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).

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.

The Frank Stinchfield Award: Assembly and Dissociation Forces Differ Between Commonly Used Dual Mobility Implants: A Biomechanical Study.

BACKGROUND: Intraprosthetic dissociation (IPD) is a complication unique to dual mobility (DM) implants where the outer polyethylene head dissociates from the inner femoral head. Increasing reports of IPD at the time of closed reduction of large head DM dislocations prompted this biomechanical study evaluating the assembly and dissociation forces of DM heads. METHODS: We tested 17 polyethylene DM heads from 5 vendors. Of the heads, 12 were highly cross-linked polyethylene (4 vendors) and 5 were infused with vitamin E (2 vendors). Heads were between 46 and 47 mm in diameter, accepting a 28 mm-inner ceramic head. Implants were assembled and disassembled using a servohydraulic machine that recorded the forces and torques applied during testing. Dissociation was tested via both axial pull-out and lever-out techniques, where lever-out simulated stem-on-acetabular component impingement. RESULTS: The initial maximum assembly force was significantly different between all vendors (P < .01) and decreased for all implants with subsequent assembly. Vendor 4-E (Link with vitamin E) heads required the highest assembly force (1,831.9 ± 81.95 N), followed by Vendor 3 (Smith & Nephew), Vendor 5 (DePuy Synthes), Vendor 1-E (Zimmer Biomet with vitamin E), Vendor 2 (Stryker), and Vendor 1 (Zimmer Biomet Arcom). Vendor 4-E implants showed the greatest dissociation resistance in both pull-out (2,059.89 N, n = 1) and lever-out (38.95 ± 2.79 Nm) tests. Vendor 1-E implants with vitamin E required higher assembly force, dissociation force, and energy than Vendor 1 heads without vitamin E. CONCLUSIONS: There were notable differences in DM assembly and dissociation forces between implants. Diminishing force was required for assembly with each additional trial across vendors. Vendor 4-E DM heads required the highest assembly and dissociation forces. Vitamin E appeared to increase the assembly and dissociation forces. Based on these results, DM polyethylene heads should not be reimplanted after dissociation, and there may be a role for establishing a minimum dissociation energy standard to minimize IPD risk.

A Randomized Clinical Trial of Direct Anterior Versus Mini-Posterior Total Hip Arthroplasty: Small, Early Functional Differences Did Not Lead to Meaningful Clinical Differences at 7.5 Years.

BACKGROUND: Our previously reported randomized clinical trial of direct anterior approach (DAA) versus mini-posterior approach (MPA) total hip arthroplasty showed slightly faster initial recovery for patients who had a DAA and no differences in complications or clinical or radiographic outcomes beyond 8 weeks. The aims of the current study were to determine if early advantages of DAA led to meaningful clinical differences beyond 5 years and to identify differences in midterm complications. METHODS: Of the 101 original patients, 93 were eligible for follow-up at a mean of 7.5 years (range, 2.1 to 10). Clinical outcomes were compared with Harris Hip, 12-Item Short Form Health Survey, and Hip Disability and Osteoarthritis Outcomes Scores (HOOS) scores and subscores, complications, reoperations, and revisions. RESULTS: Harris Hip scores were similar (95.3 ± 6.0 versus 93.5 ± 10.3 for DAA and MPA, respectively, P = .79). The 12-Item Short Form Health Survey physical and mental scores were similar (46.2 ± 9.3 versus 46.2 ± 10.6, P = .79, and 52.3 ± 7.1 versus 55.2 ± 4.5, P = .07 in the DAA and MPA groups, respectively). The HOOS scores were similar (97.4 ± 7.9 versus 96.3 ± 6.7 for DAA and MPA, respectively, P = .07). The HOOS quality of life subscores were 96.9 ± 10.8 versus 92.3 ± 16.0 for DAA and MPA, respectively (P = .046). No clinical outcome met the minimally clinically important difference. There were 4 surgical complications in the DAA group (1 femoral loosening requiring revision, 1 dislocation treated closed, and 2 wound dehiscences requiring debridement), and 6 surgical complications in the MPA group (3 dislocations, 2 treated closed, and 1 revised to dual mobility; 2 intraoperative fractures treated with a cable; and 1 wound dehiscence treated nonoperatively). CONCLUSIONS: At a mean of 7.5 years, this randomized clinical trial demonstrated no clinically meaningful differences in outcomes, complications, reoperations, or revisions between DAA and MPA total hip arthroplasty. LEVEL OF EVIDENCE: IV.

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.

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.

Total knee replacement with an accelerometer-based, hand-held navigation system improves knee alignment: reliable in all patients.

BACKGROUND: Achieving adequate alignment has traditionally been an important goal in total knee arthroplasty to achieve long-term implant survival. While accelerometer-based hand-held navigation systems (ABN) has been introduced as a way to achieve alignment, there is a limited body of evidence on its accuracy, especially in patients under 65 years with differing etiologies for knee arthritis. This study aimed to assess the precision of a specific ABN system in restoring the mechanical axis and report surgical variables and complications, with particular attention to younger patients. METHODS: We conducted a retrospective review of 310 primary TKA performed with ABN from May 2016 to February 2021. The mean patient age was 67.4 (SD 8.9) years, with 43% under 65 years and mean body mass index of 33.2 (SD 6.8). The average surgical time was 96.8 min (57-171) and the average follow-up was 3.3 years (1.9-6.7). Data regarding length of stay, pain, range of motion (ROM), complications, and reinterventions were collected from the institutional joint arthroplasty registry and the medical records. Preoperative mechanical axis measurements and postoperative radiological data, including mechanical axis, component alignment and mechanical alignment outliers were analyzed. RESULTS: The mean preoperative mechanical axis was 175.4° (SD 7.6), with 248 knees (80%) in preoperative varus. The mean postoperative mechanical axis was 179.5° (SD 1.96) with 98% of knees falling within ± 3° of the neutral mechanical axis. Only 6 knees (2 varus, 4 valgus) fell outside the ± 3° range. And 3 knees (1 varus, 2 valgus) fell outside the ± 5° range. In the sagittal plane, 296 knees (95.5%) knees were within ± 3° of goal of 3 degrees of femoral flexion and 302 (97.4%) knees were within ± 2° of goal 1° of slope for tibial component. Far outliers (alignment outside ± 5° of targeted position) were found in 3 knees. Factors such as posttraumatic arthrosis, previous surgery, presence of retained hardware, and age below 65 years were not associated with increase in alignment outliers and far outliers. No complications related to the navigation system were observed. There were 22 complications and 20 reoperations, including 2 revisions for periprosthetic joint infection and 1 revision for flexion instability. Patients that required knee manipulation achieved an ultimate flexion of 110° (SD 14.1). CONCLUSIONS: The ABN system proved to be user-friendly and accurate in reducing alignment outliers in both coronal and sagittal planes in all patient populations. It offers a straightforward navigation solution while preserving surgeon autonomy and the use of traditional surgical tools. These findings advocate for the integration of this navigation system as a valuable tool to enhance the precision of TKA surgery in all patient groups.

Health and Socioeconomic Risk Factors for Unplanned Hospitalization Following Ambulatory Unicompartmental Knee Arthroplasty: Development of a Patient Selection Tool Using Machine Learning.

BACKGROUND: Identifying ambulatory surgical candidates at risk for adverse surgical outcomes can optimize outcomes. The purpose of this study was to develop and internally validate a machine learning (ML) algorithm to predict contributors to unexpected hospitalizations after ambulatory unicompartmental knee arthroplasty (UKA). METHODS: A total of 2,521 patients undergoing UKA from 2006 to 2018 were retrospectively evaluated. Patients admitted overnight postoperatively were identified as those who had a length of stay ≥ 1 day were analyzed with four individual ML models (ie, random forest, extreme gradient boosting, adaptive boosting, and elastic net penalized logistic regression). An additional model was produced as a weighted ensemble of the four individual algorithms. Area under the receiver operating characteristics (AUROC) compared predictive capacity of these models to conventional logistic regression techniques. RESULTS: Of the 2,521 patients identified, 103 (4.1%) required at least one overnight stay following ambulatory UKA. The ML ensemble model achieved the best performance based on discrimination assessed via internal validation (AUROC = 87.3), outperforming individual models and conventional logistic regression (AUROC = 81.9-85.7). The variables determined most important by the ensemble model were cumulative time in the operating room, utilization of general anesthesia, increasing age, and patient residency in more urban areas. The model was integrated into a web-based open-access application. CONCLUSION: The ensemble gradient-boosted ML algorithm demonstrated the highest performance in identifying factors contributing to unexpected hospitalizations in patients receiving UKA. This tool allows physicians and healthcare systems to identify patients at a higher risk of needing inpatient care after UKA.

Identifying Modifiable Cost Drivers of Outpatient Unicompartmental Knee Arthroplasty With Machine Learning.

BACKGROUND: Implementing tools that identify cost-saving opportunities for ambulatory orthopaedic surgeries can improve access to value-based care. We developed and internally validated a machine learning (ML) algorithm to predict cost drivers of total charges after ambulatory unicompartmental knee arthroplasty (UKA). METHODS: We queried the New York State Ambulatory Surgery and Services database to identify patients who underwent ambulatory, defined as <24 hours of care before discharge, elective UKA between 2014 and 2016. A total of 1,311 patients were included. The median costs after ambulatory UKA were $14,710. Patient demographics and intraoperative parameters were entered into 4 candidate ML algorithms. The most predictive model was selected following internal validation of candidate models, with conventional linear regression as a benchmark. Global variable importance and partial dependence curves were constructed to determine the impact of each input parameter on total charges. RESULTS: The gradient-boosted ensemble model outperformed all candidate algorithms and conventional linear regression. The major differential cost drivers of UKA identified (in decreasing order of magnitude) were increased operating room time, length of stay, use of regional and adjunctive periarticular analgesia, utilization of computer-assisted navigation, and routinely sending resected tissue to pathology. CONCLUSION: We developed and internally validated a supervised ML algorithm that identified operating room time, length of stay, use of computer-assisted navigation, regional primary anesthesia, adjunct periarticular analgesia, and routine surgical pathology as essential cost drivers of UKA. Following external validation, this tool may enable surgeons and health insurance providers optimize the delivery of value-based care to patients receiving outpatient UKA. LEVEL OF EVIDENCE: III.

Defining Clinically Meaningful Subgroups for Risk Stratification in Patients Undergoing Revision Total Hip Arthroplasty: A Combined Unsupervised and Supervised Machine Learning Approach.

BACKGROUND: Studies developing predictive models from large datasets to risk-stratify patients under going revision total hip arthroplasties (rTHAs) are limited. We used machine learning (ML) to stratify patients undergoing rTHA into risk-based subgroups. METHODS: We retrospectively identified 7,425 patients who underwent rTHA from a national database. An unsupervised random forest algorithm was used to partition patients into high-risk and low-risk strata based on similarities in rates of mortality, reoperation, and 25 other postoperative complications. A risk calculator was produced using a supervised ML algorithm to identify high-risk patients based on preoperative parameters. RESULTS: There were 3,135 and 4,290 patients identified in the high-risk and low-risk subgroups, respectively. Each group significantly differed by rate of 30-day mortalities, unplanned reoperations/readmissions, routine discharges, and hospital lengths of stay (P < .05). An Extreme Gradient Boosting algorithm identified preoperative platelets < 200, hematocrit > 35 or < 20, increasing age, albumin < 3, international normalized ratio > 2, body mass index > 35, American Society of Anesthesia class ≥ 3, blood urea nitrogen > 50 or < 30, creatinine > 1.5, diagnosis of hypertension or coagulopathy, and revision for periprosthetic fracture and infection as predictors of high risk. CONCLUSION: Clinically meaningful risk strata in patients undergoing rTHA were identified using an ML clustering approach. Preoperative labs, demographics, and surgical indications have the greatest impact on differentiating high versus low risk. LEVEL OF EVIDENCE: III.

The Fate of the Patient With Superficial Dehiscence Following Direct Anterior Total Hip Arthroplasty.

BACKGROUND: Direct anterior approach (DAA) total hip arthroplasty (THA) has been associated with higher rates of superficial incisional dehiscence. However, limited data are available regarding the outcomes following initial treatment of this complication. This study aimed to evaluate patient risk factors, reoperations, and revisions in those who developed superficial wound dehiscence following DAA THA. METHODS: We identified 3,687 patients who underwent a primary DAA THA between 2010 and 2019 from our enterprise total joint registry. Of these, 98 (2.7%) patients developed a superficial wound dehiscence requiring intervention [irrigation and debridement (n = 42) or wound care with or without antibiotics (n = 56)]. Dehiscence was noted at a median of 27 (range, 2-105) days. These patients were compared to patients who did not have a superficial wound complication (n = 3,589). Landmark survivorship analysis was performed to account for immortal time bias with a 45-day landmark time. RESULTS: Patients who had superficial wound dehiscence compared to those who did not, were more often women (64 versus 53%, P = .02) and had increased mean body mass index (33 versus 29, P < .001). There was no difference in 4-year survivorship free from any revision between cohorts (97 versus 98%, respectively, P = .14). There were 2 (2.0%) revisions in the superficial dehiscence group: 1 for periprosthetic joint infection and 1 for aseptic femoral loosening. CONCLUSION: Superficial wound dehiscence following DAA THA was associated with higher body mass index and was more common in women. Fortunately, with proper index management, the risk of revision THA and periprosthetic joint infection was not increased for these patients.

Classifying Bone Loss in Failed Stemmed Total Knee Arthroplasty: Determining Reliability.

BACKGROUND: Failed stemmed total knee arthroplasty (TKA) components present with varying degrees of bone loss and technical challenges. A classification system has been proposed based upon metaphyseal bone loss and diaphyseal cortical integrity. A validation study was performed to determine interobserver and intraobserver reliability at multiple institutions and with different levels of training. METHODS: An online survey with digital anteroposterior and lateral radiographs was sent to 5 arthroplasty surgeons and 5 adult reconstruction fellows. The survey included 62 cases with stemmed femoral and tibial components, considered failures and pending revision, and scored by each reviewer independently using the classification system. Each case was scored in 2 separate sessions. Interobserver and intraobserver reliability was assessed using the intraclass correlation coefficient (ICC). RESULTS: Interobserver grading for both the femur (0.69) and tibia (0.72) showed strong reliability among the attendings and fellows, with slightly stronger reliability in tibia cases. The intraclass correlation coefficient (ICC) for attendings and fellows was similar overall, demonstrating consistency of the grading regardless of training level. Intraobserver comparisons showed a strong ICC for attendings and fellows in femoral cases, while fellows had near-perfect ICC in tibia cases. Across all reviewers there was on average 93% agreement within 1 grade per case with the majority of the discrepancy occurring at the metaphyseal-diaphyseal junction. CONCLUSION: This classification demonstrated overall strong interobserver and intraobserver reliability, with 93% agreement within 1 grade of bone loss. With further education, this classification system can ultimately be used to standardize the degree of bone loss in failed stemmed components and help with preoperative planning.

Pubic Symphysis to Sacrococcygeal Joint: A Poor Correlate to Other Spinopelvic Measurements.

BACKGROUND: The hip-spine relationship is increasingly recognized as critical for optimizing stability following total hip arthroplasty (THA). However, these measurements are not routinely obtained during THA workup. It has been suggested that insight can be gained from supine antero-posterior pelvis radiograph, measuring the distance from the superior border of the pubic symphysis to the sacro-coccygeal joint (PSCD). This study assessed the correlation between PSCD and lateral lumbar radiographic metrics in a cohort of preoperative THA patients. METHODS: We retrospectively evaluated 250 consecutive patients who underwent THA with preoperative supine antero-posterior pelvis and lateral lumbar radiographs. The mean age was 68 years (range, 42 to 89), 61% were women, and the mean body mass index was 30 kg/m2 (range, 19 to 52). Two reviewers measured PSCD, pelvic tilt (PT), sacral slope (SS), pelvic incidence (PI), and lumbar lordosis (LL). Inter-observer reliability was calculated for all measurements, and correlation coefficients were calculated for PSCD with respect to PT, SS, PI, and LL. RESULTS: Correlations between PSCD and lumbar radiographic metrics were all statistically significant, except for PI in men but graded as "weak" or "very weak" for men and women, respectively, as follows: PT = -0.30 (P < .01) and -0.46 (P < .01); SS = 0.27 (P < .01) and 0.22 (P < .01); PI = -0.04 (P = .70) and -0.19 (P = .02); and LL = 0.45 (P < .01) and 0.30 (P < .01). Inter-observer reliability was graded as "strong" for every metric. CONCLUSION: The PSCD was weakly correlated with all evaluated lateral lumbar radiographic metrics in both sexes, despite strong inter-observer reliability. Therefore, PSCD cannot reliably serve as a proxy for evaluating the hip-spine relationship.

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.

Educational Overview of the Concept and Application of Computer Vision in Arthroplasty.

Image data has grown exponentially as systems have increased their ability to collect and store it. Unfortunately, there are limits to human resources both in time and knowledge to fully interpret and manage that data. Computer Vision (CV) has grown in popularity as a discipline for better understanding visual data. Computer Vision has become a powerful tool for imaging analytics in orthopedic surgery, allowing computers to evaluate large volumes of image data with greater nuance than previously possible. Nevertheless, even with the growing number of uses in medicine, literature on the fundamentals of CV and its implementation is mainly oriented toward computer scientists rather than clinicians, rendering CV unapproachable for most orthopedic surgeons as a tool for clinical practice and research. The purpose of this article is to summarize and review the fundamental concepts of CV application for the orthopedic surgeon and musculoskeletal researcher.

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.

Primary and Revision Total Hip Arthroplasty in Patients With Pulmonary Hypertension: High Perioperative Mortality and Medical Complications.

BACKGROUND: Perioperative medical management during total hip arthroplasty (THA) is continuously improving, allowing an increasing number of medically complex patients to undergo total joint arthroplasty. This study examined mortalities, medical complications, implant survivorships, and clinical outcomes of THA in patients who have pulmonary hypertension (HTN). METHODS: We identified 638 patients who had pulmonary HTN and underwent 508 primary THAs and 191 revision THAs from 2000 to 2016 at a tertiary care center. Patients were followed up at regular intervals until death, revision surgery, or last clinical follow-up. Perioperative medical complications were individually reviewed. The risk of death was examined by calculating standardized mortality ratios and Cox proportional hazards regression models. Cumulative incidence analyses were used for reporting mortality, reoperation, and revision with death as a competing risk. RESULTS: The 90-day mortality was 1.8% and 3.1% for primary and revision THAs, respectively. The risk of death was approximately two-fold higher compared to primary (hazard ratio 2.69) and revision (hazard ratio 2.04) THA patients who did not have pulmonary HTN. Rate of medical complications within 90 days from surgery were 6.2% and 13.1% in primary and revision THAs, respectively. The 10-year cumulative incidence of any revision was 9% and 14% following primaries and revisions, respectively. CONCLUSION: Patients who had pulmonary HTN undergoing primary and revision THAs had an increased risk of death and experienced a high rate of medical complications within 90 days of surgery. Counseling of risks, medical optimization, and referral to medical centers expert at managing complex medical problems should be considered. LEVEL OF EVIDENCE: Level IV.

A Deep Learning Tool for Automated Landmark Annotation on Hip and Pelvis Radiographs.

BACKGROUND: Automatic methods for labeling and segmenting pelvis structures can improve the efficiency of clinical and research workflows and reduce the variability introduced with manual labeling. The purpose of this study was to develop a single deep learning model to annotate certain anatomical structures and landmarks on antero-posterior (AP) pelvis radiographs. METHODS: A total of 1,100 AP pelvis radiographs were manually annotated by 3 reviewers. These images included a mix of preoperative and postoperative images as well as a mix of AP pelvis and hip images. A convolutional neural network was trained to segment 22 different structures (7 points, 6 lines, and 9 shapes). Dice score, which measures overlap between model output and ground truth, was calculated for the shapes and lines structures. Euclidean distance error was calculated for point structures. RESULTS: Dice score averaged across all images in the test set was 0.88 and 0.80 for the shape and line structures, respectively. For the 7-point structures, average distance between real and automated annotations ranged from 1.9 mm to 5.6 mm, with all averages falling below 3.1 mm except for the structure labeling the center of the sacrococcygeal junction, where performance was low for both human and machine-produced labels. Blinded qualitative evaluation of human and machine produced segmentations did not reveal any drastic decrease in performance of the automatic method. CONCLUSION: We present a deep learning model for automated annotation of pelvis radiographs that flexibly handles a variety of views, contrasts, and operative statuses for 22 structures and landmarks.