Analyzing Racial Differences in Imaging Joint Replacement Registries Using Generative Artificial Intelligence: Advancing Orthopaedic Data Equity.

Background: Discrepancies in medical data sets can perpetuate bias, especially when training deep learning models, potentially leading to biased outcomes in clinical applications. Understanding these biases is crucial for the development of equitable healthcare technologies. This study employs generative deep learning technology to explore and understand radiographic differences based on race among patients undergoing total hip arthroplasty. Methods: Utilizing a large institutional registry, we retrospectively analyzed pelvic radiographs from total hip arthroplasty patients, characterized by demographics and image features. Denoising diffusion probabilistic models generated radiographs conditioned on demographic and imaging characteristics. Fréchet Inception Distance assessed the generated image quality, showing the diversity and realism of the generated images. Sixty transition videos were generated that showed transforming White pelvises to their closest African American counterparts and vice versa while controlling for patients' sex, age, and body mass index. Two expert surgeons and 2 radiologists carefully studied these videos to understand the systematic differences that are present in the 2 races' radiographs. Results: Our data set included 480,407 pelvic radiographs, with a predominance of White patients over African Americans. The generative denoising diffusion probabilistic model created high-quality images and reached an Fréchet Inception Distance of 6.8. Experts identified 6 characteristics differentiating races, including interacetabular distance, osteoarthritis degree, obturator foramina shape, femoral neck-shaft angle, pelvic ring shape, and femoral cortical thickness. Conclusions: This study demonstrates the potential of generative models for understanding disparities in medical imaging data sets. By visualizing race-based differences, this method aids in identifying bias in downstream tasks, fostering the development of fairer healthcare practices.

Uncertainty-Aware Deep Learning Characterization of Knee Radiographs for Large-Scale Registry Creation.

BACKGROUND: We present an automated image ingestion pipeline for a knee radiography registry, integrating a multilabel image-semantic classifier with conformal prediction-based uncertainty quantification and an object detection model for knee hardware. METHODS: Annotators retrospectively classified 26,000 knee images detailing presence, laterality, prostheses, and radiographic views. They further annotated surgical construct locations in 11,841 knee radiographs. An uncertainty-aware multilabel EfficientNet-based classifier was trained to identify the knee laterality, implants, and radiographic view. A classifier trained with embeddings from the EfficientNet model detected out-of-domain images. An object detection model was trained to identify 20 different knee implants. Model performance was assessed against a held-out internal and an external dataset using per-class F1 score, accuracy, sensitivity, and specificity. Conformal prediction was evaluated with marginal coverage and efficiency. RESULTS: Classification Model with Conformal Prediction: F1 scores for each label output > 0.98. Coverage of each label output was >0.99 and the average efficiency was 0.97. DOMAIN DETECTION MODEL: The F1 score was 0.99, with precision and recall for knee radiographs of 0.99. OBJECT DETECTION MODEL: Mean average precision across all classes was 0.945 and ranged from 0.695 to 1.000. Average precision and recall across all classes were 0.950 and 0.886. CONCLUSIONS: We present a multilabel classifier with domain detection and an object detection model to characterize knee radiographs. Conformal prediction enhances transparency in cases when the model is uncertain.

The Impact of Leg Length and Offset Change on Dislocation Risk Following Primary Total Hip Arthroplasty.

BACKGROUND: Soft tissue management in total hip arthroplasty includes appropriate restoration and/or alteration of leg length (LL) and offset to re-establish natural hip biomechanics. The purpose of this study was to evaluate the effect of LL and offset-derived variables in a multivariable survival model for dislocation. METHODS: Clinical, surgical, and radiographic data was retrospectively acquired for 12,582 patients undergoing primary total hip arthroplasty at a single institution from 1998 to 2018. There were twelve variables derived from preoperative and postoperative radiographs related to LL and offset that were measured using a validated automated algorithm. These measurements, as well as other modifiable and nonmodifiable surgical, clinical, and demographic factors, were used to determine hazard ratios for dislocation risk. RESULTS: None of the LL or offset variables conferred significant risk or protective benefit for dislocation risk. By contrast, all other variables included in the multivariable model demonstrated a statistically significant effect on dislocation risk with a minimum effect size of 28% (range 0.72 to 1.54) (sex, surgical approach, acetabular liner type, femoral head size, neurologic disease, spine disease, and prior spine surgery). CONCLUSIONS: Contrary to traditional teaching and our hypothesis, operative changes in LL and offset did not demonstrate any clinically or statistically significant effect in this large and well-characterized cohort. This does not imply that these variables are not important in individual cases, but rather suggests the overall impact of LL and offset changes is relatively minor for dislocation risk compared to other variables that were found to be highly clinically and statistically significant in this population. These results may also suggest that surgeons do a good job of restoring native LL and offset for patients, which may mitigate their analyzed impact.

Blood metal concentrations and cardiac structure and function in total joint arthroplasty patients.

BACKGROUND: There is concern regarding potential long-term cardiotoxicity with systemic distribution of metals in total joint arthroplasty (TJA) patients. AIM: To determine the association of commonly used implant metals with echocardiographic measures in TJA patients. METHODS: The study comprised 110 TJA patients who had a recent history of high chromium, cobalt or titanium concentrations. Patients underwent two-dimensional, three-dimensional, Doppler and speckle-strain transthoracic echocardiography and a blood draw to measure metal concentrations. Age and sex-adjusted linear and logistic regression models were used to examine the association of metal concentrations (exposure) with echocardiographic measures (outcome). RESULTS: Higher cobalt concentrations were associated with increased left ventricular end-diastolic volume (estimate 5.09; 95%CI: 0.02-10.17) as well as left atrial and right ventricular dilation, particularly in men but no changes in cardiac function. Higher titanium concentrations were associated with a reduction in left ventricle global longitudinal strain (estimate 0.38; 95%CI: 0.70 to 0.06) and cardiac index (estimate 0.08; 95%CI, -0.15 to -0.01). CONCLUSION: Elevated cobalt and titanium concentrations may be associated with structural and functional cardiac changes in some patients. Longitudinal studies are warranted to better understand the systemic effects of metals in TJA patients.

Deep learning classification of pediatric spinal radiographs for use in large scale imaging registries.

PURPOSE: The purpose of this study is to develop and apply an algorithm that automatically classifies spine radiographs of pediatric scoliosis patients. METHODS: Anterior-posterior (AP) and lateral spine radiographs were extracted from the institutional picture archive for patients with scoliosis. Overall, there were 7777 AP images and 5621 lateral images. Radiographs were manually classified into ten categories: two preoperative and three postoperative categories each for AP and lateral images. The images were split into training, validation, and testing sets (70:15:15 proportional split). A deep learning classifier using the EfficientNet B6 architecture was trained on the spine training set. Hyperparameters and model architecture were tuned against the performance of the models in the validation set. RESULTS: The trained classifiers had an overall accuracy on the test set of 1.00 on 1166 AP images and 1.00 on 843 lateral images. Precision ranged from 0.98 to 1.00 in the AP images, and from 0.91 to 1.00 on the lateral images. Lower performance was observed on classes with fewer than 100 images in the dataset. Final performance metrics were calculated on the assigned test set, including accuracy, precision, recall, and F1 score (the harmonic mean of precision and recall). CONCLUSIONS: A deep learning convolutional neural network classifier was trained to a high degree of accuracy to distinguish between 10 categories pre- and postoperative spine radiographs of patients with scoliosis. Observed performance was higher in more prevalent categories. These models represent an important step in developing an automatic system for data ingestion into large, labeled imaging registries.

Overview of Artificial Intelligence Research Within Hip and Knee Arthroplasty.

Hip and knee arthroplasty are high-volume procedures undergoing rapid growth. The large volume of procedures generates a vast amount of data available for next-generation analytics. Techniques in the field of artificial intelligence (AI) can assist in large-scale pattern recognition and lead to clinical insights. AI methodologies have become more prevalent in orthopaedic research. This review will first describe an overview of AI in the medical field, followed by a description of the 3 arthroplasty research areas in which AI is commonly used (risk modeling, automated radiographic measurements, arthroplasty registry construction). Finally, we will discuss the next frontier of AI research focusing on model deployment and uncertainty quantification.

Synthetically enhanced: unveiling synthetic data's potential in medical imaging research.

BACKGROUND: Chest X-rays (CXR) are essential for diagnosing a variety of conditions, but when used on new populations, model generalizability issues limit their efficacy. Generative AI, particularly denoising diffusion probabilistic models (DDPMs), offers a promising approach to generating synthetic images, enhancing dataset diversity. This study investigates the impact of synthetic data supplementation on the performance and generalizability of medical imaging research. METHODS: The study employed DDPMs to create synthetic CXRs conditioned on demographic and pathological characteristics from the CheXpert dataset. These synthetic images were used to supplement training datasets for pathology classifiers, with the aim of improving their performance. The evaluation involved three datasets (CheXpert, MIMIC-CXR, and Emory Chest X-ray) and various experiments, including supplementing real data with synthetic data, training with purely synthetic data, and mixing synthetic data with external datasets. Performance was assessed using the area under the receiver operating curve (AUROC). FINDINGS: Adding synthetic data to real datasets resulted in a notable increase in AUROC values (up to 0.02 in internal and external test sets with 1000% supplementation, p-value <0.01 in all instances). When classifiers were trained exclusively on synthetic data, they achieved performance levels comparable to those trained on real data with 200%-300% data supplementation. The combination of real and synthetic data from different sources demonstrated enhanced model generalizability, increasing model AUROC from 0.76 to 0.80 on the internal test set (p-value <0.01). INTERPRETATION: Synthetic data supplementation significantly improves the performance and generalizability of pathology classifiers in medical imaging. FUNDING: Dr. Gichoya is a 2022 Robert Wood Johnson Foundation Harold Amos Medical Faculty Development Program and declares support from RSNA Health Disparities grant (#EIHD2204), Lacuna Fund (#67), Gordon and Betty Moore Foundation, NIH (NIBIB) MIDRC grant under contracts 75N92020C00008 and 75N92020C00021, and NHLBI Award Number R01HL167811.

Surgical Approach and Body Mass Index Impact Risk of Wound Complications Following Total Hip Arthroplasty.

BACKGROUND: Previous studies have suggested that wound complications may differ by surgical approach after total hip arthroplasty (THA), with particular attention toward the direct anterior approach (DAA). However, there is a paucity of data documenting wound complication rates by surgical approach and the impact of concomitant patient factors, namely body mass index (BMI). This investigation sought to determine the rates of wound complications by surgical approach and identify BMI thresholds that portend differential risk. METHODS: This multicenter study retrospectively evaluated all primary THA patients from 2010 to 2023. Patients were classified by skin incision as having a laterally based approach (posterior or lateral approach) or DAA (longitudinal incision). We identified 17,111 patients who had 11,585 laterally based (68%) and 5,526 (32%) DAA THAs. The mean age was 65 years (range, 18 to 100), 8,945 patients (52%) were women, and the mean BMI was 30 (range, 14 to 79). Logistic regression and cut-point analyses were performed to identify an optimal BMI cutoff, overall and by approach, with respect to the risk of wound complications at 90 days. RESULTS: The 90-day risk of wound complications was higher in the DAA group versus the laterally based group, with an absolute risk of 3.6% versus 2.6% and a multivariable adjusted odds ratio of 1.5 (P < .001). Cut-point analyses demonstrated that the risk of wound complications increased steadily for both approaches, but most markedly above a BMI of 33. CONCLUSIONS: Wound complications were higher after longitudinal incision DAA THA compared to laterally based approaches, with a 1% higher absolute risk and an adjusted odds ratio of 1.5. Furthermore, BMI was an independent risk factor for wound complications regardless of surgical approach, with an optimal cut-point BMI of 33 for both approaches. These data can be used by surgeons to help consider the risks and benefits of approach selection. LEVEL OF EVIDENCE: Level III.

How are Oral Antibiotics Being Used in Total Joint Arthroplasty? A Review of the Literature.

While the role and benefit of perioperative intravenous (IV) antibiotics in patients undergoing total joint arthroplasty (TJA) is well-established, oral antibiotic use in TJA remains a controversial topic with wide variations in practice patterns. With this review, we aimed to better educate the orthopedic surgeon on when and how oral antibiotics may be used most effectively in TJA patients, and to identify gaps in the literature that could be clarified with targeted research. Extended oral antibiotic prophylaxis (EOAP) use in high-risk primary, aseptic revision, and exchange TJA for infection may be useful in decreasing periprosthetic joint infection (PJI) rates. When prescribing oral antibiotics either as EOAP or for draining wounds, patient factors, type of surgery, and type of infectious organisms should be considered in order to optimally prevent and treat PJI. It is important to maintain antibiotic stewardship by administering the proper duration, dose, and type of antibiotics and by consulting infectious disease when necessary.

Artificial intelligence-based three-dimensional templating for total joint arthroplasty planning: a scoping review.

PURPOSE: The purpose of this review is to evaluate the current status of research on the application of artificial intelligence (AI)-based three-dimensional (3D) templating in preoperative planning of total joint arthroplasty. METHODS: This scoping review followed the PRISMA, PRISMA-ScR guidelines, and five stage methodological framework for scoping reviews. Studies of patients undergoing primary or revision joint arthroplasty surgery that utilised AI-based 3D templating for surgical planning were included. Outcome measures included dataset and model development characteristics, AI performance metrics, and time performance. After AI-based 3D planning, the accuracy of component size and placement estimation and postoperative outcome data were collected. RESULTS: Nine studies satisfied inclusion criteria including a focus on computed tomography (CT) or magnetic resonance imaging (MRI)-based AI templating for use in hip or knee arthroplasty. AI-based 3D templating systems reduced surgical planning time and improved implant size/position and imaging feature estimation compared to conventional radiographic templating. Several components of data processing and model development and testing were insufficiently covered in the studies included in this scoping review. CONCLUSIONS: AI-based 3D templating systems have the potential to improve preoperative planning for joint arthroplasty surgery. This technology offers more accurate and personalized preoperative planning, which has potential to improve functional outcomes for patients. However, deficiencies in several key areas, including data handling, model development, and testing, can potentially hinder the reproducibility and reliability of the methods proposed. As such, further research is needed to definitively evaluate the efficacy and feasibility of these systems.

THA-AID: Deep Learning Tool for Total Hip Arthroplasty Automatic Implant Detection With Uncertainty and Outlier Quantification.

BACKGROUND: Revision total hip arthroplasty (THA) requires preoperatively identifying in situ implants, a time-consuming and sometimes unachievable task. Although deep learning (DL) tools have been attempted to automate this process, existing approaches are limited by classifying few femoral and zero acetabular components, only classify on anterior-posterior (AP) radiographs, and do not report prediction uncertainty or flag outlier data. METHODS: This study introduces Total Hip Arhtroplasty Automated Implant Detector (THA-AID), a DL tool trained on 241,419 radiographs that identifies common designs of 20 femoral and 8 acetabular components from AP, lateral, or oblique views and reports prediction uncertainty using conformal prediction and outlier detection using a custom framework. We evaluated THA-AID using internal, external, and out-of-domain test sets and compared its performance with human experts. RESULTS: THA-AID achieved internal test set accuracies of 98.9% for both femoral and acetabular components with no significant differences based on radiographic view. The femoral classifier also achieved 97.0% accuracy on the external test set. Adding conformal prediction increased true label prediction by 0.1% for acetabular and 0.7 to 0.9% for femoral components. More than 99% of out-of-domain and >89% of in-domain outlier data were correctly identified by THA-AID. CONCLUSIONS: The THA-AID is an automated tool for implant identification from radiographs with exceptional performance on internal and external test sets and no decrement in performance based on radiographic view. Importantly, this is the first study in orthopedics to our knowledge including uncertainty quantification and outlier detection of a DL model.

Whole Blood Metal Levels in the Setting of an Oncologic Endoprosthesis: Is There Cause for Concern?

BACKGROUND: Massive modular endoprostheses have become a primary means of reconstruction after oncologic resection of a lower extremity tumor. These implants are commonly made with cobalt-chromium alloys that can undergo wear and corrosion, releasing cobalt and chromium ions into the surrounding tissue and blood. However, there are few studies about the blood metal levels in these patients. QUESTION/PURPOSE: What is the whole blood cobalt and chromium ion level in patients with massive modular endoprostheses? METHODS: We performed a cross-sectional study of our total joints registry to identify patients with a history of an endoprosthetic reconstruction performed at our institution. Patients who were alive at the time of our review in addition to those undergoing an endoprosthetic reconstruction after an oncologic resection were included. Whole blood samples were obtained from 27 (14 male and 13 female) patients with a history of a lower extremity oncologic endoprosthesis. The median time from surgery to blood collection was 8 years (range 6 months to 32 years). Blood samples were collected and stored in metal-free ethylenediaminetetraacetic acid tubes. Samples were analyzed on an inductively coupled plasma mass spectrometer in an International Organization for Standardization seven-class clean room using polytetrafluoroethylene-coated instruments to reduce the risk of metal contamination. The analytical measuring range was 1 to 200 ng/mL for chromium and cobalt. Cobalt and chromium levels were considered elevated when the blood level was ≥ 1 ppb. RESULTS: Cobalt levels were elevated in 59% (16 of 27) of patients, and chromium levels were elevated in 26% (seven of 27). In patients with elevated metal ion values, 15 of 17 patients had a reconstruction using a Stryker/Howmedica Global Modular Replacement System implant. CONCLUSION: Blood metal levels were elevated in patients who received reconstructions using modular oncology endoprostheses Future work is needed to establish appropriate follow-up routines and determine whether and when systemic complications occur because of elevated metal levels and how to potentially address these elevated levels when complications occur. Prospective and retrospective collaboration between multiple centers and specialty societies will be necessary to address these unknown questions in this potentially vulnerable patient group. LEVEL OF EVIDENCE: Level IV, therapeutic study.

THA-Net: A Deep Learning Solution for Next-Generation Templating and Patient-specific Surgical Execution.

BACKGROUND: This study introduces THA-Net, a deep learning inpainting algorithm for simulating postoperative total hip arthroplasty (THA) radiographs from a single preoperative pelvis radiograph input, while being able to generate predictions either unconditionally (algorithm chooses implants) or conditionally (surgeon chooses implants). METHODS: The THA-Net is a deep learning algorithm which receives an input preoperative radiograph and subsequently replaces the target hip joint with THA implants to generate a synthetic yet realistic postoperative radiograph. We trained THA-Net on 356,305 pairs of radiographs from 14,357 patients from a single institution's total joint registry and evaluated the validity (quality of surgical execution) and realism (ability to differentiate real and synthetic radiographs) of its outputs against both human-based and software-based criteria. RESULTS: The surgical validity of synthetic postoperative radiographs was significantly higher than their real counterparts (mean difference: 0.8 to 1.1 points on 10-point Likert scale, P < .001), but they were not able to be differentiated in terms of realism in blinded expert review. Synthetic images showed excellent validity and realism when analyzed with already validated deep learning models. CONCLUSION: We developed a THA next-generation templating tool that can generate synthetic radiographs graded higher on ultimate surgical execution than real radiographs from training data. Further refinement of this tool may potentiate patient-specific surgical planning and enable technologies such as robotics, navigation, and augmented reality (an online demo of THA-Net is available at: https://demo.osail.ai/tha_net).

Anonymizing Radiographs Using an Object Detection Deep Learning Algorithm.

Radiographic markers contain protected health information that must be removed before public release. This work presents a deep learning algorithm that localizes radiographic markers and selectively removes them to enable de-identified data sharing. The authors annotated 2000 hip and pelvic radiographs to train an object detection computer vision model. Data were split into training, validation, and test sets at the patient level. Extracted markers were then characterized using an image processing algorithm, and potentially useful markers (eg, "L" and "R") without identifying information were retained. The model achieved an area under the precision-recall curve of 0.96 on the internal test set. The de-identification accuracy was 100% (400 of 400), with a de-identification false-positive rate of 1% (eight of 632) and a retention accuracy of 93% (359 of 386) for laterality markers. The algorithm was further validated on an external dataset of chest radiographs, achieving a de-identification accuracy of 96% (221 of 231). After fine-tuning the model on 20 images from the external dataset to investigate the potential for improvement, a 99.6% (230 of 231, P = .04) de-identification accuracy and decreased false-positive rate of 5% (26 of 512) were achieved. These results demonstrate the effectiveness of a two-pass approach in image de-identification. Keywords: Conventional Radiography, Skeletal-Axial, Thorax, Experimental Investigations, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2023 See also the commentary by Chang and Li in this issue.

A Stepwise Approach to Analyzing Musculoskeletal Imaging Data With Artificial Intelligence.

The digitization of medical records and expanding electronic health records has created an era of "Big Data" with an abundance of available information ranging from clinical notes to imaging studies. In the field of rheumatology, medical imaging is used to guide both diagnosis and treatment of a wide variety of rheumatic conditions. Although there is an abundance of data to analyze, traditional methods of image analysis are human resource intensive. Fortunately, the growth of artificial intelligence (AI) may be a solution to handle large datasets. In particular, computer vision is a field within AI that analyzes images and extracts information. Computer vision has impressive capabilities and can be applied to rheumatologic conditions, necessitating a need to understand how computer vision works. In this article, we provide an overview of AI in rheumatology and conclude with a five step process to plan and conduct research in the field of computer vision. The five steps include (1) project definition, (2) data handling, (3) model development, (4) performance evaluation, and (5) deployment into clinical care.

Few-shot biomedical image segmentation using diffusion models: Beyond image generation.

BACKGROUND: Medical image analysis pipelines often involve segmentation, which requires a large amount of annotated training data, which is time-consuming and costly. To address this issue, we proposed leveraging generative models to achieve few-shot image segmentation. METHODS: We trained a denoising diffusion probabilistic model (DDPM) on 480,407 pelvis radiographs to generate 256 âœ• 256 px synthetic images. The DDPM was conditioned on demographic and radiologic characteristics and was rigorously validated by domain experts and objective image quality metrics (Frechet inception distance [FID] and inception score [IS]). For the next step, three landmarks (greater trochanter [GT], lesser trochanter [LT], and obturator foramen [OF]) were annotated on 45 real-patient radiographs; 25 for training and 20 for testing. To extract features, each image was passed through the pre-trained DDPM at three timesteps and for each pass, features from specific blocks were extracted. The features were concatenated with the real image to form an image with 4225 channels. The feature-set was broken into random patches, which were fed to a U-Net. Dice Similarity Coefficient (DSC) was used to compare the performance with a vanilla U-Net trained on radiographs. RESULTS: Expert accuracy was 57.5 % in determining real versus generated images, while the model reached an FID = 7.2 and IS = 210. The segmentation UNet trained on the 20 feature-sets achieved a DSC of 0.90, 0.84, and 0.61 for OF, GT, and LT segmentation, respectively, which was at least 0.30 points higher than the naively trained model. CONCLUSION: We demonstrated the applicability of DDPMs as feature extractors, facilitating medical image segmentation with few annotated samples.

Demystifying Statistics and Machine Learning in Analysis of Structured Tabular Data.

Electronic health records have facilitated the extraction and analysis of a vast amount of data with many variables for clinical care and research. Conventional regression-based statistical methods may not capture all the complexities in high-dimensional data analysis. Therefore, researchers are increasingly using machine learning (ML)-based methods to better handle these more challenging datasets for the discovery of hidden patterns in patients' data and for classification and predictive purposes. This article describes commonly used ML methods in structured data analysis with examples in orthopedic surgery. We present practical considerations in starting an ML project and appraising published studies in this field.

An Overview of Machine Learning in Orthopedic Surgery: An Educational Paper.

The growth of artificial intelligence combined with the collection and storage of large amounts of data in the electronic medical record collection has created an opportunity for orthopedic research and translation into the clinical environment. Machine learning (ML) is a type of artificial intelligence tool well suited for processing the large amount of available data. Specific areas of ML frequently used by orthopedic surgeons performing total joint arthroplasty include tabular data analysis (spreadsheets), medical imaging processing, and natural language processing (extracting concepts from text). Previous studies have discussed models able to identify fractures in radiographs, identify implant type in radiographs, and determine the stage of osteoarthritis based on walking analysis. Despite the growing popularity of ML, there are limitations including its reliance on "good" data, potential for overfitting, long life cycle for creation, and ability to only perform one narrow task. This educational article will further discuss a general overview of ML, discussing these challenges and including examples of successfully published models.

The use of deep learning in medical imaging to improve spine care: A scoping review of current literature and clinical applications.

Background: Artificial intelligence is a revolutionary technology that promises to assist clinicians in improving patient care. In radiology, deep learning (DL) is widely used in clinical decision aids due to its ability to analyze complex patterns and images. It allows for rapid, enhanced data, and imaging analysis, from diagnosis to outcome prediction. The purpose of this study was to evaluate the current literature and clinical utilization of DL in spine imaging. Methods: This study is a scoping review and utilized the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to review the scientific literature from 2012 to 2021. A search in PubMed, Web of Science, Embased, and IEEE Xplore databases with syntax specific for DL and medical imaging in spine care applications was conducted to collect all original publications on the subject. Specific data was extracted from the available literature, including algorithm application, algorithms tested, database type and size, algorithm training method, and outcome of interest. Results: A total of 365 studies (total sample of 232,394 patients) were included and grouped into 4 general applications: diagnostic tools, clinical decision support tools, automated clinical/instrumentation assessment, and clinical outcome prediction. Notable disparities exist in the selected algorithms and the training across multiple disparate databases. The most frequently used algorithms were U-Net and ResNet. A DL model was developed and validated in 92% of included studies, while a pre-existing DL model was investigated in 8%. Of all developed models, only 15% of them have been externally validated. Conclusions: Based on this scoping review, DL in spine imaging is used in a broad range of clinical applications, particularly for diagnosing spinal conditions. There is a wide variety of DL algorithms, database characteristics, and training methods. Future studies should focus on external validation of existing models before bringing them into clinical use.

Application of Natural Language Processing in Total Joint Arthroplasty: Opportunities and Challenges.

Total joint arthroplasty is becoming one of the most common surgeries within the United States, creating an abundance of analyzable data to improve patient experience and outcomes. Unfortunately, a large majority of this data is concealed in electronic health records only accessible by manual extraction, which takes extensive time and resources. Natural language processing (NLP), a field within artificial intelligence, may offer a viable alternative to manual extraction. Using NLP, a researcher can analyze written and spoken data and extract data in an organized manner suitable for future research and clinical use. This article will first discuss common subtasks involved in an NLP pipeline, including data preparation, modeling, analysis, and external validation, followed by examples of NLP projects. Challenges and limitations of NLP will be discussed, closing with future directions of NLP projects, including large language models.