESULTS

The AUC, sensitivity and specificity of our radiomics model by LLR algorithm were 0.792, 0.967, and 0.600 for the training group and 0.643, 1.00, and 0.378 for the validation group, respectively, in predicting EGFR mutations. The AUC was 0.838 for the training group and 0.696 for the validation group after combining radiomics features with clinical features. The prediction results based on the SVM classifier showed that the validation group had the best performance when based on radial kernel function with AUC, sensitivity, and specificity of 0.741, 0.667, and 0.825, respectively.

CONCLUSIONS

Radiomics models based on 18F-FDG PET/CT modeled with different machine learning algorithms can improve the predictive efficacy of the models. Models that combine clinical features are more clinically valuable.

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.

Artificial intelligence in fracture detection with different image modalities and data types: A systematic review and meta-analysis

Artificial Intelligence (AI), encompassing Machine Learning and Deep Learning, has increasingly been applied to fracture detection using diverse imaging modalities and data types. This systematic review and meta-analysis aimed to assess the efficacy of AI in detecting fractures through various imaging modalities and data types (image, tabular, or both) and to synthesize the existing evidence related to AI-based fracture detection. Peer-reviewed studies developing and validating AI for fracture detection were identified through searches in multiple electronic databases without time limitations. A hierarchical meta-analysis model was used to calculate pooled sensitivity and specificity. A diagnostic accuracy quality assessment was performed to evaluate bias and applicability. Of the 66 eligible studies, 54 identified fractures using imaging-related data, nine using tabular data, and three using both. Vertebral fractures were the most common outcome (n = 20), followed by hip fractures (n = 18). Hip fractures exhibited the highest pooled sensitivity (92%; 95% CI: 87-96, p< 0.01) and specificity (90%; 95% CI: 85-93, p< 0.01). Pooled sensitivity and specificity using image data (92%; 95% CI: 90-94, p< 0.01; and 91%; 95% CI: 88-93, p < 0.01) were higher than those using tabular data (81%; 95% CI: 77-85, p< 0.01; and 83%; 95% CI: 76-88, p < 0.01), respectively. Radiographs demonstrated the highest pooled sensitivity (94%; 95% CI: 90-96, p < 0.01) and specificity (92%; 95% CI: 89-94, p< 0.01). Patient selection and reference standards were major concerns in assessing diagnostic accuracy for bias and applicability. AI displays high diagnostic accuracy for various fracture outcomes, indicating potential utility in healthcare systems for fracture diagnosis. However, enhanced transparency in reporting and adherence to standardized guidelines are necessary to improve the clinical applicability of AI. Review Registration: PROSPERO (CRD42021240359).

A Bibliometric Analysis of Artificial Intelligence Applications in Spine Care

BACKGROUND

 With the rapid development of science and technology, artificial intelligence (AI) has been widely used in the diagnosis and prognosis of various spine diseases. It has been proved that AI has a broad prospect in accurate diagnosis and treatment of spine disorders.

METHODS

 On May 7, 2022, the Web of Science (WOS) Core Collection database was used to identify the documents on the application of AI in the field of spine care. HistCite and VOSviewer were used for citation analysis and visualization mapping.

RESULTS

 A total of 693 documents were included in the final analysis. The most prolific authors were Karhade A.V. and Schwab J.H. United States was the most productive country. The leading journal was Spine. The most frequently used keyword was spinal. The most prolific institution was Northwestern University in Illinois, USA. Network visualization map showed that United States was the largest network of international cooperation. The keyword "machine learning" had the strongest total link strengths (TLS) and largest number of occurrences. The latest trends suggest that AI for the diagnosis of spine diseases may receive widespread attention in the future.

CONCLUSIONS

 AI has a wide range of application in the field of spine care, and an increasing number of scholars are committed to research on the use of AI in the field of spine care. Bibliometric analysis in the field of AI and spine provides an overall perspective, and the appreciation and research of these influential publications are useful for future research.

Cross-subject emotion recognition using hierarchical feature optimization and support vector machine with multi-kernel collaboration

Objective. Due to individual differences, it is greatly challenging to realize the multiple types of emotion identification across subjects.Approach. In this research, a hierarchical feature optimization method is proposed in order to represent emotional states effectively based on peripheral physiological signals. Firstly, sparse learning combined with binary search is employed to achieve feature selection of single signals. Then an improved fast correlation-based filter is proposed to implement fusion optimization of multi-channel signal features. Aiming at overcoming the limitations of the support vector machine (SVM), which uses a single kernel function to make decisions, the multi-kernel function collaboration strategy is proposed to improve the classification performance of SVM.Main results. The effectiveness of the proposed method is verified on the DEAP dataset. Experimental results show that the proposed method presents a competitive performance for four cross-subject  types of emotion identification with an accuracy of 84% (group 1) and 85.07% (group 2). Significance. The proposed model with hierarchical feature optimization and SVM with multi-kernel function collaboration demonstrates superior emotion recognition accuracy compared to state-of-the-art techniques. In addition, the analysis based on DEAP dataset composition characteristics presents a novel perspective to explore the emotion recognition issue more objectively and comprehensively.

Artificial Intelligence-Assisted Detection of Osteoporotic Vertebral Fractures on Lateral Chest Radiographs in Post-Menopausal Women

Osteoporotic vertebral fractures (OVFs) are often not reported by radiologists on routine chest radiographs. This study aims to investigate the clinical value of a newly developed artificial intelligence (AI) tool, Ofeye 1.0, for automated detection of OVFs on lateral chest radiographs in post-menopausal women (>60 years) who were referred to undergo chest x-rays for other reasons. A total of 510 de-identified lateral chest radiographs from three clinical sites were retrieved and analysed using the Ofeye 1.0 tool. These images were then reviewed by a consultant radiologist with findings serving as the reference standard for determining the diagnostic performance of the AI tool for the detection of OVFs. Of all the original radiologist reports, missed OVFs were found in 28.8% of images but were detected using the AI tool. The AI tool demonstrated high specificity of 92.8% (95% CI: 89.6, 95.2%), moderate accuracy of 80.3% (95% CI: 76.3, 80.4%), positive predictive value (PPV) of 73.7% (95% CI: 65.2, 80.8%), and negative predictive value (NPV) of 81.5% (95% CI: 79, 83.8%), but low sensitivity of 49% (95% CI: 40.7, 57.3%). The AI tool showed improved sensitivity compared with the original radiologist reports, which was 20.8% (95% CI: 14.5, 28.4). The new AI tool can be used as a complementary tool in routine diagnostic reports for the reduction in missed OVFs in elderly women.

Predictive value of machine learning on fracture risk in osteoporosis: a systematic review and meta-analysis

OBJECTIVES

Early identification of fracture risk in patients with osteoporosis is essential. Machine learning (ML) has emerged as a promising technique to predict the risk, whereas its predictive performance remains controversial. Therefore, we conducted this systematic review and meta-analysis to explore the predictive efficiency of ML for the risk of fracture in patients with osteoporosis.

METHODS

Relevant studies were retrieved from four databases (PubMed, Embase, Cochrane Library and Web of Science) until 31 May 2023. A meta-analysis of the C-index was performed using a random-effects model, while a bivariate mixed-effects model was used for the meta-analysis of sensitivity and specificity. In addition, subgroup analysis was performed according to the types of ML models and fracture sites.

RESULTS

Fifty-three studies were included in our meta-analysis, involving 15 209 268 patients, 86 prediction models specifically developed for the osteoporosis population and 41 validation sets. The most commonly used predictors in these models encompassed age, BMI, past fracture history, bone mineral density T-score, history of falls, BMD, radiomics data, weight, height, gender and other chronic diseases. Overall, the pooled C-index of ML was 0.75 (95% CI: 0.72, 0.78) and 0.75 (95% CI: 0.71, 0.78) in the training set and validation set, respectively; the pooled sensitivity was 0.79 (95% CI: 0.72, 0.84) and 0.76 (95% CI: 0.80, 0.81) in the training set and validation set, respectively; and the pooled specificity was 0.81 (95% CI: 0.75, 0.86) and 0.83 (95% CI: 0.72, 0.90) in the training set and validation set, respectively.

CONCLUSIONS

ML has a favourable predictive performance for fracture risk in patients with osteoporosis. However, most current studies lack external validation. Thus, external validation is required to verify the reliability of ML models.

PROSPERO REGISTRATION NUMBER

CRD42022346896.

Machine Learning for Opportunistic Screening for Osteoporosis and Osteopenia Using Knee CT Scans

PURPOSE

To predict whether a patient has osteoporosis/osteopenia using the attenuation of trabecular bone obtained from knee computed tomography (CT) scans.

METHODS

Retrospective analysis of 273 patients who underwent contemporaneous knee CT scans and dual-energy X-ray absorptiometry (DXA) within 1 year. Volumetric segmentation of the trabecular bone of the distal femur, proximal tibia, patella, and proximal fibula was performed to obtain the bone CT attenuation. The data was randomly split into training/validation (78%) and test (22%) datasets and the performance in the test dataset were evaluated. The predictive properties of the CT attenuation of each bone to predict osteoporosis/osteopenia were assessed. Multivariable support vector machines (SVM) and random forest classifiers (RF) were used to predict osteoporosis/osteopenia.

RESULTS

Patients with a mean age (range) of 67.9 (50-87) years, 85% female were evaluated. Seventy-seven (28.2%) of patients had normal bone mineral density (BMD), 140 (51.3%) had osteopenia, and 56 (20.5%) had osteoporosis. The proximal tibia had the best predictive ability of all bones and a CT attenuation threshold of 96.0 Hounsfield Units (HU) had a sensitivity of .791, specificity of .706, and area under the curve (AUC) of .748. The AUC for the SVM with cubic kernel classifier (AUC = .912) was better than the RF classifier (AUC = .683, P < .001) and better than using the CT attenuation threshold of 96.0 HU at the proximal tibia (AUC = .748, P = .025).

CONCLUSIONS

Opportunistic screening for osteoporosis/osteopenia can be performed using knee CT scans. Multivariable machine learning models are more predictive than the CT attenuation of a single bone.

Machine Learning Applications in Spine Surgery

This literature review sought to identify and evaluate the current applications of artificial intelligence (AI)/machine learning (ML) in spine surgery that can effectively guide clinical decision-making and surgical planning. By using specific keywords to maximize search sensitivity, a thorough literature research was conducted in several online databases: Scopus, PubMed, and Google Scholar, and the findings were filtered according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 46 studies met the requirements and were included in this review. According to this study, AI/ML models were sufficiently accurate with a mean overall value of 74.9%, and performed best at preoperative patient selection, cost prediction, and length of stay. Performance was also good at predicting functional outcomes and postoperative mortality. Regression analysis was the most frequently utilized application whereas deep learning/artificial neural networks had the highest sensitivity score (81.5%). Despite the relatively brief history of engagement with AI/ML, as evidenced by the fact that 77.5% of studies were published after 2018, the outcomes have been promising. In light of the Big Data era, the increasing prevalence of National Registries, and the wide-ranging applications of AI, such as exemplified by ChatGPT (OpenAI, San Francisco, California), it is highly likely that the field of spine surgery will gradually adopt and integrate AI/ML into its clinical practices. Consequently, it is of great significance for spine surgeons to acquaint themselves with the fundamental principles of AI/ML, as these technologies hold the potential for substantial improvements in overall patient care.

Revolutionizing Spinal Care: Current Applications and Future Directions of Artificial Intelligence and Machine Learning

Artificial intelligence (AI) and machine learning (ML) are rapidly becoming integral components of modern healthcare, offering new avenues for diagnosis, treatment, and outcome prediction. This review explores their current applications and potential future in the field of spinal care. From enhancing imaging techniques to predicting patient outcomes, AI and ML are revolutionizing the way we approach spinal diseases. AI and ML have significantly improved spinal imaging by augmenting detection and classification capabilities, thereby boosting diagnostic accuracy. Predictive models have also been developed to guide treatment plans and foresee patient outcomes, driving a shift towards more personalized care. Looking towards the future, we envision AI and ML further ingraining themselves in spinal care with the development of algorithms capable of deciphering complex spinal pathologies to aid decision making. Despite the promise these technologies hold, their integration into clinical practice is not without challenges. Data quality, integration hurdles, data security, and ethical considerations are some of the key areas that need to be addressed for their successful and responsible implementation. In conclusion, AI and ML represent potent tools for transforming spinal care. Thoughtful and balanced integration of these technologies, guided by ethical considerations, can lead to significant advancements, ushering in an era of more personalized, effective, and efficient healthcare.

Opportunistic screening for osteoporosis and osteopenia from CT scans of the abdomen and pelvis using machine learning

OBJECTIVES

To use multivariable machine learning using the computed tomography (CT) attenuation of each of the bones in the lumbar spine, pelvis, and sacrum, to predict osteoporosis/osteopenia.

METHODS

This was a retrospective study of 394 patients aged 50 years or older with CT scans of the abdomen and pelvis and dual-energy x-ray absorptiometry (DXA) scans obtained within 6 months of each other. Volumetric segmentations were performed for each of the bones from L1-L4 vertebrae, pelvis, and sacrum to obtain the mean CT attenuation of each bone. The data was randomly split into training/validation (n = 274, 70%) and test (n = 120, 30%) datasets. The CT attenuation of the L1 vertebrae, univariate logistic regression, least absolute shrinkage and selection operator (LASSO), and support vector machines (SVM) with radial basis function (RBF) were used to predict osteoporosis/osteopenia. The performance of using the CT attenuation at L1 to the univariate logistic regression, LASSO, and SVM models were compared using DeLong's test in the test dataset.

RESULTS

All CT attenuation measurements were predictive of osteoporosis/osteopenia (p < 0.001 for all). The SVM model (accuracy = 0.892, AUC = 0.886) outperformed the models using the CT attenuation of threshold of 173.9 Hounsfield units (HU) at L1 (accuracy = 0.725, AUC = 0.739, p = 0.010), the univariate logistic regression model (accuracy = 0.767, AUC = 0.533, p < 0.001) and the LASSO model (accuracy = 0.817, AUC = 0.711, p = 0.007) to predict osteoporosis/osteopenia.

CONCLUSION

A SVM model using the CT attenuations of multiple bones within the lumbar spine and pelvis and clinical data has a better ability to predict osteoporosis/osteopenia than using the CT attenuation of L1 or a LASSO model.

KEY POINTS

• Multivariable SVM model using the CT attenuation of multiple bones and clinical/demographic data was more predictive than using the CT attenuation at L1 only.

Performance of a deep convolutional neural network for MRI-based vertebral body measurements and insufficiency fracture detection

OBJECTIVES

The aim is to validate the performance of a deep convolutional neural network (DCNN) for vertebral body measurements and insufficiency fracture detection on lumbar spine MRI.

METHODS

This retrospective analysis included 1000 vertebral bodies in 200 patients (age 75.2 ± 9.8 years) who underwent lumbar spine MRI at multiple institutions. 160/200 patients had ≥ one vertebral body insufficiency fracture, 40/200 had no fracture. The performance of the DCNN and that of two fellowship-trained musculoskeletal radiologists in vertebral body measurements (anterior/posterior height, extent of endplate concavity, vertebral angle) and evaluation for insufficiency fractures were compared. Statistics included (a) interobserver reliability metrics using intraclass correlation coefficient (ICC), kappa statistics, and Bland-Altman analysis, and (b) diagnostic performance metrics (sensitivity, specificity, accuracy). A statistically significant difference was accepted if the 95% confidence intervals did not overlap.

RESULTS

The inter-reader agreement between radiologists and the DCNN was excellent for vertebral body measurements, with ICC values of > 0.94 for anterior and posterior vertebral height and vertebral angle, and good to excellent for superior and inferior endplate concavity with ICC values of 0.79-0.85. The performance of the DCNN in fracture detection yielded a sensitivity of 0.941 (0.903-0.968), specificity of 0.969 (0.954-0.980), and accuracy of 0.962 (0.948-0.973). The diagnostic performance of the DCNN was independent of the radiological institution (accuracy 0.964 vs. 0.960), type of MRI scanner (accuracy 0.957 vs. 0.964), and magnetic field strength (accuracy 0.966 vs. 0.957).

CONCLUSIONS

A DCNN can achieve high diagnostic performance in vertebral body measurements and insufficiency fracture detection on heterogeneous lumbar spine MRI.

KEY POINTS

• A DCNN has the potential for high diagnostic performance in measuring vertebral bodies and detecting insufficiency fractures of the lumbar spine.

Current Applications of Machine Learning in Spine: From Clinical View

STUDY DESIGN

Narrative review.

OBJECTIVES

This review aims to present current applications of machine learning (ML) in spine domain to clinicians.

METHODS

We conducted a comprehensive PubMed search of peer-reviewed articles that were published between 2006 and 2020 using terms (spine, spinal, lumbar, cervical, thoracic, machine learning) to examine ML in spine. Then exclude research of other domain, case report, review or meta-analysis, and which without available abstract or full text.

RESULTS

Total 1738 articles were retrieved from database, and 292 studies were finally included. Key findings of current applications were compiled and summarized in this review. Main clinical applications of those techniques including image processing, diagnosis, decision supporting, operative assistance, rehabilitation, surgery outcomes, complications, hospitalization and cost.

CONCLUSIONS

ML had achieved excellent performance and hold immense potential in spine. ML could help clinical staff to improve medical level, enhance work efficiency, and reduce adverse events. However more randomized controlled trials and improvement of interpretability are essential to clinicians accepting models' assistance in real work.

Support vector machines are superior to principal components analysis for selecting the optimal bones’ CT attenuations for opportunistic screening for osteoporosis using CT scans of the foot or ankle

Objectives

To use the computed tomography (CT) attenuation of the foot and ankle bones for opportunistic screening for osteoporosis.

Methods

Retrospective study of 163 consecutive patients from a tertiary care academic center who underwent CT scans of the foot or ankle and dual-energy X-ray absorptiometry (DXA) within 1 year of each other. Volumetric segmentation of each bone of the foot and ankle was done in 3D Slicer to obtain the mean CT attenuation. Pearson's correlations were used to correlate the 10.13039/100004811CT attenuations with each other and with DXA measurements. Support vector machines (SVM) with various kernels and principal components analysis (PCA) were used to predict osteoporosis and osteopenia/osteoporosis in training/validation and test datasets.

Results

CT attenuation measurements at the talus, calcaneus, navicular, cuboid, and cuneiforms were correlated with each other and positively correlated with BMD T-scores at the L1-4 lumbar spine, hip, and femoral neck; however, there was no significant correlation with the L1-4 trabecular bone scores. A CT attenuation threshold of 143.2 Hounsfield units (HU) of the calcaneus was best for detection of osteoporosis in the training/validation dataset. SVMs with radial basis function (RBF) kernels were significantly better than the PCA model and the calcaneus for predicting osteoporosis in the test dataset.

Conclusions

Opportunistic screening for osteoporosis is possible using the CT attenuation of the foot and ankle bones. SVMs with RBF using all bones is more accurate than the CT attenuation of the calcaneus.

Utilizing machine learning for opportunistic screening for low BMD using CT scans of the cervical spine

BACKGROUND

Computed Tomography (CT) scans of the cervical spine are often performed to evaluate patients for trauma and degenerative changes of the cervical spine. We hypothesized that the CT attenuation of the cervical vertebrae can be used to identify patients who should be screened for osteoporosis.

METHODS

Retrospective study of 253 patients (177 training/validation and 76 test) with unenhanced CT scans of the cervical spine and DXA studies within 12 months of each other. Volumetric segmentation of C1-T1, clivus, and first ribs was performed to obtain the CT attenuation of each bone. The correlations of the CT attenuations between the bones and with DXA measurements were evaluated. Univariate receiver operator characteristic (ROC) analyses, and multivariate classifiers (Random Forest (RF), XGBoost, Naïve Bayes (NB), and Support Vector Machines (SVM)) analyzing the CT attenuation of all bones, were utilized to predict patients with osteopenia/osteoporosis and femoral neck bone mineral density (BMD) T-scores <-1.

RESULTS

There were positive correlations between the CT attenuation of each bone, and with the DXA measurements. A CT attenuation threshold of 305.2 Hounsfield Units (HU) at C3 had the highest accuracy =0.763 (AUC=0.814) to detect femoral neck BMD T-scores ≤-1 and a CT attenuation threshold of 323.6 HU at C3 had the highest accuracy=0.774 (AUC=0.843) to detect osteopenia/osteoporosis. The SVM classifier (AUC=0.756) had higher AUC than the RF (AUC=0.692, P=0.224), XGBoost (AUC=0.736; P=0.814), NB (AUC=0.622, P=0.133) and CT threshold of 305.2 HU at C3 (AUC=0.704, P=0.531) classifiers to identify patients with femoral neck BMD T-scores <-1. The SVM classifier (accuracy=0.816) was more accurate than using the CT threshold of 305.2 HU at C3 (accuracy=0.671) (McNemar's χ₁²=7.55, P=0.006).

CONCLUSION

Opportunistic screening for low BMD can be done using cervical spine CT scans. A SVM classifier was more accurate than using the CT threshold of 305.2 HU at C3.

Machine learning for the prediction of osteopenia/osteoporosis using the CT attenuation of multiple osseous sites from chest CT

PURPOSE

To use machine learning and the CT attenuation of all bones visible on chest CT scans to predict osteopenia/osteoporosis.

METHOD

We retrospectively evaluated 364 patients with CT scans of the chest, and Dual-energy X-ray absorptiometry (DXA) scans within 6 months of each other. Studies were performed between 01/01/2015 and 08/01/2021. Volumetric segmentation of the ribs, thoracic vertebrae, sternum, and clavicle was performed using 3D Slicer to obtain the mean CT attenuation of each bone. The study sample was randomly split into training/validation (80 %, n = 291 patients) and test (20 %, n = 73 patients) datasets. Univariate analyses were used to identify the optimal CT attenuation thresholds to diagnose osteopenia/osteoporosis. We used penalized multivariable logistic regression models including Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net, and Ridge regression, and Support Vector Machines (SVM) with radial basis functions (RBF) to predict osteopenia/osteoporosis and compared these results to the CT attenuation threshold at T12.

RESULTS

There were positive correlations between the CT attenuation between all bones (r > 0.6, P < 0.001 for all). There were positive correlations between CT attenuation of the bones and the L1-L4 BMD T-score, total hip T-score, and femoral neck T-scores (r > 0.4, P < 0.001 for all). A CT attenuation threshold of 170.2 Hounsfield units (HU) at T12 had an AUC of 0.702, while a threshold of 192.1 HU at T4 had an AUC of 0.757. The SVM with RBF had the highest AUC (AUC = 0.864) and was better than the LASSO (P = 0.011), Elastic Net (P = 0.011), Ridge regression (P = 0.011) but was not better than using the CT attenuation at T12 (P = 0.060).

CONCLUSIONS

The CT attenuation of the ribs, thoracic vertebra, sternum, and clavicle can be used individually and collectively to predict BMD and to predict osteopenia/osteoporosis.

Artificial intelligence and spine imaging: limitations, regulatory issues and future direction

BACKGROUND

As big data and artificial intelligence (AI) in spine care, and medicine as a whole, continue to be at the forefront of research, careful consideration to the quality and techniques utilized is necessary. Predictive modeling, data science, and deep analytics have taken center stage. Within that space, AI and machine learning (ML) approaches toward the use of spine imaging have gathered considerable attention in the past decade. Although several benefits of such applications exist, limitations are also present and need to be considered.

PURPOSE

The following narrative review presents the current status of AI, in particular, ML, with special regard to imaging studies, in the field of spinal research.

METHODS

A multi-database assessment of the literature was conducted up to September 1, 2021, that addressed AI as it related to imaging of the spine. Articles written in English were selected and critically assessed.

RESULTS

Overall, the review discussed the limitations, data quality and applications of ML models in the context of spine imaging. In particular, we addressed the data quality and ML algorithms in spine imaging research by describing preliminary results from a widely accessible imaging algorithm that is currently available for spine specialists to reference for information on severity of spine disease and degeneration which ultimately may alter clinical decision-making. In addition, awareness of the current, under-recognized regulation surrounding the execution of ML for spine imaging was raised.

CONCLUSIONS

Recommendations were provided for conducting high-quality, standardized AI applications for spine imaging.

Artificial intelligence in spine care: current applications and future utility

PURPOSE

The field of artificial intelligence is ever growing and the applications of machine learning in spine care are continuously advancing. Given the advent of the intelligence-based spine care model, understanding the evolution of computation as it applies to diagnosis, treatment, and adverse event prediction is of great importance. Therefore, the current review sought to synthesize findings from the literature at the interface of artificial intelligence and spine research.

METHODS

A narrative review was performed based on the literature of three databases (MEDLINE, CINAHL, and Scopus) from January 2015 to March 2021 that examined historical and recent advancements in the understanding of artificial intelligence and machine learning in spine research. Studies were appraised for their role in, or description of, advancements within image recognition and predictive modeling for spinal research. Only English articles that fulfilled inclusion criteria were ultimately incorporated in this review.

RESULTS

This review briefly summarizes the history and applications of artificial intelligence and machine learning in spine. Three basic machine learning training paradigms: supervised learning, unsupervised learning, and reinforced learning are also discussed. Artificial intelligence and machine learning have been utilized in almost every facet of spine ranging from localization and segmentation techniques in spinal imaging to pathology specific algorithms which include but not limited to; preoperative risk assessment of postoperative complications, screening algorithms for patients at risk of osteoporosis and clustering analysis to identify subgroups within adolescent idiopathic scoliosis. The future of artificial intelligence and machine learning in spine surgery is also discussed with focusing on novel algorithms, data collection techniques and increased utilization of automated systems.

CONCLUSION

Improvements to modern-day computing and accessibility to various imaging modalities allow for innovative discoveries that may arise, for example, from management. Given the imminent future of AI in spine surgery, it is of great importance that practitioners continue to inform themselves regarding AI, its goals, use, and progression. In the future, it will be critical for the spine specialist to be able to discern the utility of novel AI research, particularly as it continues to pervade facets of everyday spine surgery.

A software program for automated compressive vertebral fracture detection on elderly women's lateral chest radiograph: Ofeye 1.0

Background

Because osteoporotic vertebral fracture (OVF) on chest radiographs is commonly missed in radiological reports, we aimed to develop a software program which offers automated detection of compressive vertebral fracture (CVF) on lateral chest radiographs, and which emphasizes CVF detection specificity with a low false positivity rate.

Methods

For model training, we retrieved 3,991 spine radiograph cases and 1,979 chest radiograph cases from 16 sources, with among them in total 1,404 cases had OVF. For model testing, we retrieved 542 chest radiograph cases and 162 spine radiograph cases from four independent clinics, with among them 215 cases had OVF. All cases were female subjects, and except for 31 training data cases which were spine trauma cases, all the remaining cases were post-menopausal women. Image data included DICOM (Digital Imaging and Communications in Medicine) format, hard film scanned PNG (Portable Network Graphics) format, DICOM exported PNG format, and PACS (Picture Archiving and Communication System) downloaded resolution reduced DICOM format. OVF classification included: minimal and mild grades with <20% or ≥20-25% vertebral height loss respectively, moderate grade with ≥25-40% vertebral height loss, severe grade with ≥40%-2/3 vertebral height loss, and collapsed grade with ≥2/3 vertebral height loss. The CVF detection base model was mainly composed of convolution layers that include convolution kernels of different sizes, pooling layers, up-sampling layers, feature merging layers, and residual modules. When the model loss function could not be further decreased with additional training, the model was considered to be optimal and termed 'base-model 1.0'. A user-friendly interface was also developed, with the synthesized software termed 'Ofeye 1.0'.

Results

Counting cases and with minimal and mild OVFs included, base-model 1.0 demonstrated a specificity of 97.1%, a sensitivity of 86%, and an accuracy of 93.9% for the 704 testing cases. In total, 33 OVFs in 30 cases had a false negative reading, which constituted a false negative rate of 14.0% (30/215) by counting all OVF cases. Eighteen OVFs in 15 cases had OVFs of ≥ moderate grades missed, which constituted a false negative rate of 7.0% (15/215, i.e., sensitivity 93%) if only counting cases with ≥ moderate grade OVFs missed. False positive reading was recorded in 13 vertebrae in 13 cases (one vertebra in each case), which constituted a false positivity rate of 2.7% (13/489). These vertebrae with false positivity labeling could be readily differentiated from a true OVF by a human reader. The software Ofeye 1.0 allows 'batch processing', for example, 100 radiographs can be processed in a single operation. This software can be integrated into hospital PACS, or installed in a standalone personal computer.

Conclusions

A user-friendly software program was developed for CVF detection on elderly women's lateral chest radiographs. It has an overall low false positivity rate, and for moderate and severe CVFs an acceptably low false negativity rate. The integration of this software into radiological practice is expected to improve osteoporosis management for elderly women.

Diagnostic accuracy and potential covariates of artificial intelligence for diagnosing orthopedic fractures: a systematic literature review and meta-analysis

OBJECTIVES

To systematically quantify the diagnostic accuracy and identify potential covariates affecting the performance of artificial intelligence (AI) in diagnosing orthopedic fractures.

METHODS

PubMed, Embase, Web of Science, and Cochrane Library were systematically searched for studies on AI applications in diagnosing orthopedic fractures from inception to September 29, 2021. Pooled sensitivity and specificity and the area under the receiver operating characteristic curves (AUC) were obtained. This study was registered in the PROSPERO database prior to initiation (CRD 42021254618).

RESULTS

Thirty-nine were eligible for quantitative analysis. The overall pooled AUC, sensitivity, and specificity were 0.96 (95% CI 0.94-0.98), 90% (95% CI 87-92%), and 92% (95% CI 90-94%), respectively. In subgroup analyses, multicenter designed studies yielded higher sensitivity (92% vs. 88%) and specificity (94% vs. 91%) than single-center studies. AI demonstrated higher sensitivity with transfer learning (with vs. without: 92% vs. 87%) or data augmentation (with vs. without: 92% vs. 87%), compared to those without. Utilizing plain X-rays as input images for AI achieved results comparable to CT (AUC 0.96 vs. 0.96). Moreover, AI achieved comparable results to humans (AUC 0.97 vs. 0.97) and better results than non-expert human readers (AUC 0.98 vs. 0.96; sensitivity 95% vs. 88%).

CONCLUSIONS

AI demonstrated high accuracy in diagnosing orthopedic fractures from medical images. Larger-scale studies with higher design quality are needed to validate our findings.

KEY POINTS

• Multicenter study design, application of transfer learning, and data augmentation are closely related to improving the performance of artificial intelligence models in diagnosing orthopedic fractures. • Utilizing plain X-rays as input images for AI to diagnose fractures achieved results comparable to CT (AUC 0.96 vs. 0.96). • AI achieved comparable results to humans (AUC 0.97 vs. 0.97) but was superior to non-expert human readers (AUC 0.98 vs. 0.96, sensitivity 95% vs. 88%) in diagnosing fractures.

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.

Automated prediction of the Thoracolumbar Injury Classification and Severity Score from CT using a novel deep learning algorithm

OBJECTIVE

Damage to the thoracolumbar spine can confer significant morbidity and mortality. The Thoracolumbar Injury Classification and Severity Score (TLICS) is used to categorize injuries and determine patients at risk of spinal instability for whom surgical intervention is warranted. However, calculating this score can constitute a bottleneck in triaging and treating patients, as it relies on multiple imaging studies and a neurological examination. Therefore, the authors sought to develop and validate a deep learning model that can automatically categorize vertebral morphology and determine posterior ligamentous complex (PLC) integrity, two critical features of TLICS, using only CT scans.

METHODS

All patients who underwent neurosurgical consultation for traumatic spine injury or degenerative pathology resulting in spine injury at a single tertiary center from January 2018 to December 2019 were retrospectively evaluated for inclusion. The morphology of injury and integrity of the PLC were categorized on CT scans. A state-of-the-art object detection region-based convolutional neural network (R-CNN), Faster R-CNN, was leveraged to predict both vertebral locations and the corresponding TLICS. The network was trained with patient CT scans, manually labeled vertebral bounding boxes, TLICS morphology, and PLC annotations, thus allowing the model to output the location of vertebrae, categorize their morphology, and determine the status of PLC integrity.

RESULTS

A total of 111 patients were included (mean ± SD age 62 ± 20 years) with a total of 129 separate injury classifications. Vertebral localization and PLC integrity classification achieved Dice scores of 0.92 and 0.88, respectively. Binary classification between noninjured and injured morphological scores demonstrated 95.1% accuracy. TLICS morphology accuracy, the true positive rate, and positive injury mismatch classification rate were 86.3%, 76.2%, and 22.7%, respectively. Classification accuracy between no injury and suspected PLC injury was 86.8%, while true positive, false negative, and false positive rates were 90.0%, 10.0%, and 21.8%, respectively.

CONCLUSIONS

In this study, the authors demonstrate a novel deep learning method to automatically predict injury morphology and PLC disruption with high accuracy. This model may streamline and improve diagnostic decision support for patients with thoracolumbar spinal trauma.

Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis

Background Patients with fractures are a common emergency presentation and may be misdiagnosed at radiologic imaging. An increasing number of studies apply artificial intelligence (AI) techniques to fracture detection as an adjunct to clinician diagnosis. Purpose To perform a systematic review and meta-analysis comparing the diagnostic performance in fracture detection between AI and clinicians in peer-reviewed publications and the gray literature (ie, articles published on preprint repositories). Materials and Methods A search of multiple electronic databases between January 2018 and July 2020 (updated June 2021) was performed that included any primary research studies that developed and/or validated AI for the purposes of fracture detection at any imaging modality and excluded studies that evaluated image segmentation algorithms. Meta-analysis with a hierarchical model to calculate pooled sensitivity and specificity was used. Risk of bias was assessed by using a modified Prediction Model Study Risk of Bias Assessment Tool, or PROBAST, checklist. Results Included for analysis were 42 studies, with 115 contingency tables extracted from 32 studies (55 061 images). Thirty-seven studies identified fractures on radiographs and five studies identified fractures on CT images. For internal validation test sets, the pooled sensitivity was 92% (95% CI: 88, 93) for AI and 91% (95% CI: 85, 95) for clinicians, and the pooled specificity was 91% (95% CI: 88, 93) for AI and 92% (95% CI: 89, 92) for clinicians. For external validation test sets, the pooled sensitivity was 91% (95% CI: 84, 95) for AI and 94% (95% CI: 90, 96) for clinicians, and the pooled specificity was 91% (95% CI: 81, 95) for AI and 94% (95% CI: 91, 95) for clinicians. There were no statistically significant differences between clinician and AI performance. There were 22 of 42 (52%) studies that were judged to have high risk of bias. Meta-regression identified multiple sources of heterogeneity in the data, including risk of bias and fracture type. Conclusion Artificial intelligence (AI) and clinicians had comparable reported diagnostic performance in fracture detection, suggesting that AI technology holds promise as a diagnostic adjunct in future clinical practice. Clinical trial registration no. CRD42020186641 © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Cohen and McInnes in this issue.

Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm

Background: We investigated whether opportunistic screening for osteoporosis can be done from computed tomography (CT) scans of the wrist/forearm using machine learning. Methods: A retrospective study of 196 patients aged 50 years or greater who underwent CT scans of the wrist/forearm and dual-energy X-ray absorptiometry (DEXA) scans within 12 months of each other was performed. Volumetric segmentation of the forearm, carpal, and metacarpal bones was performed to obtain the mean CT attenuation of each bone. The correlations of the CT attenuations of each of the wrist/forearm bones and their correlations to the DEXA measurements were calculated. The study was divided into training/validation (n = 96) and test (n = 100) datasets. The performance of multivariable support vector machines (SVMs) was evaluated in the test dataset and compared to the CT attenuation of the distal third of the radial shaft (radius 33%). Results: There were positive correlations between each of the CT attenuations of the wrist/forearm bones, and with DEXA measurements. A threshold hamate CT attenuation of 170.2 Hounsfield units had a sensitivity of 69.2% and a specificity of 77.1% for identifying patients with osteoporosis. The radial-basis-function (RBF) kernel SVM (AUC = 0.818) was the best for predicting osteoporosis with a higher AUC than other models and better than the radius 33% (AUC = 0.576) (p = 0.020). Conclusions: Opportunistic screening for osteoporosis could be performed using CT scans of the wrist/forearm. Multivariable machine learning techniques, such as SVM with RBF kernels, that use data from multiple bones were more accurate than using the CT attenuation of a single bone.

Predictors of adverse events after percutaneous pedicle screws fixation in patients with single-segment thoracolumbar burst fractures

BACKGROUND

Percutaneous pedicle screw fixation (PPSF) is the primary approach for single-segment thoracolumbar burst fractures (TLBF). The healing angle at the thoracolumbar junction is one of the most significant criteria for evaluating the efficacy of PPSF. Therefore, the purpose of this study was to analyze the predictors associated with the poor postoperative alignment of the thoracolumbar region from routine variables using a support vector machine (SVM) model.

METHODS

We retrospectively analyzed patients with TLBF operated at our academic institute between March 1, 2014 and December 31, 2019. Stepwise logistic regression analysis was performed to assess potential statistical differences between all clinical and radiological variables and the adverse events. Based on multivariate logistic results, a series of independent risk factors were fed into the SVM model. Meanwhile, the feature importance of radiologic outcome for each parameter was explored. The predictive performance of the SVM classifier was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy (ACC) and confusion matrices with 10-fold cross-validation, respectively.

RESULTS

In the recruited 150 TLBFs, unfavorable radiological outcomes were observed in 53 patients (35.33%). The relationship between osteoporosis (p = 0.036), preoperative Cobb angle (p = 0.001), immediate postoperative Cobb angle (p = 0.029), surgically corrected Cobb angle (p = 0.001), intervertebral disc injury (Score 2 p = 0.001, Score 3 p = 0.001), interpedicular distance (IPD) (p = 0.001), vertebral body compression rate (VBCR) (p = 0.010) and adverse events was confirmed by univariate regression. Thereafter, independent risk factors including preoperative Cobb angle, the disc status and IPD and independent protective factors surgical correction angle were identified by multivariable logistic regression. The established SVM classifier demonstrated favorable predictive performance with the best AUC = 0.93, average AUC = 0.88, and average ACC = 0.87. The variables associated with radiological outcomes, in order of correlation strength, were intervertebral disc injury (42%), surgically corrected Cobb angle (25%), preoperative Cobb angle (18%), and IPD (15%). The confusion matrix reveals the classification results of the discriminant analysis.

CONCLUSIONS

Critical radiographic indicators and surgical purposes were confirmed to be associated with an unfavorable radiographic outcome of TLBF. This SVM model demonstrated good predictive ability for endpoints in terms of adverse events in patients after PPSF surgery.

A Surgeon's Guide to Understanding Artificial Intelligence and Machine Learning Studies in Orthopaedic Surgery

PURPOSE OF REVIEW

In recent years, machine learning techniques have been increasingly utilized across medicine, impacting the practice and delivery of healthcare. The data-driven nature of orthopaedic surgery presents many targets for improvement through the use of artificial intelligence, which is reflected in the increasing number of publications in the medical literature. However, the unique methodologies utilized in AI studies can present a barrier to its widespread acceptance and use in orthopaedics. The purpose of our review is to provide a tool that can be used by practitioners to better understand and ultimately leverage AI studies.

RECENT FINDINGS

The increasing interest in machine learning across medicine is reflected in a greater utilization of AI in recent medical literature. The process of designing machine learning studies includes study design, model choice, data collection/handling, model development, training, testing, and interpretation. Recent studies leveraging ML in orthopaedics provide useful examples for future research endeavors. This manuscript intends to create a guide discussing the use of machine learning and artificial intelligence in orthopaedic surgery research. Our review outlines the process of creating a machine learning algorithm and discusses the different model types, utilizing examples from recent orthopaedic literature to illustrate the techniques involved.

Preoperative paraspinal neck muscle characteristics predict early onset adjacent segment degeneration in anterior cervical fusion patients: A machine-learning modeling analysis

Early onset adjacent segment degeneration (ASD) can be found within six months after anterior cervical discectomy and fusion (ACDF). Deficits in deep paraspinal neck muscles may be related to early onset ASD. This study aimed to determine whether the morphometry of preoperative deep neck muscles (multifidus and semispinalis cervicis) predicted early onset ASD in patients with ACDF. Thirty-two cases of early onset ASD after a two-level ACDF and 30 matched non-ASD cases were identified from a large-scale cohort. The preoperative total cross-sectional area (CSA) of bilateral deep neck muscles and the lean muscle CSAs from C3 to C7 levels were measured manually on T2-weighted magnetic resonance imaging. Paraspinal muscle CSA asymmetry at each level was calculated. A support vector machine (SVM) algorithm was used to identify demographic, radiographic, and/or muscle parameters that predicted proximal/distal ASD development. No significant between-group differences in demographic or preoperative radiographic data were noted (mean age: 52.4 ± 10.9 years). ACDFs comprised C3 to C5 (n = 9), C4 to C6 (n = 20), and C5 to C7 (n = 32) cases. Eighteen, eight, and six patients had proximal, distal, or both ASD, respectively. The SVM model achieved high accuracy (96.7%) and an area under the curve (AUC = 0.97) for predicting early onset ASD. Asymmetry of fat at C5 (coefficient: 0.06), and standardized measures of C7 lean (coefficient: 0.05) and total CSA measures (coefficient: 0.05) were the strongest predictors of early onset ASD. This is the first study to show that preoperative deep neck muscle CSA, composition, and asymmetry at C5 to C7 independently predicted postoperative early onset ASD in patients with ACDF. Paraspinal muscle assessments are recommended to identify high-risk patients for personalized intervention.

Machine Learning Solutions for Osteoporosis-A Review

Osteoporosis and its clinical consequence, bone fracture, is a multifactorial disease that has been the object of extensive research. Recent advances in machine learning (ML) have enabled the field of artificial intelligence (AI) to make impressive breakthroughs in complex data environments where human capacity to identify high-dimensional relationships is limited. The field of osteoporosis is one such domain, notwithstanding technical and clinical concerns regarding the application of ML methods. This qualitative review is intended to outline some of these concerns and to inform stakeholders interested in applying AI for improved management of osteoporosis. A systemic search in PubMed and Web of Science resulted in 89 studies for inclusion in the review. These covered one or more of four main areas in osteoporosis management: bone properties assessment (n = 13), osteoporosis classification (n = 34), fracture detection (n = 32), and risk prediction (n = 14). Reporting and methodological quality was determined by means of a 12-point checklist. In general, the studies were of moderate quality with a wide range (mode score 6, range 2 to 11). Major limitations were identified in a significant number of studies. Incomplete reporting, especially over model selection, inadequate splitting of data, and the low proportion of studies with external validation were among the most frequent problems. However, the use of images for opportunistic osteoporosis diagnosis or fracture detection emerged as a promising approach and one of the main contributions that ML could bring to the osteoporosis field. Efforts to develop ML-based models for identifying novel fracture risk factors and improving fracture prediction are additional promising lines of research. Some studies also offered insights into the potential for model-based decision-making. Finally, to avoid some of the common pitfalls, the use of standardized checklists in developing and sharing the results of ML models should be encouraged. © 2021 American Society for Bone and Mineral Research (ASBMR).

A Statistical Approach Regarding the Diagnosis of Osteoporosis and Osteopenia From DXA: Are We Underdiagnosing Osteoporosis?

Osteoporosis and osteopenia are diagnosed most commonly by evaluating the lowest T‐score of BMD measurements, typically taken at three sites: the L1‐L4 lumbar spine, femoral neck, and total hip. This study aimed to evaluate the effect of using all three BMD measurements and multivariate statistical theory to evaluate how the diagnoses of osteoporosis and osteopenia change in simulation studies and in real data. First, it was found that the T‐scores from these three BMD measurements rarely give concordant diagnoses using the same World Health Organization (WHO) and International Society for Clinical Densitometry (ISCD) guidelines, so that the diagnosis strongly depends on the BMD sites measured. Next, strong correlations were found between the BMD measurements at different sites within the same person, which resulted in increased congruence/concordance between the diagnoses obtained from the BMD T‐scores. Multivariate statistical theory was used to show that the joint distribution of the BMD T‐scores at different sites follows a multivariate t distribution and found that the marginal distribution of any BMD T‐score follows a univariate t distribution. Confidence ellipsoids were derived that are equivalent to the univariate WHO/ISCD thresholds for osteoporosis (T‐score ≤−2.5) and osteopenia (−2.5 < T‐score <−1). The study found that more patients are diagnosed with osteoporosis using the multivariate version of the WHO/ISCD guidelines rather than the current WHO/ISCD guidelines in both real data and simulation studies. Diagnoses of osteoporosis using the statistics derived method were also associated with higher FRAX (fracture risk assessment tool) probabilities of major osteoporotic (p = 0.001) and hip fractures (p = 2.2 × 10⁻⁶). In conclusion, this study shows that considering all three BMD T‐scores is potentially more informative than using the single lowest BMD T‐score. © 2020 The Authors. JBMR Plus published by Wiley Periodicals LLC. on behalf of American Society for Bone and Mineral Research.

The Role of Machine Learning in Spine Surgery: The Future Is Now

The recent influx of machine learning centered investigations in the spine surgery literature has led to increased enthusiasm as to the prospect of using artificial intelligence to create clinical decision support tools, optimize postoperative outcomes, and improve technologies used in the operating room. However, the methodology underlying machine learning in spine research is often overlooked as the subject matter is quite novel and may be foreign to practicing spine surgeons. Improper application of machine learning is a significant bioethics challenge, given the potential consequences of over- or underestimating the results of such studies for clinical decision-making processes. Proper peer review of these publications requires a baseline familiarity of the language associated with machine learning, and how it differs from classical statistical analyses. This narrative review first introduces the overall field of machine learning and its role in artificial intelligence, and defines basic terminology. In addition, common modalities for applying machine learning, including classification and regression decision trees, support vector machines, and artificial neural networks are examined in the context of examples gathered from the spine literature. Lastly, the ethical challenges associated with adapting machine learning for research related to patient care, as well as future perspectives on the potential use of machine learning in spine surgery, are discussed specifically.