Diagnostic Performance of Artificial Intelligence for Detection of Scaphoid and Distal Radius Fractures: A Systematic Review

PURPOSE

To review the existing literature to (1) determine the diagnostic efficacy of artificial intelligence (AI) models for detecting scaphoid and distal radius fractures and (2) compare the efficacy to human clinical experts.

METHODS

PubMed, OVID/Medline, and Cochrane libraries were queried for studies investigating the development, validation, and analysis of AI for the detection of scaphoid or distal radius fractures. Data regarding study design, AI model development and architecture, prediction accuracy/area under the receiver operator characteristic curve (AUROC), and imaging modalities were recorded.

RESULTS

A total of 21 studies were identified, of which 12 (57.1%) used AI to detect fractures of the distal radius, and nine (42.9%) used AI to detect fractures of the scaphoid. AI models demonstrated good diagnostic performance on average, with AUROC values ranging from 0.77 to 0.96 for scaphoid fractures and from 0.90 to 0.99 for distal radius fractures. Accuracy of AI models ranged between 72.0% to 90.3% and 89.0% to 98.0% for scaphoid and distal radius fractures, respectively. When compared to clinical experts, 13 of 14 (92.9%) studies reported that AI models demonstrated comparable or better performance. The type of fracture influenced model performance, with worse overall performance on occult scaphoid fractures; however, models trained specifically on occult fractures demonstrated substantially improved performance when compared to humans.

CONCLUSIONS

AI models demonstrated excellent performance for detecting scaphoid and distal radius fractures, with the majority demonstrating comparable or better performance compared with human experts. Worse performance was demonstrated on occult fractures. However, when trained specifically on difficult fracture patterns, AI models demonstrated improved performance.

CLINICAL RELEVANCE

AI models can help detect commonly missed occult fractures while enhancing workflow efficiency for distal radius and scaphoid fracture diagnoses. As performance varies based on fracture type, future studies focused on wrist fracture detection should clearly define whether the goal is to (1) identify difficult-to-detect fractures or (2) improve workflow efficiency by assisting in routine tasks.

Biomechanical Characteristics of Ulnar Collateral Ligament Injuries Treated With and Without Augmentation: A Network Meta-analysis of Controlled Laboratory Studies

BACKGROUND

Treatment of ulnar collateral ligament (UCL) tears with suture tape augmentation has gained interest given preliminary reports of favorable biomechanical characteristics. No study to date has quantitatively assessed the biomechanical effects of multiple augmentation techniques relative to the native UCL.

PURPOSE

To perform a systematic review and meta-analysis of controlled laboratory studies to assess and comparatively rank biomechanical effects of UCL repair or reconstruction with or without augmentation.

STUDY DESIGN

Systematic review and meta-analysis; Level of evidence, 4.

METHODS

PubMed, OVID/Medline, and Cochrane databases were queried in January 2023. A frequentist network meta-analytic approach was used to perform mixed-treatment comparisons of UCL repair and reconstruction techniques with and without augmentation, with the native UCL as the reference condition. Pooled treatment estimates were quantified under the random-effects assumption. Competing treatments were ranked in the network meta-analysis by using point estimates and standard errors to calculate P scores (greater P score indicates superiority of treatment for given outcome).

RESULTS

Ten studies involving 206 elbow specimens in which a distal UCL tear was simulated were included. UCL reconstruction with suture tape augmentation (AugRecon) restored load to failure to a statistically noninferior magnitude (mean difference [MD], -1.99 N·m; 95% CI, -10.2 to 6.2 N·m; P = .63) compared with the native UCL. UCL reconstruction (Recon) (MD, -12.7 N·m; P < .001) and UCL repair with suture tape augmentation (AugRepair) (MD, -14.8 N·m; P < .001) were both statistically inferior to the native UCL. The AugRecon condition conferred greater load to failure compared with Recon (P < .001) and AugRepair (P = .002) conditions. AugRecon conferred greater torsional stiffness relative to all other conditions and was not statistically different from the native UCL (MD, 0.32 N·m/deg; 95% CI, -0.30 to 0.95 N·m/deg; P = .31). Medial ulnohumeral gapping was not statistically different for the AugRepair (MD, 0.30 mm; 95% CI, -1.22 to 1.82 mm; P = .70), AugRecon (MD, 0.57 mm; 95% CI, -0.70 to 1.84 mm; P = .38), or Recon (MD, 1.02 mm; 95% CI, -0.02 to 2.05 mm; P = .055) conditions compared with the native UCL. P-score analysis indicated that AugRecon was the most effective treatment for increasing ultimate load to failure and torsional stiffness, whereas AugRepair was the most effective for minimizing medial gapping.

CONCLUSION

AugRecon restored load to failure and torsional stiffness most similar to the parameters of the native UCL, whereas Recon and AugRepair did not restore the same advantageous properties at time zero. Medial ulnohumeral gapping during a valgus load was minimized by all 3 treatments. Based on network interactions, AugRecon was the superior treatment approach for restoring important biomechanical features of the UCL at time zero that are jeopardized during a complete distal tear.

Deep-Learning Automation of Preoperative Radiographic Parameters Associated With Early Periprosthetic Femur Fracture After Total Hip Arthroplasty

BACKGROUND

The radiographic assessment of bone morphology impacts implant selection and fixation type in total hip arthroplasty (THA) and is important to minimize the risk of periprosthetic femur fracture (PFF). We utilized a deep-learning algorithm to automate femoral radiographic parameters and determined which automated parameters were associated with early PFF.

METHODS

Radiographs from a publicly available database and from patients undergoing primary cementless THA at a high-volume institution (2016 to 2020) were obtained. A U-Net algorithm was trained to segment femoral landmarks for bone morphology parameter automation. Automated parameters were compared against that of a fellowship-trained surgeon and compared in an independent cohort of 100 patients who underwent THA (50 with early PFF and 50 controls matched by femoral component, age, sex, body mass index, and surgical approach).

RESULTS

On the independent cohort, the algorithm generated 1,710 unique measurements for 95 images (5% lesser trochanter identification failure) in 22 minutes. Medullary canal width, femoral cortex width, canal flare index, morphological cortical index, canal bone ratio, and canal calcar ratio had good-to-excellent correlation with surgeon measurements (Pearson's correlation coefficient: 0.76 to 0.96). Canal calcar ratios (0.43 ± 0.08 versus 0.40 ± 0.07) and canal bone ratios (0.39 ± 0.06 versus 0.36 ± 0.06) were higher (P < .05) in the PFF cohort when comparing the automated parameters.

CONCLUSIONS

Deep-learning automated parameters demonstrated differences in patients who had and did not have early PFF after cementless primary THA. This algorithm has the potential to complement and improve patient-specific PFF risk-prediction tools.

Artificial Intelligence for Clinically Meaningful Outcome Prediction in Orthopedic Research: Current Applications and Limitations

PURPOSE OF REVIEW

Patient-reported outcome measures (PROM) play a critical role in evaluating the success of treatment interventions for musculoskeletal conditions. However, predicting which patients will benefit from treatment interventions is complex and influenced by a multitude of factors. Artificial intelligence (AI) may better anticipate the propensity to achieve clinically meaningful outcomes through leveraging complex predictive analytics that allow for personalized medicine. This article provides a contemporary review of current applications of AI developed to predict clinically significant outcome (CSO) achievement after musculoskeletal treatment interventions.

RECENT FINDINGS

The highest volume of literature exists in the subspecialties of total joint arthroplasty, spine, and sports medicine, with only three studies identified in the remaining orthopedic subspecialties combined. Performance is widely variable across models, with most studies only reporting discrimination as a performance metric. Given the complexity inherent in predictive modeling for this task, including data availability, data handling, model architecture, and outcome selection, studies vary widely in their methodology and results. Importantly, the majority of studies have not been externally validated or demonstrate important methodological limitations, precluding their implementation into clinical settings. A substantial body of literature has accumulated demonstrating variable internal validity, limited scope, and low potential for clinical deployment. The majority of studies attempt to predict the MCID-the lowest bar of clinical achievement. Though a small proportion of models demonstrate promise and highlight the utility of AI, important methodological limitations need to be addressed moving forward to leverage AI-based applications for clinical deployment.

Hip Arthroscopy Simulator Training With Immersive Virtual Reality Has Similar Effectiveness to Nonimmersive Virtual Reality

PURPOSE

To (1) compare the efficacy of immersive virtual reality (iVR) to nonimmersive virtual reality (non-iVR) training in hip arthroscopy on procedural and knowledge-based skills acquisition and (2) evaluate the relative cost of each platform.

METHODS

Fourteen orthopaedic surgery residents were randomized to simulation training utilizing an iVR Hip Arthroscopy Simulator (n = 7; PrecisionOS) or non-iVR simulator (n = 7; ArthroS Hip VR; VirtaMed). After training, performance was assessed on a cadaver by 4 expert hip arthroscopists through arthroscopic video review of a diagnostic hip arthroscopy. Performance was assessed using the Objective Structured Assessment of Technical Skills (OSATS) and Arthroscopic Surgery Skill Evaluation Tool (ASSET) scores. A cost analysis was performed using the transfer effectiveness ratio (TER) and a direct cost comparison of iVR to non-iVR.

RESULTS

Demographic characteristics did not differ between treatment arms or by training level, hip arthroscopy experience, or prior simulator use. No significant differences were observed in OSATS and ASSET scores between iVR and non-iVR cohorts (OSATS: iVR 19.6 ± 4.4, non-iVR 21.0 ± 4.1, P = .55; ASSET: iVR 23.7 ± 4.5, non-iVR 25.8 ± 4.8, P = .43). The absolute TER was 0.06 and there was a 132-fold cost difference of iVR to non-iVR.

CONCLUSIONS

Hip arthroscopy simulator training with iVR had similar performance results to non-iVR for technical skill and procedural knowledge acquisition after expert arthroscopic video assessment. The iVR platform had similar effectiveness in transfer of skill compared to non-iVR with a 132 times cost differential. CLINICAL RELEVANCE: Due to the accessibility, effectiveness, and relative affordability, iVR training may be beneficial in the future of safe arthroscopic hip training.

Relationships between throwing mechanics and shoulder anterior force in high school and professional baseball pitchers

Background

Excessive shoulder anterior force has been implicated in pathology of the rotator cuff in little league and professional baseball pitchers; in particular, anterior laxity, posterior stiffness, and glenohumeral joint impingement. Distinctly characterized motions associated with excessive shoulder anterior force remain poorly understood.

Methods

High school and professional pitchers were instructed to throw fastballs while being evaluated with 3D motion capture (480 Hz). A supplementary random forest model was designed and implemented to identify the most important features for regressing to shoulder anterior force, with subsequent standardized regression coefficients to quantify directionality.

Results

130 high school pitchers (16.3 ± 1.2 yrs; 179.9 ± 7.7 cm; 74.5 ± 12.0 kg) and 322 professionals (21.9 ± 2.1 yrs; 189.7 ± 5.7 cm; 94.8 ± 9.5 kg) were included. Random forest models determined nearly all the variance for professional pitchers (R2 = 0.96), and less than half for high school pitchers (R2 = 0.41). Important predictors of shoulder anterior force in high school pitchers included: trunk flexion at maximum shoulder external rotation (MER) (X.IncMSE = 2.4, β = -0.23, p < 0.001), shoulder external rotation at ball release (BR)(X.IncMSE = 1.7, β = -0.34, p < 0.001), and shoulder abduction at BR (X.IncMSE = 3.1, β = 0.17, p < 0.001). In professional pitchers, shoulder horizontal adduction at foot contact (FC) was the highest predictor (X.IncMSE = 13.9, β = 0.50, p < 0.001), followed by shoulder external rotation at FC (X.IncMSE = 3.6, β = 0.26, p < 0.001), and maximum elbow extension velocity (X.IncMSE = 8.5, β = 0.19, p < 0.001).

Conclusion

A random forest model successfully selected a subset of features that accounted for the majority of variance in shoulder anterior force for professional pitchers; however, less than half of the variance was accounted for in high school pitchers. Temporal and kinematic movements at the shoulder were prominent predictors of shoulder anterior force for both groups.

Clinical relevance

: Our statistical model successfully identified a combination of features with the ability to adequately explain the majority of variance in anterior shoulder force among high school and professional pitchers. To minimize shoulder anterior force, high school pitchers should emphasize decreased shoulder abduction at BR, while professionals can decrease shoulder horizontal adduction at FC.

The Reverse Fragility Index for Mortality End Points in Randomized Trials Comparing Uncemented and Cemented Hemiarthroplasty for Intracapsular Hip Fractures

BACKGROUND

Interpreting clinical relevance of randomized clinical trials (RCTs) is challenging when P-values are marginally above or below the P = .05 threshold. This study examined the robustness of statistically insignificant mortality events from RCTs comparing hemiarthroplasty femoral fixation for displaced intracapsular hip fractures through the reverse fragility index (RFI).

METHODS

RCTs were identified using Pubmed, OVID/Medline, and Cochrane databases. Mortality endpoints were stratified into 3 categories: (1) within 30-days, (2) within 90-days, and (3) at latest follow-up. The RFI was derived by manipulating reported mortality events utilizing a contingency table while maintaining a constant number of participants. The reverse fragility quotient (RFQ) was quantified by dividing the RFI by the study sample.

RESULTS

Eight RCTs (2,494 participants) were included. The median RFI and RFQ within 30-days was 3.0 (interquartile range [IQR]: 3.0 to 6.0) and 0.016 (IQR: 0.015 to 0.021), suggesting nonsignificant findings were contingent on 1.6 mortality events/100 participants. The median RFI and RFQ within 90-days was 6.0 (IQR: 4.0 to 7.0) and 0.028 (IQR: 0.024 to 0.038), suggesting nonsignificant findings were contingent on 2.8 mortality events/100 participants. At latest follow-up, the median RFI and RFQ was 7.0 (IQR: 6.0 to 12.0) and 0.038 (IQR: 0.029 to 0.054), suggesting nonsignificant findings were contingent on only 3.8 mortality events/100 participants. Median loss to follow-up was 16.0 (IQR: 11.0 to 58.0; 228% greater than RFI), and exceeded the RFI in 6/7(85.7%) studies.

CONCLUSIONS

A small number of events (median of 7) was required to convert a statistically nonsignificant finding to one that is significant for the endpoint of mortality. The median loss to follow-up exceeded the median RFI by greater than 200%, suggesting methodological limitations such as patient allocation could alter conclusions.

Enabling Personalized Medicine in Orthopaedic Surgery Through Artificial Intelligence: A Critical Analysis Review

» The application of artificial intelligence (AI) in the field of orthopaedic surgery holds potential for revolutionizing health care delivery across 3 crucial domains: (I) personalized prediction of clinical outcomes and adverse events, which may optimize patient selection, surgical planning, and enhance patient safety and outcomes; (II) diagnostic automated and semiautomated imaging analyses, which may reduce time burden and facilitate precise and timely diagnoses; and (III) forecasting of resource utilization, which may reduce health care costs and increase value for patients and institutions.» Computer vision is one of the most highly studied areas of AI within orthopaedics, with applications pertaining to fracture classification, identification of the manufacturer and model of prosthetic implants, and surveillance of prosthesis loosening and failure.» Prognostic applications of AI within orthopaedics include identifying patients who will likely benefit from a specified treatment, predicting prosthetic implant size, postoperative length of stay, discharge disposition, and surgical complications. Not only may these applications be beneficial to patients but also to institutions and payors because they may inform potential cost expenditure, improve overall hospital efficiency, and help anticipate resource utilization.» AI infrastructure development requires institutional financial commitment and a team of clinicians and data scientists with expertise in AI that can complement skill sets and knowledge. Once a team is established and a goal is determined, teams (1) obtain, curate, and label data; (2) establish a reference standard; (3) develop an AI model; (4) evaluate the performance of the AI model; (5) externally validate the model, and (6) reinforce, improve, and evaluate the model's performance until clinical implementation is possible.» Understanding the implications of AI in orthopaedics may eventually lead to wide-ranging improvements in patient care. However, AI, while holding tremendous promise, is not without methodological and ethical limitations that are essential to address. First, it is important to ensure external validity of programs before their use in a clinical setting. Investigators should maintain high quality data records and registry surveillance, exercise caution when evaluating others' reported AI applications, and increase transparency of the methodological conduct of current models to improve external validity and avoid propagating bias. By addressing these challenges and responsibly embracing the potential of AI, the medical field may eventually be able to harness its power to improve patient care and outcomes.

Variability of the femoral mechanical-anatomical axis angle and its implications in primary and revision total knee arthroplasty

Aims

Distal femoral resection in conventional total knee arthroplasty (TKA) utilizes an intramedullary guide to determine coronal alignment, commonly planned for 5° of valgus. However, a standard 5° resection angle may contribute to malalignment in patients with variability in the femoral anatomical and mechanical axis angle. The purpose of the study was to leverage deep learning (DL) to measure the femoral mechanical-anatomical axis angle (FMAA) in a heterogeneous cohort.

Methods

Patients with full-limb radiographs from the Osteoarthritis Initiative were included. A DL workflow was created to measure the FMAA and validated against human measurements. To reflect potential intramedullary guide placement during manual TKA, two different FMAAs were calculated either using a line approximating the entire diaphyseal shaft, and a line connecting the apex of the femoral intercondylar sulcus to the centre of the diaphysis. The proportion of FMAAs outside a range of 5.0° (SD 2.0°) was calculated for both definitions, and FMAA was compared using univariate analyses across sex, BMI, knee alignment, and femur length.

Results

The algorithm measured 1,078 radiographs at a rate of 12.6 s/image (2,156 unique measurements in 3.8 hours). There was no significant difference or bias between reader and algorithm measurements for the FMAA (p = 0.130 to 0.563). The FMAA was 6.3° (SD 1.0°; 25% outside range of 5.0° (SD 2.0°)) using definition one and 4.6° (SD 1.3°; 13% outside range of 5.0° (SD 2.0°)) using definition two. Differences between males and females were observed using definition two (males more valgus; p < 0.001).

Conclusion

We developed a rapid and accurate DL tool to quantify the FMAA. Considerable variation with different measurement approaches for the FMAA supports that patient-specific anatomy and surgeon-dependent technique must be accounted for when correcting for the FMAA using an intramedullary guide. The angle between the mechanical and anatomical axes of the femur fell outside the range of 5.0° (SD 2.0°) for nearly a quarter of patients.

Medical Imaging Applications Developed Using Artificial Intelligence Demonstrate High Internal Validity Yet Are Limited in Scope and Lack External Validation

PURPOSE

To (1) review definitions and concepts necessary to interpret applications of deep learning (DL; a domain of artificial intelligence that leverages neural networks to make predictions on media inputs such as images) and (2) identify knowledge and translational gaps in the literature to provide insight into specific areas for improvement as adoption of this technology continues.

METHODS

A comprehensive search of the literature was performed in December 2023 for articles regarding the use of DL in sports medicine. For each study, information regarding the joint of focus, specific anatomic structure/pathology to which DL was applied, imaging modality utilized, source of images used for model training and testing, data set size, model performance, and whether the DL model was externally validated was recorded. A numerical scale was used to rate each DL model's clinical impact, with 1 corresponding to proof-of-concept studies with little to no direct clinical impact and 5 corresponding to practice-changing clinical impact and ready for clinical deployment.

RESULTS

Fifty-five studies were identified, all of which were published within the past 5 years, while 82% were published within the past 3 years. Of the DL models identified, 84% were developed for classification tasks, 9% for automated measurements, and 7% for segmentation. A total of 62% of studies utilized magnetic resonance imaging as the imaging modality, 25% radiographs, and 7% ultrasound, while 1 study each used computed tomography, arthroscopic images, or arthroscopic video. Sixty-five percent of studies focused on the detection of tears (anterior cruciate ligament [ACL], rotator cuff [RC], and meniscus). The diagnostic performance of ACL tears, as determined by the area under the receiver operator curve (AUROC), ranged from 0.81 to 0.99 for ACL tears (excellent to near perfect), 0.83 to 0.94 for RC tears (excellent), and from 0.75 to 0.96 for meniscus tears (acceptable to excellent). In addition, 3 studies focused on detection of cartilage lesions had AUROC ranging from 0.90 to 0.92 (excellent performance). However, only 4 (7%) studies externally validated their models, suggesting that they may not be generalizable or may not perform well when applied to populations other than that used to develop the model. Finally, the mean clinical impact score was 2 (range, 1-3) on scale of 1 to 5, corresponding to limited clinical applicability.

CONCLUSIONS

DL models in orthopaedic sports medicine show generally excellent performance (high internal validity) but require external validation to facilitate clinical deployment. In addition, current models have low clinical applicability and fail to advance the field due to a focus on routine tasks and a narrow conceptual framework.

LEVEL OF EVIDENCE

Level IV, scoping review of Level I to IV studies.

Editorial Commentary: Artificial Intelligence Models Show Impressive Results for Musculoskeletal Pathology Detection

An important domain of artificial intelligence is deep learning, which comprises computed vision tasks used for recognizing complex patterns in orthopaedic imaging, thus automating the identification of pathology. Purported benefits include an expedited clinical workflow; improved performance and consistency in diagnostic tasks; decreased time allocation burden; augmentation of diagnostic performance, decreased inter-reader discrepancies in measurements and diagnosis as a function of reducing subjectivity in the setting of differences in imaging quality, resolution, penetrance, or orientation; and the ability to function autonomously without rest (unlike human observers). Detection may include the presence or absence of an entity or identification of a specific landmark. Within the field of musculoskeletal health, such capabilities have been shown across a wide range of tasks such as detecting the presence or absence of a rotator cuff tear or automatically identifying the center of the hip joint. The clinical relevance and success of these research endeavors have led to a plethora of novel algorithms. However, few of these algorithms have been externally validated, and evidence remains inconclusive as to whether they provide a diagnostic benefit when compared with the current, human gold standard.

Low Rates of Postoperative Complications and Revision Surgery After Primary Medial Elbow Ulnar Collateral Ligament Repair

Purpose

To evaluate the incidence of early postoperative complications and revision surgery in patients who underwent primary medial ulnar collateral ligament (MUCL) repair with minimum of 2-year follow-up.

Methods

A retrospective review of a national insurance database was conducted to identify patients with MUCL injuries who underwent primary MUCL repair between 2015 to 2020 with minimum 2-year follow-up. Patients >40 years of age and those who had concomitant elbow fractures or dislocations, lateral UCL injures, medial epicondylitis, elbow arthritis, or a history of previous elbow injury/surgery were excluded. The number of patients who underwent a concomitant ulnar nerve procedure (transposition or decompression) during the primary MUCL repair was recorded. Complications within 90 days of surgery and the incidence and timing of subsequent ipsilateral ulnar nerve surgery or revision MUCL surgery were assessed.

Results

A total of 313 patients (63.6% male) were included. The mean age was 20.3 ± 6.9 years, and mean follow-up was 3.7 ± 1.3 years. Concomitant ulnar nerve transposition or decompression was performed in 34.2% (N = 107). The early postoperative complication rate was 7.3% (N = 23). The most common complication was ulnar neuropathy (5.8%, N = 18). Wound complications, elbow stiffness, and medial epicondyle fractures were much less common (N = 5). Sixteen of 18 (88.9%) patients with postoperative ulnar neuropathy underwent transposition or decompression at the time of primary repair. Of these 18 patients, 5 (27.8%) underwent a subsequent ulnar nerve surgery (1 primary and 4 secondary), with the majority occurring within 6 months. The incidence of revision MUCL surgery was low (1.0%, N=3), with all 3 patients undergoing MUCL reconstruction.

Conclusion

There was a low incidence of early postoperative complications (7.3%) and 2-year revision MUCL surgery (1.0%) in young patients who underwent primary MUCL repair with no additional ligamentous, fracture, and dislocation-related diagnoses. All 3 (1.0%) MUCL revisions underwent reconstruction.

Level of Evidence

Level IV, therapeutic case series.

High Rate of Clinically Meaningful Achievement in Outcomes After Subacromial Balloon Spacer Implantation for Massive Irreparable Rotator Cuff Tears: A Systematic Review and Meta-analysis

BACKGROUND

Subacromial balloon spacers have been introduced as a potential treatment option for patients with massive irreparable rotator cuff tears. However, it is important to comprehensively assess the clinical efficacy of this procedure in the context of an increasing amount of contemporary literature.

PURPOSE

To perform a systematic review of the contemporary literature to understand the propensity for clinically meaningful improvements after subacromial balloon spacer implantation for massive irreparable rotator cuff tears.

STUDY DESIGN

Systematic review and meta-analysis; Level of evidence, 4.

METHODS

The PubMed, Ovid/MEDLINE, and Cochrane databases were queried in July 2022 for data pertaining to studies reporting clinically significant outcomes after subacromial balloon spacer implantation. Freeman-Tukey double arcsine transformation was used to quantify the pooled rate of clinically meaningful improvements in outcomes as evaluated using the minimal clinically important difference (MCID), Patient Acceptable Symptom State (PASS), and substantial clinical benefit (SCB). Qualitative analysis was performed when data were variably presented to avoid misleading reporting.

RESULTS

There were 10 studies included, all of which reported MCID achievement. The overall pooled rate of MCID achievement for the Constant-Murley score was 83% (95% CI, 71%-93%; range, 40%-98%), with 6 of 8 studies reporting rates equal to or exceeding 85%. One study reported a 98% rate of PASS achievement for the Constant-Murley score at 3-year follow-up. The rate of MCID achievement for the American Shoulder and Elbow Surgeons (ASES) score ranged between 83% and 87.5%. The rate of PASS achievement for the ASES score was 56% at 2-year follow-up, while the rate of SCB achievement for the ASES score was 83% and 82% at 1- and 2-year follow-up, respectively. At 1-year follow-up, 74% and 78% of patients achieved the MCID for the Numeric Rating Scale and Oxford Shoulder Score, respectively. At 3 years, 69% of patients achieved the MCID for the Numeric Rating Scale and 87% achieved it for the Oxford Shoulder Score.

CONCLUSION

Patients who underwent isolated subacromial balloon spacer implantation for massive irreparable rotator cuff tears demonstrated a high rate of clinically significant improvement in outcomes at short- to mid-term follow-up. A paucity of literature exists to appropriately define and evaluate the rates of achieving the PASS and SCB after subacromial balloon spacer implantation, necessitating further study.

30-day to 10-year mortality rates following total hip arthroplasty: a meta-analysis of the last decade (2011-2021)

BACKGROUND

Mortality after total hip arthroplasty (THA) is a rare but devastating complication. This meta-analysis aimed to: (1) determine the mortality rates at 30 days, 90 days, 1 year, 5 years and 10 years after THA; (2) identify risk factors and causes of mortality after THA.

METHODS

Pubmed, MEDLINE, Cochrane, EBSCO Host, and Google Scholar databases were queried for studies reporting mortality rates after primary elective, unilateral THA. Inverse-proportion models were constructed to quantify the incidence of all-cause mortality at 30 days, 90 days, 1 year, 5 years and 10 years after THA. Random-effects multiple regression was performed to investigate the potential effect modifiers of age (at time of THA), body mass index, and gender.

RESULTS

A total of 53 studies (3,297,363 patients) were included. The overall mortality rate was 3.9%. The 30-day mortality was 0.49% (95% CI; 0.23-0.84). Mortality at 90 days was 0.47% (95% CI, 0.38-0.57). Mortality increased exponentially between 90 days and 5 years, with a 1-year mortality rate of 1.90% (95% CI, 1.22-2.73) and a 5-year mortality rate of 9.85% (95% CI, 5.53-15.22). At 10-year follow-up, the mortality rate was 16.43% (95% CI, 1.17-22.48). Increasing comorbidity indices, socioeconomic disadvantage, age, anaemia, and smoking were found to be risk factors for mortality. The most commonly reported causes of death were ischaemic heart disease, malignancy, and pulmonary disease.

CONCLUSIONS

All-cause mortality remains low after contemporary THA. However, 1 out of 10 patients and 1 out of 6 patients were deceased after 5 years and 10 years of THA, respectively. As expected, age, but not BMI or gender, was significantly associated with mortality.

Subacromial Balloon Spacer Implantation for Massive Irreparable Rotator Cuff Tears Is Associated With Restoration of the Acromiohumeral Interval and Glenohumeral Center of Pressure: A Systematic Review and Meta-Analysis of Controlled Laboratory Studies

BACKGROUND

Biodegradable subacromial balloon spacers (SBSs) have become increasingly used for the treatment of massive irreparable rotator cuff tears given their theorized clinical benefits; however, the relationship between biomechanical functions of the balloon spacer and clinical benefits remains unclear.

PURPOSE

To perform a systematic review and meta-analysis of controlled laboratory studies investigating the use of SBSs for massive irreparable rotator cuff tears.

STUDY DESIGN

Systematic review and meta-analysis; Level of evidence, 4.

METHODS

PubMed, OVID/Medline, and Cochrane databases were queried in July 2022 for biomechanical data pertaining to SBS implantation in cadaveric models of irreparable rotator cuff tears. Random-effects meta-analysis of continuous outcomes using the DerSimonian-Laird method was performed to estimate pooled-treatment effect sizes between the irreparable rotator cuff tear state and the state in which an SBS was implanted. Data reported variably or in formats not amenable to analysis were presented descriptively.

RESULTS

Five studies involving 44 cadaveric specimens were included. At 0° of shoulder abduction, SBS implantation resulted in a mean inferior humeral head translation of 4.80 mm (95% CI, 3.20-6.40; P < .001) relative to the irreparable rotator cuff tear state. This decreased to 4.39 mm and 4.35 mm at 30° and 60° of abduction, respectively. At 0° of abduction, implantation of an SBS was associated with a 5.01-mm (95% CI, 3.56-6.46, P < .001) anterior translation of the glenohumeral center of contact pressure relative to the irreparable tear state. This translation changed to 5.11 mm and 5.49 mm at 30° and 60° of abduction. In 2 studies, SBS implantation restored the glenohumeral contact pressure to that of the intact state and significantly reduced subacromial pressure distribution over a rotator cuff repair state. In 1 study, a high balloon fill volume (40 mL) resulted in a significant 10.3 ± 1.4-mm more anterior humeral head position relative to the intact cuff state.

CONCLUSION

SBS implantation in cadaveric models of irreparable rotator cuff tears results in significant improvements in humeral head position at 0°, 30°, and 60° of shoulder abduction. Balloon spacers may also improve glenohumeral and subacromial contact pressures, although insufficient evidence currently exists to corroborate these findings. High balloon fill volumes (40 mL) may confer supraphysiologic anteroinferior translation of the humeral head.

Editorial Commentary: Recognizing and Avoiding Medical Misinformation Across Digital Platforms: Smoke, Mirrors (and Streaming)

The evolution of social media and related online sources has substantially increased the ability of patients to query and access publicly available information that may have relevance to a potential musculoskeletal condition of interest. Although increased accessibility to information has several purported benefits, including encouragement of patients to become more invested in their care through self-teaching, a downside to the existence of a vast number of unregulated resources remains the risk of misinformation. As health care providers, we have a moral and ethical obligation to mitigate this risk by directing patients to high-quality resources for medical information and to be aware of resources that are unreliable. To this end, a growing body of evidence has suggested that YouTube lacks reliability and quality in terms of medical information concerning a variety of musculoskeletal conditions.

Predictors of Adverse Events in the Surgical Treatment of Adult Distal Humerus Fractures

The purpose of this study was to identify surgical complications after distal humerus fracture fixation as well as correlations between these complications and patient variables. A total of 132 patients underwent open reduction and internal fixation of traumatic distal humerus fractures between October 2011 and June 2018. Included were adult patients who underwent surgical fixation and had more than 6 months of follow-up. Excluded were patients with inadequate radiographic imaging, less than 6 months of follow-up, and previous distal humerus surgery. Multivariate logistic regression models controlling for age and body mass index were used to determine preoperative factors predictive of postoperative complications. A total of 73 patients were included in this analysis. Surgical complications were reported for 17 patients. Reoperation was required for 13 patients. Open injury at presentation was predictive of delayed union. Predictors of subsequent elbow surgery included younger age, polytrauma, open fracture, and ulnar nerve injury at the time of injury. Radial nerve injury at the time of presentation was also a risk factor for postoperative radial nerve symptoms. Predictors of postoperative heterotopic ossification included older age. Thirty-one patients had an olecranon osteotomy during their open reduction and internal fixation and none went on to nonunion. There were 13 patients with ulnar nerve complications. Of these patients, 3 had undergone an ulnar nerve transposition. None of the other studied variables were predictors of complications, malunion, or nonunion at latest follow-up. Although open reduction and internal fixation is effective in treating distal humerus fractures, its complications cannot be overlooked. Open fractures are more likely to go on to delayed union. Ulnar nerve injury, open fracture, and polytrauma were predictive for reoperation. Older patients were less likely to have subsequent surgery but more likely to develop heterotopic ossification. By identifying at-risk patients, managing physicians can better prognosticate and counsel patients on their recovery. [Orthopedics. 2023;46(6):352-357.].

Challenges and Opportunities for the Use of Patient-Reported Outcome Measures in Orthopaedic Pediatric and Sports Medicine Surgery

Patient-reported outcome measures (PROMs) are essential tools in assessing treatment response, informing clinical decision making, driving healthcare policy, and providing important prognostic data regarding patient health status change. These tools become essential in orthopaedic disciplines, such as pediatrics and sports medicine, given the diversity of patient populations and procedures. However, the creation and routine administration of standard PROMs alone do not suffice to appropriately facilitate the aforementioned functions. Indeed, both the interpretation and optimal application of PROMs are essential to provide to achieve greatest clinical benefit. Contemporary developments and technologies surrounding PROMs may help augment this benefit, including the application of artificial intelligence, novel PROM structure with improved interpretability and validity, and PROM delivery methods that provide increased access to patients resulting in greater compliance and data acquisition yields. Despite these exciting innovations, several challenges remain in this realm that must be addressed to continue to advance the clinical usefulness and subsequent benefit of PROMs. This review will highlight the opportunities and challenges surrounding contemporary PROM use in the orthopaedic subspecialties of pediatrics and sports medicine.

Leg-Length Discrepancy Variability on Standard Anteroposterior Pelvis Radiographs: An Analysis Using Deep Learning Measurements

BACKGROUND

Leg-length discrepancy (LLD) is a critical factor in component selection and placement for total hip arthroplasty. However, LLD radiographic measurements are subject to variation based on the femoral/pelvic landmarks chosen. This study leveraged deep learning (DL) to automate LLD measurements on pelvis radiographs and compared LLD based on several anatomically distinct landmarks.

METHODS

Patients who had baseline anteroposterior pelvis radiographs from the Osteoarthritis Initiative were included. A DL algorithm was created to identify LLD-relevant landmarks (ie, teardrop (TD), obturator foramen, ischial tuberosity, greater and lesser trochanters) and measure LLD accurately using six landmark combinations. The algorithm was then applied to automate LLD measurements in the entire cohort of patients. Interclass correlation coefficients (ICC) were calculated to assess agreement between different LLD methods.

RESULTS

The DL algorithm measurements were first validated in an independent cohort for all six LLD methods (ICC = 0.73-0.98). Images from 3,689 patients (22,134 LLD measurements) were measured in 133 minutes. When using the TD and lesser trochanter landmarks as the standard LLD method, only measuring LLD using the TD and greater trochanter conferred acceptable agreement (ICC = 0.72). When comparing all six LLD methods for agreement, no combination had an ICC>0.90. Only two (13%) combinations had an ICC>0.75 and eight (53%) combinations had a poor ICC (<0.50).

CONCLUSION

We leveraged DL to automate LLD measurements in a large patient cohort and found considerable variation in LLD based on the pelvic/femoral landmark selection. This emphasizes the need for the standardization of landmarks for both research and surgical planning.

Patients With Chronic Foot and Ankle Conditions Experience Significant Improvements in Sleep Quality Following Surgical Intervention

BACKGROUND

Poor sleep quality is associated with metabolic dysregulation and impaired healing. The purpose of the current study was to quantify the prevalence of poor sleep in patients with atraumatic foot and ankle (F&A) conditions and determine whether surgical treatment is associated with sleep quality improvement.

METHODS

Patients scheduled for surgical management of atraumatic F&A conditions were enrolled by 4 fellowship-trained orthopaedic F&A surgeons between May 2018 and April 2019. Patients completed the Pittsburgh Sleep Quality Index (PSQI) pre- and postoperatively. The PSQI ranges from 0 to 21, with a score ≥5 indicative of poor sleep quality. Patients also reported their perception of how their current F&A pain influenced their sleep quality on a scale of 0 to 10, where 0 indicated no influence and 10 indicated a strong influence (pain perception score [PPS]). Patients with known sleep disorders, acute surgical trauma, and infection were excluded.

RESULTS

A total of 115 patients were enrolled. The mean preoperative PSQI and PPS were 8.1 ± 3.6 (range, 2-19) and 3.1 ± 2.7 (range, 0-10), respectively. Overall, 86.1% of patients had poor sleep quality (PSQI score ≥5). Similarly, 64.3% of patients had a PPS ≥1, indicating the belief that F&A pain contributed to sleep disturbance. A minimum of 6 months of follow-up was collected for 72 (62.6%) patients. On average, these 72 patients experienced significant improvements in sleep quality (mean PSQI decreased from 7.8 ± 3.2 to 5.4 ± 3.1, P < .001). Of these patients, 59.7% continued to experience poor sleep quality (PSQI ≥5), and 55.6% perceived that F&A pain contributed to sleep disturbance (PPS ≥1).

CONCLUSION

In this series, 86.1% of patients presenting for management of atraumatic F&A conditions had poor sleep quality at the time of their initial visit, with 64.3% perceiving their F&A conditions to influence their sleep quality. Improvements in sleep quality were observed at 6 months postoperatively, though over half of patients continued to experience poor sleep quality. The location of pathology and procedure performed was not associated with sleep quality.

LEVELS OF EVIDENCE

Level IV: Prospective case series.

Artificial intelligence for automated identification of total shoulder arthroplasty implants

BACKGROUND

Accurate and rapid identification of implant manufacturer and model is critical in the evaluation and management of patients requiring revision total shoulder arthroplasty (TSA). Failure to correctly identify implant designs in these circumstances may lead to delay in care, unexpected intraoperative challenges, increased morbidity, and excess health care costs. Deep learning (DL) permits automated image processing and holds the potential to mitigate such challenges while improving the value of care rendered. The purpose of this study was to develop an automated DL algorithm to identify shoulder arthroplasty implants from plain radiographs.

METHODS

A total of 3060 postoperative images from patients who underwent TSA between 2011 and 2021 performed by 26 fellowship-trained surgeons at 2 independent tertiary academic hospitals in the Pacific Northwest and Mid-Atlantic Northeast were included. A DL algorithm was trained using transfer learning and data augmentation to classify 22 different reverse TSA and anatomic TSA prostheses from 8 implant manufacturers. Images were split into training and testing cohorts (2448 training and 612 testing images). Optimized model performance was assessed using standardized metrics including the multiclass area under the receiver operating characteristic curve (AUROC) and compared with a reference standard of implant data from operative reports.

RESULTS

The algorithm classified implants at a mean speed of 0.079 seconds (±0.002 seconds) per image. The optimized model discriminated between 8 manufacturers (22 unique implants) with AUROCs of 0.994-1.000, accuracy of 97.1%, and sensitivities between 0.80 and 1.00 on the independent testing set. In the subset of single-institution implant predictions, a DL model identified 6 specific implants with AUROCs of 0.999-1.000, accuracy of 99.4%, and sensitivity >0.97 for all implants. Saliency maps revealed key differentiating features across implant manufacturers and designs recognized by the algorithm for classification.

CONCLUSION

A DL model demonstrated excellent accuracy in identifying 22 unique TSA implants from 8 manufacturers. This algorithm may provide a clinically meaningful adjunct in assisting with preoperative planning for the failed TSA and allows for scalable expansion with additional radiographic data and validation efforts.

Kinematic and Kinetic Comparisons of Arm Slot Position Between High School and Professional Pitchers

Background

Throwing arm kinetics differ in pitchers at varying arm slot (AS) positions (frontal-plane arm position at ball release relative to the vertical axis).

Purpose

To determine how kinematic and kinetic values differ between professional and high school pitchers with varying AS positions, and whether these differences are similarly observed in both populations.

Methods

High school (n = 130) and professional (n = 288) pitchers threw 8 to 12 fastballs under 3-dimensional motion capture technology. Pitchers in each cohort were subdivided based on mean AS position at ball release: AS1 (least degree of AS: most overhand throwing styles), AS2 (intermediate degree of AS: three-quarter throwing styles), or AS3 (greatest degree of AS: most sidearm throwing styles). Kinetic and kinematic parameters were compared between groups.

Study Design

Controlled laboratory study.

Results

High school pitchers had a more overhand AS at ball release (50° ± 11°) compared with professional pitchers (58° ± 14°) (P < .001). In both cohorts, AS1 pitchers had significantly greater shoulder abduction (high school, P <0.001; professional, P <0.0001) and lateral trunk flexion (high school, P < 0.001; professional, P <0.0001) at ball release compared with AS3 pitchers. Professional pitchers with an AS3 position had significantly delayed timing of maximum upper trunk angular velocity compared with AS1 pitchers (64% ± 7% vs 57% ± 7% of pitch time, respectively; P < .0001). A significant positive correlation between AS and elbow flexion torque was found in high school pitchers (P = .002; β = 0.28), and a significant negative correlation between AS and elbow varus torque (P < .001; β = -0.22) and shoulder internal rotation torque (P < .001; β = -0.20) was noted in professional pitchers.

Conclusion

AS position was related to shoulder abduction and trunk lateral tilt. Professional and high school pitchers with varying AS positions did not experience similar changes in throwing arm kinetics.

Clinical Relevance

In professional pitchers, the earlier onset of maximum upper trunk angular velocity with overhand throwing style may reflect inappropriate pelvis-trunk timing separation, a parameter implicated in upper extremity injury, and the negative correlation between AS and elbow varus and shoulder internal rotation torque suggests that both excessive and minimal AS positions have negative implications.

Machine Learning on Medicare Claims Poorly Predicts the Individual Risk of 30-Day Unplanned Readmission After Total Joint Arthroplasty, Yet Uncovers Interesting Population-level Associations With Annual Procedure Volumes

BACKGROUND

Unplanned hospital readmissions after total joint arthroplasty (TJA) represent potentially serious adverse events and remain a critical measure of hospital quality. Predicting the risk of readmission after TJA may provide patients and clinicians with valuable information for preoperative decision-making.

QUESTIONS/PURPOSES

(1) Can nonlinear machine-learning models integrating preoperatively available patient, surgeon, hospital, and county-level information predict 30-day unplanned hospital readmissions in a large cohort of nationwide Medicare beneficiaries undergoing TJA? (2) Which predictors are the most important in predicting 30-day unplanned hospital readmissions? (3) What specific information regarding population-level associations can we obtain from interpreting partial dependency plots (plots describing, given our modeling choice, the potentially nonlinear shape of associations between predictors and readmissions) of the most important predictors of 30-day readmission?

METHODS

National Medicare claims data (chosen because this database represents a large proportion of patients undergoing TJA annually) were analyzed for patients undergoing inpatient TJA between October 2016 and September 2018. A total of 679,041 TJAs (239,391 THAs [61.3% women, 91.9% White, 52.6% between 70 and 79 years old] and 439,650 TKAs [63.3% women, 90% White, 55.2% between 70 and 79 years old]) were included. Model features included demographics, county-level social determinants of health, prior-year (365-day) hospital and surgeon TJA procedure volumes, and clinical classification software-refined diagnosis and procedure categories summarizing each patient's Medicare claims 365 days before TJA. Machine-learning models, namely generalized additive models with pairwise interactions (prediction models consisting of both univariate predictions and pairwise interaction terms that allow for nonlinear effects), were trained and evaluated for predictive performance using area under the receiver operating characteristic (AUROC; 1.0 = perfect discrimination, 0.5 = no better than random chance) and precision-recall curves (AUPRC; equivalent to the average positive predictive value, which does not give credit for guessing "no readmission" when this is true most of the time, interpretable relative to the base rate of readmissions) on two holdout samples. All admissions (except the last 2 months' worth) were collected and split randomly 80%/20%. The training cohort was formed with the random 80% sample, which was downsampled (so it included all readmissions and a random, equal number of nonreadmissions). The random 20% sample served as the first test cohort ("random holdout"). The last 2 months of admissions (originally held aside) served as the second test cohort ("2-month holdout"). Finally, feature importances (the degree to which each variable contributed to the predictions) and partial dependency plots were investigated to answer the second and third research questions.

RESULTS

For the random holdout sample, model performance values in terms of AUROC and AUPRC were 0.65 and 0.087, respectively, for THA and 0.66 and 0.077, respectively, for TKA. For the 2-month holdout sample, these numbers were 0.66 and 0.087 and 0.65 and 0.075. Thus, our nonlinear models incorporating a wide variety of preoperative features from Medicare claims data could not well-predict the individual likelihood of readmissions (that is, the models performed poorly and are not appropriate for clinical use). The most predictive features (in terms of mean absolute scores) and their partial dependency graphs still confer information about population-level associations with increased risk of readmission, namely with older patient age, low prior 365-day surgeon and hospital TJA procedure volumes, being a man, patient history of cardiac diagnoses and lack of oncologic diagnoses, and higher county-level rates of hospitalizations for ambulatory-care sensitive conditions. Further inspection of partial dependency plots revealed nonlinear population-level associations specifically for surgeon and hospital procedure volumes. The readmission risk for THA and TKA decreased as surgeons performed more procedures in the prior 365 days, up to approximately 75 TJAs (odds ratio [OR] = 1.2 for TKA and 1.3 for THA), but no further risk reduction was observed for higher annual surgeon procedure volumes. For THA, the readmission risk decreased as hospitals performed more procedures, up to approximately 600 TJAs (OR = 1.2), but no further risk reduction was observed for higher annual hospital procedure volumes.

CONCLUSION

A large dataset of Medicare claims and machine learning were inadequate to provide a clinically useful individual prediction model for 30-day unplanned readmissions after TKA or THA, suggesting that other factors that are not routinely collected in claims databases are needed for predicting readmissions. Nonlinear population-level associations between low surgeon and hospital procedure volumes and increased readmission risk were identified, including specific volume thresholds above which the readmission risk no longer decreases, which may still be indirectly clinically useful in guiding policy as well as patient decision-making when selecting a hospital or surgeon for treatment.

LEVEL OF EVIDENCE

Level III, therapeutic study.

A clinical prediction model for 10-year risk of self-reported osteoporosis diagnosis in pre- and perimenopausal women

A machine learning model using clinical, laboratory, and imaging data was developed to predict 10-year risk of menopause-related osteoporosis. The resulting predictions, which are sensitive and specific, highlight distinct clinical risk profiles that can be used to identify patients most likely to be diagnosed with osteoporosis.

PURPOSE

The aim of this study was to incorporate demographic, metabolic, and imaging risk factors into a model for long-term prediction of self-reported osteoporosis diagnosis.

METHODS

This was a secondary analysis of 1685 patients from the longitudinal Study of Women's Health Across the Nation using data collected between 1996 and 2008. Participants were pre- or perimenopausal women between 42 and 52 years of age. A machine learning model was trained using 14 baseline risk factors-age, height, weight, body mass index, waist circumference, race, menopausal status, maternal osteoporosis history, maternal spine fracture history, serum estradiol level, serum dehydroepiandrosterone level, serum thyroid-stimulating hormone level, total spine bone mineral density, and total hip bone mineral density. The self-reported outcome was whether a doctor or other provider had told participants they have osteoporosis or treated them for osteoporosis.

RESULTS

At 10-year follow-up, a clinical osteoporosis diagnosis was reported by 113 (6.7%) women. Area under the receiver operating characteristic curve of the model was 0.83 (95% confidence interval, 0.73-0.91) and Brier score was 0.054 (95% confidence interval, 0.035-0.074). Total spine bone mineral density, total hip bone mineral density, and age had the largest contributions to predicted risk. Using two discrimination thresholds, stratification into low, medium, and high risk, respectively, was associated with likelihood ratios of 0.23, 3.2, and 6.8. At the lower threshold, sensitivity was 0.81, and specificity was 0.82.

CONCLUSION

The model developed in this analysis integrates clinical data, serum biomarker levels, and bone mineral densities to predict 10-year risk of osteoporosis with good performance.

Risk Factors for Graft Failure After Meniscal Allograft Transplantation: A Systematic Review and Meta-analysis

Background

Graft failure after meniscal allograft transplantation (MAT) may necessitate revision surgery or conversion to arthroplasty. A comprehensive understanding of the risk factors for failure after MAT of the knee may facilitate more informed shared decision-making discussions before surgery and help determine whether MAT should be performed based on patient risk.

Purpose

To perform a systematic review and meta-analysis of risk factors associated with graft failure after MAT of the knee.

Study Design

Systematic review; Level of evidence, 4.

Methods

The PubMed, OVID/Medline, and Cochrane databases were queried in October 2021. Data pertaining to study characteristics and risk factors associated with failure after MAT were recorded. DerSimonian-Laird binary random-effects models were constructed to quantitatively evaluate the association between risk factors and MAT graft failure by generating effect estimates in the form of odds ratios (ORs) with 95% CIs. Qualitative analysis was performed to describe risk factors that were variably reported.

Results

In total, 17 studies including 2184 patients were included. The overall pooled prevalence of failure at the latest follow-up was 17.8% (range, 3.3%-81.0%). In 10 studies reporting 5-year failure rates, the pooled prevalence of failure was 10.9% (range, 4.7%-23%). In 4 studies reporting 10-year failure rates, the pooled prevalence was 22.7% (range, 8.1%-55.0%). A total of 39 risk factors were identified, although raw data presented in a manner amenable to meta-analysis only allowed for 3 to be explored quantitatively. There was strong evidence to support that an International Cartilage Regeneration & Joint Preservation Society grade >3a (OR, 5.32; 95% CI, 2.75-10.31; P < .001) was a significant risk factor for failure after MAT. There was no statistically significant evidence to incontrovertibly support that patient sex (OR, 2.16; 95% CI, 0.83-5.64; P = .12) or MAT laterality (OR, 1.11; 95% CI, 0.38-3.28; P = .85) was associated with increased risk of failure after MAT.

Conclusion

Based on the studies reviewed, there was strong evidence to suggest that degree of cartilage damage at the time of MAT is associated with graft failure; however, the evidence was inconclusive on whether laterality or patient sex is associated with graft failure.

What's all the chatter about?

The OpenAI chatbot ChatGPT is an artificial intelligence (AI) application that uses state-of-the-art language processing AI. It can perform a vast number of tasks, from writing poetry and explaining complex quantum mechanics, to translating language and writing research articles with a human-like understanding and legitimacy. Since its initial release to the public in November 2022, ChatGPT has garnered considerable attention due to its ability to mimic the patterns of human language, and it has attracted billion-dollar investments from Microsoft and PricewaterhouseCoopers. The scope of ChatGPT and other large language models appears infinite, but there are several important limitations. This editorial provides an introduction to the basic functionality of ChatGPT and other large language models, their current applications and limitations, and the associated implications for clinical practice and research.

A guide to appropriately planning and conducting meta-analyses: part 3. Special considerations-the network meta-analysis

The meta-analysis has become one of the predominant studies designs in orthopaedic literature. Within recent years, the network meta-analysis has been implicated as a powerful approach to comparing multiple treatments for an outcome of interest when conducting a meta-analysis (as opposed to two competing treatments which is typical of a traditional meta-analysis). With the increasing use of the network meta-analysis, it is imperative for readers to possess the ability to independently and critically evaluate these types of studies. The purpose of this article is to provide the necessary foundation of knowledge to both properly conduct and interpret the results of a network meta-analysis.

Apophyseal ilium avulsion fractures in young athletes: a systematic review and return to sport analysis

The purpose of the current investigation was to synthesize the epidemiology, cause, management, and return to sport (RTS) outcomes of ilium avulsion fractures sustained during sporting activities in young athletes. Studies reporting on athletes <18 years old sustaining an avulsion fracture along the ilium [injury to the anterior superior or inferior iliac spine (ASIS or AIIS), or the iliac crest (IC)], and the athlete's RTS status were included. RTS was analyzed by injury acuity, location, mechanism of injury, and management, whereas complications were recorded. Seventy studies comprising 286 avulsions (169 ASIS, 87 AIIS, and 30 IC) were included. The mean age of athletes was 14.5 + 1.3 years (range, 8-18 years). Sprinting (n = 103/286; 36.0%) and soccer (n = 97/286; 33.9%) were the most common sports during which injuries occurred. A total of 96.5% (n = 276/286) of athletes reported successful RTS at an average of 16.2 + 19.3 weeks. The RTS rate for patients sustaining ASIS, AIIS, and IC avulsions was 95.3, 97.7, and 100%, respectively. Acute trauma was responsible for 89.8% (n = 158/176) of injuries, which demonstrated a significantly faster (13.3 + 9.3 weeks) and higher RTS rate (99.4%) compared with those with chronic avulsions (74.4 + 40.9 weeks and 83.3%, respectively). Those with complications (18.2%) had a significantly lower RTS rate (90.4%) and longer recovery (23.7 weeks) compared with athletes without complications (97.9% and 14.5 weeks, respectively). Outcomes were not significantly different based on sex or management. However, chronic avulsions and postoperative complications sustained worse RTS results. An accurate and timely diagnosis is crucial when presented with these rare injuries to avoid increasing the chronicity of injury.

An Interpretable Machine Learning Model for Predicting 10-Year Total Hip Arthroplasty Risk

BACKGROUND

As the demand for total hip arthroplasty (THA) rises, a predictive model for THA risk may aid patients and clinicians in augmenting shared decision-making. We aimed to develop and validate a model predicting THA within 10 years in patients using demographic, clinical, and deep learning (DL)-automated radiographic measurements.

METHODS

Patients enrolled in the Osteoarthritis Initiative were included. DL algorithms measuring osteoarthritis- and dysplasia-relevant parameters on baseline pelvis radiographs were developed. Demographic, clinical, and radiographic measurement variables were then used to train generalized additive models to predict THA within 10 years from baseline. A total of 4,796 patients were included (9,592 hips; 58% female; 230 THAs (2.4%)). Model performance using 1) baseline demographic and clinical variables 2) radiographic variables, and 3) all variables were compared.

RESULTS

Using 110 demographic and clinical variables, the model had a baseline area under the receiver operating curve (AUROC) of 0.68 and area under the precision recall curve (AUPRC) of 0.08. Using 26 DL-automated hip measurements, the AUROC was 0.77 and AUPRC was 0.22. Combining all variables, the model improved to an AUROC of 0.81 and AUPRC of 0.28. Three of the top five predictive features in the combined model were radiographic variables including minimum joint space along with hip pain and analgesic use. Partial dependency plots revealed predictive discontinuities for radiographic measurements consistent with literature thresholds of osteoarthritis progression and hip dysplasia.

CONCLUSION

A machine learning model predicting 10-year THA performed more accurately with DL radiographic measurements. The model weighted predictive variables in concordance with clinical THA-pathology assessments.

Development and internal validation of machine learning algorithms for predicting complications after primary total hip arthroplasty

INTRODUCTION

Complications after total hip arthroplasty (THA) may result in readmission or reoperation and impose a significant cost on the healthcare system. Understanding which patients are at-risk for complications can potentially allow for targeted interventions to decrease complication rates through pursuing preoperative health optimization. The purpose of the current was to develop and internally validate machine learning (ML) algorithms capable of performing patient-specific predictions of all-cause complications within two years of primary THA.

METHODS

This was a retrospective case-control study of clinical registry data from 616 primary THA patients from one large academic and two community hospitals. The primary outcome was all-cause complications at a minimum of 2-years after primary THA. Recursive feature elimination was applied to identify preoperative variables with the greatest predictive value. Five ML algorithms were developed on the training set using tenfold cross-validation and internally validated on the independent testing set of patients. Algorithms were assessed by discrimination, calibration, Brier score, and decision curve analysis to quantify performance.

RESULTS

The observed complication rate was 16.6%. The stochastic gradient boosting model achieved the best performance with an AUC = 0.88, calibration intercept = 0.1, calibration slope = 1.22, and Brier score = 0.09. The most important factors for predicting complications were age, drug allergies, prior hip surgery, smoking, and opioid use. Individual patient-level explanations were provided for the algorithm predictions and incorporated into an open access digital application: https://sorg-apps.shinyapps.io/tha_complication/ CONCLUSIONS: The stochastic boosting gradient algorithm demonstrated good discriminatory capacity for identifying patients at high-risk of experiencing a postoperative complication and proof-of-concept for creating office-based applications from ML that can perform real-time prediction. However, this clinical utility of the current algorithm is unknown and definitions of complications broad. Further investigation on larger data sets and rigorous external validation is necessary prior to the assessment of clinical utility with respect to risk-stratification of patients undergoing primary THA.

LEVEL OF EVIDENCE

III, therapeutic study.

Propensity for Clinically Meaningful Improvement and Surgical Failure After Anterior Cruciate Ligament Repair

Background

Primary repair of the anterior cruciate ligament (ACL) confers an alternative to ACL reconstruction in appropriately selected patients.

Purpose

To prospectively assess survivorship and to define the clinically meaningful outcomes after ACL repair.

Study Design

Case series; Level of evidence, 4.

Methods

Included were consecutive patients with Sherman grade 1-2 tears who underwent primary ACL repair with or without suture augmentation between 2017 and 2019. Patient-reported outcomes (Lysholm, Tegner, International Knee Documentation Committee, Western Ontario and McMaster Universities Osteoarthritis Index, and Knee injury and Osteoarthritis Outcome Score [KOOS] subscales) were collected preoperatively and at 6 months, 1 year, and 2 years postoperatively. The minimal clinically important difference (MCID) was calculated using a distribution-based method, whereas the Patient Acceptable Symptom State (PASS) and substantial clinical benefit (SCB) were calculated using an anchor-based method. Plain radiographs and magnetic resonance imaging (MRI) were obtained at 6 months, 1 year, and 2 years postoperatively.

Results

A total of 120 patients were included. The overall failure rate was 11.3% at 2 years postoperatively. Changes in outcome scores required to achieve the MCID ranged between 5.1 and 14.3 at 6 months, 4.6 and 8.4 at 1 year, and 4.7 and 11.9 at 2 years postoperatively. Thresholds for PASS achievement ranged between 62.5 and 89 at 6 months, 75 and 89 at 1 year, and 78.6 and 93.2 at 2 years postoperatively. Threshold scores (absolute/change based) for achieving the SCB ranged between 82.8 and 96.4/17.7 and 40.1 at 6 months, between 94.7 and 100/23 and 45 at 1 year, and between 95.3 and 100/29.4 and 45 at 2 years. More patients achieved the MCID and PASS at 1 year compared with 6 months and 2 years. For SCB, this trend was also observed for non-KOOS outcomes, while for KOOS subdomains, more patients achieved the SCB at 2 years. High-intensity signal of the ACL repair (odds ratio [OR], 31.7 [95% CI, 1.5-73.4]; P = .030) and bone contusions on MRI (OR, 4.2 [95% CI, 1.7-25.2]; P = .041) at 1 year postoperatively were independently associated with increased risk of ACL repair failure.

Conclusion

The rate of clinically meaningful outcome improvement was high early after ACL repair, with the greatest proportion of patients achieving the MCID, PASS, and SCB at 1 year postoperatively. Bone contusions involving the posterolateral tibia and lateral femoral condyle as well as high repair signal intensity at 1 year postoperatively were independent predictors of failure at 2 years postoperatively.

Effect of anterior approach compared to posterolateral approach on readiness for discharge and thrombogenic markers in patients undergoing unilateral total hip arthroplasty: a prospective cohort study

INTRODUCTION

The direct anterior approach (DAA) for total hip arthroplasty (THA) is considered less invasive than the posterolateral approach (PLA), possibly leading to earlier mobilization, faster recovery, and lower levels of thrombogenic markers. The purpose of the current study was to prospectively compare readiness for discharge, rehabilitation milestones, markers of thrombosis and inflammation at 6 weeks postoperatively between DAA and PLA.

METHODS

A total of 40 patients (20 anterior and 20 posterolateral) were prospectively enrolled. Readiness for discharge, length of stay (LOS), and related outcomes were additionally documented. Blood was drawn at baseline, wound closure, 5-h post-closure, and 24-h post-closure for assays of interleukin-6 (IL-6), PAP (plasmin anti-plasmin), a marker of fibrinolysis, and PF1.2 (Prothrombin fragment 1.2), a marker of thrombin generation.

RESULTS

Compared to the PLA group, the DAA group was ready for discharge a mean 13 h earlier (p = 0.03), while rehabilitation milestones were met a mean 10 h earlier (p = 0.04), and LOS was 13 h shorter (p = 0.02) on average. Pain scores at all study timepoints and patient satisfaction at 6 weeks were similar (p > 0.05). At 24 h postoperatively, PAP levels were 537.53 ± 94.1 µg/L vs. 464.39 ± 114.6 µg/L (p = 0.05), and Il-6 levels were 40.94 ± 26.1 pg/mL vs. 60.51 ± 33.0 pg/mL (p = 0.03), in DAA vs. PLA, respectively.

CONCLUSIONS

In the immediate postoperative period, DAA patients were ready for discharge before PLA patients. DAA patients had shorter LOS, a lower inflammatory response, and higher systemic markers of fibrinolysis. However, these differences may not be clinically significant. Future studies with larger study populations are warranted to confirm the validity and significance of these findings.

LEVEL OF EVIDENCE

Level II, Therapeutic Study.

Lower donor site morbidity with hamstring and quadriceps tendon autograft compared with bone-patellar tendon-bone autograft after anterior cruciate ligament reconstruction: a systematic review and network meta-analysis of randomized controlled trials

PURPOSE

To perform a meta-analysis of RCTs evaluating donor site morbidity after bone-patellar tendon-bone (BTB), hamstring tendon (HT) and quadriceps tendon (QT) autograft harvest for anterior cruciate ligament reconstruction (ACLR).

METHODS

PubMed, OVID/Medline and Cochrane databases were queried in July 2022. All level one articles reporting the frequency of specific donor-site morbidity were included. Frequentist model network meta-analyses with P-scores were conducted to compare the prevalence of donor-site morbidity, complications, all-cause reoperations and revision ACLR among the three treatment groups.

RESULTS

Twenty-one RCTs comprising the outcomes of 1726 patients were included. The overall pooled rate of donor-site morbidity (defined as anterior knee pain, difficulty/impossibility kneeling, or combination) was 47.3% (range, 3.8-86.7%). A 69% (95% confidence interval [95% CI]: 0.18-0.56) and 88% (95% CI: 0.04-0.33) lower odds of incurring donor-site morbidity was observed with HT and QT autografts, respectively (p < 0.0001, both), when compared to BTB autograft. QT autograft was associated with a non-statistically significant reduction in donor-site morbidity compared with HT autograft (OR: 0.37, 95% CI: 0.14-1.03, n.s.). Treatment rankings (ordered from best-to-worst autograft choice with respect to donor-site morbidity) were as follows: (1) QT (P-score = 0.99), (2) HT (P-score = 0.51) and (3) BTB (P-score = 0.00). No statistically significant associations were observed between autograft and complications (n.s.), reoperations (n.s.) or revision ACLR (n.s.).

CONCLUSION

ACLR using HT and QT autograft tissue was associated with a significant reduction in donor-site morbidity compared to BTB autograft. Autograft selection was not associated with complications, all-cause reoperations, or revision ACLR. Based on the current data, there is sufficient evidence to recommend that autograft selection should be personalized through considering differential rates of donor-site morbidity in the context of patient expectations and activity level without concern for a clinically important change in the rate of adverse events.

LEVEL OF EVIDENCE

Level I.

A guide to appropriately planning and conducting meta-analyses: part 2-effect size estimation, heterogeneity and analytic approaches

Meta-analyses by definition are a subtype of systematic review intended to quantitatively assess the strength of evidence present on an intervention or treatment. Such analyses may use individual-level data or aggregate data to produce a point estimate of an effect, also known as the combined effect, and measure precision of the calculated estimate. The current article will review several important considerations during the analytic phase of a meta-analysis, including selection of effect estimators, heterogeneity and various sub-types of meta-analytic approaches.

Establishing minimal detectable change thresholds for the international knee documentation committee and Kujala scores at one and two years after patellofemoral joint arthroplasty

PURPOSE

To define the minimal detectable change (MDC) for the international knee documentation committee (IKDC) and Kujala scores one and two years after patellofemoral joint arthroplasty (PFA).

METHODS

A distribution-based method (one-half the standard deviation of the mean difference between postoperative and preoperative outcome scores) was applied to establish MDC thresholds among 225 patients undergoing primary PFA at a single high-volume musculoskeletal-care center. Stability of change in MDC achievement was explored by quantifying the proportion of achievement at one- and two-year postoperative timepoints. Multivariable logistic regression analysis was performed to explore the association between sociodemographic and operative features on MDC achievement.

RESULTS

MDC thresholds for the Kujala score were 10.3 (71.1% achievement) and 10.6 (70.4% achievement) at one- and two years, respectively. The MDC thresholds for the IKDC score were 11.2 (78.1% achievement) and 12.3 (69.0% achievement) at one- and two years, respectively. Predictors of achieving the MDC for the Kujala and IKDC scores at both time points were lower preoperative Kujala and IKDC scores, respectively. Preoperative thresholds of ≤ 24.1 and 7.6 for the Kujala and IKDC scores, respectively, were associated with a 90% MDC achievement probability. When preoperative thresholds approached 64.3 and 48.3 for the Kujala and IKDC, respectively, MDC achievement probability reduced to 50%.

CONCLUSION

The MDC thresholds for the Kujala and IKDC scores two years after PFA were 10.6 and 12.3, respectively. Clinically significant health status changes were maintained overall, with a slight decrease in achievement rates between one and two years. MDC achievement was associated with disability at presentation, and several probability-based preoperative thresholds were defined. These findings may assist knee surgeons with patient selection and the decision to proceed with PFA by better understanding the patient-specific propensity for MDC achievement.

LEVEL OF EVIDENCE

IV, retrospective case series.

Examining the Distribution of Bone Bruise Patterns in Contact and Noncontact Acute Anterior Cruciate Ligament Injuries

BACKGROUND

Bone bruises are commonly seen on magnetic resonance imaging (MRI) in acute anterior cruciate ligament (ACL) injuries and can provide insight into the underlying mechanism of injury. There are limited reports that have compared the bone bruise patterns between contact and noncontact mechanisms of ACL injury.

PURPOSE

To examine and compare the number and location of bone bruises in contact and noncontact ACL injuries.

STUDY DESIGN

Cross-sectional study; Level of evidence, 3.

METHODS

Three hundred twenty patients who underwent ACL reconstruction surgery between 2015 and 2021 were identified. Inclusion criteria were clear documentation of the mechanism of injury and MRI within 30 days of the injury on a 3-T scanner. Patients with concomitant fractures, injuries to the posterolateral corner or posterior cruciate ligament, and/or previous ipsilateral knee injury were excluded. Patients were stratified into 2 cohorts based on a contact or noncontact mechanism. Preoperative MRI scans were retrospectively reviewed by 2 musculoskeletal radiologists for bone bruises. The number and location of the bone bruises were recorded in the coronal and sagittal planes using fat-suppressed T2-weighted images and a standardized mapping technique. Lateral and medial meniscal tears were recorded from the operative notes, while medial collateral ligament (MCL) injuries were graded on MRI.

RESULTS

A total of 220 patients were included, with 142 (64.5%) noncontact injuries and 78 (35.5%) contact injuries. There was a significantly higher frequency of men in the contact cohort compared with the noncontact cohort (69.2% vs 54.2%, P = .030), while age and body mass index were comparable between the 2 cohorts. The bivariate analysis demonstrated a significantly higher rate of combined lateral tibiofemoral (lateral femoral condyle [LFC] + lateral tibial plateau [LTP]) bone bruises (82.1% vs 48.6%, P < .001) and a lower rate of combined medial tibiofemoral (medial femoral condyle [MFC] + medial tibial plateau [MTP]) bone bruises (39.7% vs 66.2%, P < .001) in knees with contact injuries. Similarly, noncontact injuries had a significantly higher rate of centrally located MFC bone bruises (80.3% vs 61.5%, P = .003) and posteriorly located MTP bruises (66.2% vs 52.6%, P = .047). When controlling for age and sex, the multivariate logistical regression model demonstrated that knees with contact injuries were more likely to have LTP bone bruises (OR, 4.721 [95% CI, 1.147-19.433], P = .032) and less likely to have combined medial tibiofemoral (MFC + MTP) bone bruises (OR, 0.331 [95% CI, 0.144-0.762], P = .009) compared with those with noncontact injuries.

CONCLUSION

Significantly different bone bruise patterns were observed on MRI based on ACL injury mechanism, with contact and noncontact injuries demonstrating characteristic findings in the lateral tibiofemoral and medial tibiofemoral compartments, respectively.

Social Media Use Among Arthroscopic and Orthopaedic Sports Medicine Specialists Varies by Subspeciality

Purpose

To evaluate active social media use among members of the Arthroscopy Association of North America (AANA) and investigate differences in social media use based on joint-specific subspecialization.

Methods

The AANA membership directory was queried to identify all active, residency-trained orthopaedic surgeons within the United States. Sex, practice location, and academic degrees earned were recorded. Google searches were conducted to find professional Facebook, Twitter, Instagram, LinkedIn, and YouTube accounts along with institutional and personal websites. The primary outcome was the Social Media Index (SMI) score, an aggregate measure of social media use across key platforms. A Poisson regression model was constructed to compare SMI scores across joint-specific subspecializations: knee, hip, shoulder, elbow, foot & ankle, and wrist. Specialization in the treatment of each joint was collected using binary indicator variables. Since surgeons were specialized in multiple groups, comparisons were made between those who do and do not treat each joint.

Results

In total, 2,573 surgeons within the United States met the inclusion criteria. 64.7% had ownership of at least 1 active account, with an average SMI score of 2.29 ± 1.59. Western practicing surgeons had a significantly greater presence on at least 1 website than those in the Northeast (P = .003, P < .001) and South (P = .005, P = .002). Social media use by knee, hip, shoulder, and elbow surgeons was greater relative to those who did not treat those respective joints (P < .001 for all). Poisson regression analysis demonstrated that knee, shoulder, or wrist specialization was a significant positive predictor of a greater SMI score (P ≤ .001 for all). Foot & ankle specialization was a negative predictor (P < .001), whereas hip (P = .125) and elbow (P = .077) were not significant predictors.

Conclusions

Social media use widely varies across joint subspecialties within orthopaedic sports medicine. Knee and shoulder surgeons had a greater social media use than their counterparts, whereas foot & ankle surgeons had the lowest social media use.

Clinical Relevance

Social media is a vital source of information for both patients and surgeons, providing a means for marketing, networking, and education. It is important to identify variations in social media use by orthopaedic surgeons by subspecialty and explore the differences.

Standardized Fixation Zones and Cone Assessments for Revision Total Knee Arthroplasty Using Deep Learning

BACKGROUND

Achieving adequate implant fixation is critical to optimize survivorship and postoperative outcomes after revision total knee arthroplasty (rTKA). Three anatomical zones (ie, epiphysis, metaphysis, and diaphysis) have been proposed to assess fixation, but are not well-defined. The purpose of the study was to develop a deep learning workflow capable of automatically delineating rTKA zones and cone placements in a standardized way on postoperative radiographs.

METHODS

A total of 235 patients who underwent rTKA were randomly partitioned (6:2:2 training, validation, and testing split), and a U-Net segmentation workflow was developed to delineate rTKA fixation zones and assess revision cone placement on anteroposterior radiographs. Algorithm performance for zone delineation and cone placement were compared against ground truths from a fellowship-trained arthroplasty surgeon using the dice segmentation coefficient and accuracy metrics.

RESULTS

On the testing cohort, the algorithm defined zones in 98% of images (8 seconds/image) using anatomical landmarks. The dice segmentation coefficient between the model and surgeon was 0.89 ± 0.08 (interquartile range [IQR]:0.88-0.94) for femoral zones, 0.91 ± 0.08 (IQR: 0.91-0.95) for tibial zones, and 0.90 ± 0.05 (IQR:0.88-0.94) for all zones. Cone identification and zonal cone placement accuracy were 98% and 96%, respectively, for the femur and 96% and 89%, respectively, for the tibia.

CONCLUSION

A deep learning algorithm was developed to automatically delineate revision zones and cone placements on postoperative rTKA radiographs in an objective, standardized manner. The performance of the algorithm was validated against a trained surgeon, suggesting that the algorithm demonstrated excellent predictive capabilities in accordance with relevant anatomical landmarks used by arthroplasty surgeons in practice.

The Top 50 Most Cited Publications in Meniscus Research

Injuries to the menisci of the knee are common in orthopedic sports medicine. Bibliometric studies can identify the core literature on a topic and help further our collective knowledge for both clinical and educational purposes. The purpose of the current study was to (1) identify and describe the 50 most cited articles in meniscus research over an 80-year time period to capture a wide range of influential articles and (2) identify the "citation classics" and milestone articles related to the meniscus of the knee. The Science Citation Index Expanded subsection of the Web of Science Core Collection was systematically searched for the 50 most cited meniscus articles. Data pertaining to bibliometric and publication characteristics were extracted and reported using descriptive statistics. The top 50 articles were published between the years 1941 and 2014 and collectively cited 13,152 times. The median (interquartile [IQR]) number of total citations per article was 203.5 (167.0-261.8), while the median citation rate was 9.6 (7.4-13.9) citations per year. The most cited article was "Knee joint changes after meniscectomy," published in 1948. The article with the highest citation rate of 78.4 citations per year was "The long-term consequence of anterior cruciate ligaments and meniscus injuries - osteoarthritis," published in 2007. The majority of articles were clinical outcome studies (n = 28, 56%). The top 50 most cited meniscus articles represent a compilation of highly influential articles which may augment reading curriculums and provide a strong knowledge base for orthopaedic surgery residents and fellows. The decade with the most articles was the 2000s, representing a recent acceleration in meniscus-based research. This is a level IV, cross-sectional study.

A Guide for the Application of Statistics in Biomedical Studies Concerning Machine Learning and Artificial Intelligence

With the plethora of machine learning (ML) analyses published in the orthopaedic literature within the last 5 years, several attempts have been made to enhance our understanding of what exactly ML means and how it is used. At its most fundamental level, ML comprises a branch of artificial intelligence that uses algorithms to analyze and learn from patterns in data without explicit programming or human intervention. On the other hand, traditional statistics require a user to specifically choose variables of interest to create a model capable of predicting an outcome, the output of which (1) may be falsely influenced by the variables chosen to be included by the user and (2) does not allow for optimization of performance. Early publications have served as succinct editorials or reviews intended to ease audiences unfamiliar with ML into the complexities that accompany the subject. Most commonly, the focus of these studies concerns the terminology and concepts surrounding ML because it is important to understand the rationale behind performing such studies. Unfortunately, these publications only touch on the most basic aspects of ML and are too frequently repetitive. Indeed, the conclusion of these articles reiterate that the potential clinical utility of these algorithms remains tangential at best in their current form and caution against premature adoption without external validation. By doing so, our perspective and ability to draw our own conclusions from these studies have not advanced, and we are left concluding with each subsequent study that a new algorithm is published for an outcome of interest that cannot be used until further validation. What readers now need is to regress to embrace the principles of the scientific method that they have used to critically assess vast numbers of publications before this wave of newly applied statistical methodology-a guide to interpret results such that their own conclusions can be drawn. LEVEL OF EVIDENCE: Level V, expert opinion.

Association Between Limited English Language Proficiency and Disparities in Length of Stay and Discharge Disposition After Total Shoulder Arthroplasty: A Retrospective Cohort Study

Background: Limited English language proficiency in patients undergoing total shoulder arthroplasty (TSA) may make treatment more challenging. Purpose: We sought to investigate the potential association between TSA patients' use of a language interpreter and 2 outcomes: hospital length of stay (LOS) and discharge disposition. Methods: We conducted a retrospective cohort study comparing LOS and discharge disposition after TSA for patients who required interpreter services and patients who did not at a single institution in an urban setting between 2016 and 2020. Consecutive patients requiring interpreter services who underwent TSA were matched 1:1 to patients who did not require an interpreter by age, body mass index (BMI), sex, and procedure. Multivariate regression models controlling for age, BMI, sex, smoking, opioid use, white or non-white race, procedure, and diagnosis were constructed to determine associations between interpreter use, LOS, and discharge disposition. Results: Forty-one patients were included in each cohort, exceeding the minimum number required per an a priori power analysis. Mean hospital LOS was longer in the interpreter cohort than in the non-interpreter cohort (2.8 ± 2.4 vs 1.8 ± 1.0 days, respectively). Multivariate linear regression demonstrated interpreter use was the strongest predictor of LOS, with the effect estimate indicating an additional 0.88-day LOS per patient. A greater proportion of patients from the interpreter cohort were discharged to an acute/subacute rehabilitation facility than patients from the non-interpreter cohort (n = 8 [19.5%] vs n = 2 [4.9%], respectively). Patients from the interpreter cohort were 454% more likely to be discharged to acute/subacute rehabilitation facilities. Conclusions: Our retrospective analysis of patients undergoing TSA suggests that the need for interpreter services may be associated with increased LOS and discharge to a facility. More rigorous study is needed to identify the factors that influence these outcomes and to avoid disparities in hospital stay and discharge.

No Difference in Complication or Reoperation Rates Between Arthroscopic and Open Debridement for Lateral Epicondylitis: A National Database Study

PURPOSE

To compare complication rates and 5-year reoperation rates between open debridement (OD) and arthroscopic debridement (AD) for lateral epicondylitis.

METHODS

The PearlDiver MUExtr database (2010-2019) was reviewed for patients diagnosed with lateral epicondylitis (queried by International Classification of Diseases, Ninth Revision and International Classification of Diseases, Tenth Revision [ICD-10] codes) undergoing OD or AD of the common extensor tendon without repair (queried by Current Procedural Terminology codes). Patients were stratified into 2 cohorts: those who underwent AD and those who underwent OD. Nonoperative treatment modalities were reported for both groups within 1 year before index procedure. The rates of 90-day postoperative complications were compared, and multivariate logistic regression analysis was used to identify risk factors for complications. The 5-year reoperation rates, using laterality-specific ICD-10 codes, were also compared between the 2 groups.

RESULTS

In total, 19,280 patients (OD = 17,139, AD = 2,141) were analyzed in this study. The most common nonoperative treatments for patients who underwent OD or AD were corticosteroid injections (49.5% vs 43.2%), physical therapy (24.8% vs 25.7%), bracing (2.8% vs 3.2%), and platelet-rich plasma injections (1.3% vs 1.0%). There were no significant differences in radial nerve injuries, hematomas, surgical site infections, wound dehiscence, and sepsis events between the 2 procedures (P = .50). The 5-year reoperation rate was not significantly different between the AD (5.0%) and OD (3.9%) cohorts (P = .10).

CONCLUSIONS

For lateral epicondylitis, both AD and OD of the extensor carpi radialis brevis (without repair) were found to have low rates of 90-day adverse events, with no significant differences between the 2 approaches. Similarly, the 5-year reoperation rate was low and not statistically different for those treated with OD or AD.

LEVEL OF EVIDENCE

Level III, cross-sectional study.

Examining Preoperative MRI for Medial Meniscal Ramp Lesions in Patients Surgically Treated for Acute Grade 3 Combined Posterolateral Corner Knee Injury

Background

While medial meniscocapsular tears (ramp lesions) are commonly associated with isolated anterior cruciate ligament injuries, there are limited descriptions of these meniscal injuries in multiligament knee injuries (MLKIs).

Purpose

To (1) retrospectively evaluate preoperative magnetic resonance imaging (MRI) scans for the presence of ramp lesions in patients surgically treated for acute grade 3 combined posterolateral corner (PLC) knee injuries and (2) determine if a preoperative posteromedial tibial plateau (PMTP) bone bruise is associated with the presence of preoperative ramp lesions on MRI in these same patients.

Study Design

Cross-sectional study; Level of evidence, 3.

Methods

Data on consecutive patients at a level 1 trauma center with MLKIs between 2001 and 2021 were retrospectively reviewed. Only patients with acute grade 3 combined PLC injuries who received an MRI scan within 30 days of injury were assessed. Two musculoskeletal radiologists retrospectively reviewed each patient's preoperative MRI for evidence of ramp lesions and bone bruises. Intraclass correlation coefficients (ICCs) were used to calculate reliability among the reviewers. Multivariate analysis was used to evaluate the relationship between PMTP bruising and the presence of a ramp lesion on MRI.

Results

A total of 68 patients (79.4% male; mean age, 33.8 ± 13.7 years) with an acute grade 3 combined PLC injury were included in the study. On MRI, the ICCs for detection of ramp lesions and PMTP bone bruising were 0.921 and 0.938, respectively. Medial meniscal ramp lesions were diagnosed in 18 of 68 (26.5%) patients. Eleven of 18 (61.1%) patients with ramp lesions also showed evidence of PMTP bruising, while 13 of 50 (26.0%) patients without ramp lesions had PMTP bruising (P = .008). When controlling for age and sex, PTMP bruising was significantly associated with the presence of a ramp lesion in combined PLC injuries (odds ratio, 4.62; P = .012).

Conclusion

Preoperative medial meniscal ramp lesions were diagnosed on MRI in 26.5% of patients with acute grade 3 combined PLC injuries. PMTP bone bruising was significantly associated with the presence of a ramp lesion on MRI. These findings reinforce the need to assess for potential ramp lesions at the time of multiligament reconstruction.

The Altmetric Attention Score Is Associated With Citation Rates and May Reflect Academic Impact in the Total Joint Arthroplasty Literature

Background: Given the increasing interest and potential use of social media for the promotion of orthopedic literature, there is a need to better understand Altmetrics. Purposes: We sought to determine the relationship between the Altmetric Attention Score (AAS) and the number of citations for articles on total joint arthroplasty (TJA) published in orthopedics journals. We also sought to determine the predictors of greater social media attention for these articles. Methods: Articles on TJA published in Bone and Joint Journal (BJJ), Journal of Bone and Joint Surgery (JBJS), Clinical Orthopedics and Related Research (CORR), Journal of Arthroplasty, Journal of Knee Surgery, Hip International, and Acta Orthopaedica in 2016 were extracted (n = 498). One-way analysis of variance with Bonferroni corrections was used to compare AAS and citations across journals. Multivariate regressions were used to determine predictors of social media attention and number of citations. Results: The mean AAS and number of citations were 7.5 (range: 0-289) and 16.7 (range: 0-156), respectively. Significant between-group effects were observed according to journal for AAS and number of citations. Publishing an article in JBJS was the strongest predictor of higher number of citations. Publishing an article in BJJ was the only independent predictor of higher AAS, while publishing an article in JBJS or CORR trended toward statistical significance. A higher AAS was a significant predictor of a higher number of citations. Number of citations and number of study references were positive predictors of greater social media attention on Twitter and Facebook. Conclusions: In articles on TJA published in 7 journals in 2016, a higher AAS was a associated with a higher number of citations. Various bibliometric characteristics were found to be significantly associated with greater social media attention; the most common influences were number of citations and number of references. Researchers in orthopedics can use this information when considering how to assess the impact of their work.

Radiographic findings involved in knee osteoarthritis progression are associated with pain symptom frequency and baseline disease severity: a population-level analysis using deep learning

PURPOSE

To (1) develop a deep-learning (DL) algorithm capable of producing limb-length and knee-alignment measurements, and (2) determine the association between limb-length discrepancy (LLD), coronal-plane alignment, osteoarthritis (OA) severity, and patient-reported knee pain.

METHODS

A multicenter, prospective patient cohort from the Osteoarthritis Initiative between 2004 and 2015 with full-limb standing radiographs at 12 month follow-up was included. A convolutional neural network was developed to automate measurements of the hip-knee-ankle (HKA) angle, femur, and tibia lengths, and LLD. At 12 month follow-up, patients reported their frequency of knee pain since enrollment and current level of knee pain.

RESULTS

A total of 1011 patients (2022 knees, 52.3% female) with an average age of 61.2 ± 9.0 years were included. The algorithm performed 12,312 measurements in 5.4 h. ICC values of HKA and LLD ranged between 0.87 and 1.00 when compared against trained radiologist measurements. Knees producing pain most days of the month were significantly more varus (mean HKA:- 3.9° ± 2.8°) or valgus (mean HKA:2.8° ± 2.3°) compared to knees that did not produce any pain (p < 0.05). In varus knees, those producing pain on most days were part of the shorter limb compared to nonpainful knees (p < 0.05). Baseline Kellgren-Lawrence grade was significantly associated with HKA magnitude, LLD, and pain frequency at 12 month follow-up (p < 0.05 all).

CONCLUSION

A higher frequency of knee pain was associated with more severe coronal plane deformity, with valgus deviation being one degree less than varus on average, suggesting that the knee tolerates less valgus deformation before symptoms become more consistent. Knee pain frequency was also associated with greater LLD and baseline KL grade, suggesting an association between radiographically apparent joint degeneration and pain frequency.

LEVEL OF EVIDENCE

IV case series.

Choosing the appropriate measure of central tendency: mean, median, or mode?

Mean, median, and mode are among the most basic and consistently used measures of central tendency in statistical analysis and are crucial for simplifying data sets to a single value. However, there is a lack of understanding of when to use each metric and how various factors can impact these values. The aim of this article is to clarify some of the confusion related to each measure and explain how to select the appropriate metric for a given data set. The authors present this work as an educational resource, ensuring that these common statistical concepts are better understood throughout the Orthopedic research community.

Treatment of an Iatrogenic Lateral Meniscal Root Tear After ACL Reconstruction

Background:

The meniscal roots are essential for preserving the structural and biomechanical properties of the tibiofemoral joint. Posterior meniscal root avulsions can cause meniscal extrusion, joint space narrowing, and progressive knee arthritis. Iatrogenic avulsions after malpositioning of the transtibial tunnels during anterior cruciate ligament (ACL) reconstruction have previously been reported in the literature to account for poor long-term outcomes seen in some patients following ACL reconstruction. Therefore, correct transtibial tunnel placement during ACL reconstruction is essential to avoid iatrogenic meniscal damage.

Indication:

Patients are indicated for surgery when presenting with a verified, symptomatic, complete meniscal root tear seen on advanced imaging or diagnostic arthroscopy. Contraindications for a root repair include the development of advanced osteoarthritis in the ipsilateral compartment, older age, and malalignment in the affected compartment.

Technique Description:

The ACL graft was appreciated and noted to be vertical and posterior relative to its native anatomical position, violating the lateral posterior horn root attachment. A full lateral posterior meniscal root avulsion was then confirmed directly adjacent to the graft tunnel. A curette was used to prepare the footprint of the lateral meniscal root on the posterolateral tibia for the 2-tunnel transtibial pull-out tunnels, and a grasper was used to position the torn meniscal root back into its anatomical site. Two ultrabraided sutures were passed through the posterior horn of the lateral meniscus using a suture passer. These were then passed through the tunnels into the body of the meniscal root and reduced to its native anatomical position. The suture repair was then secured over an Endobutton Fixation Device at 90° of knee flexion through each tunnel into its native anatomical position while confirming its adequate tension by viewing arthroscopically.

Results:

Within 2 years postoperatively, patients are expected to have improved overall knee-specific quality of life, reduced pain, and a successful return to activities.

Discussion/Conclusion:

This injury underscores the importance of an accurate tibial tunnel placement during ACL reconstruction to avoid posterior meniscal root injuries and other associated complications. Physicians should consider such pathology in the differential diagnosis of patients presenting with persistent pain and instability following a primary ACL reconstruction.

Patient Consent Disclosure Statement:

The author(s) attests that consent has been obtained from any patient(s) appearing in this publication. If the individual may be identifiable, the author(s) has included a statement of release or other written form of approval from the patient(s) with this submission for publication.

Injury to the Posterior Horn of the Lateral Meniscus from a Misplaced Tibial Tunnel for Anterior Cruciate Ligament Reconstruction: A Case Report

BACKGROUND Posterior meniscal root avulsions can cause meniscal extrusion, joint space narrowing, and progressive knee arthritis. Iatrogenic posterior meniscal root avulsions after malpositioning of the transtibial tunnels during anterior cruciate ligament (ACL) reconstruction can account for poor long-term outcomes seen in some patients following ACL reconstruction. Therefore, correct transtibial tunnel placement during ACL reconstruction is essential to avoid iatrogenic meniscal damage. CASE REPORT A 32-year-old man presented with 1 year of right knee pain and instability following a non-contact twisting injury sustained while playing soccer. An ACL tear with no meniscal involvement was diagnosed at an outside institution. A double-bundle reconstruction was performed at that time. Three months after surgery, a medial partial meniscectomy was performed after a medial meniscal tear and failure to reduce initial symptoms during the index procedure. Advanced imaging at our institution 6 months later demonstrated an iatrogenic lateral posterior meniscal root avulsions after malpositioning of the transtibial tunnels. Given the ACL graft integrity upon arthroscopic evaluation, the root tear was repaired using a 2-tunnel transtibial pull-out technique. Advanced imaging 1 year after surgery showed a well-maintained meniscal repair with no extrusion. CONCLUSIONS Accurate transtibial tunnel placement during ACL reconstructive surgery is vital to avoid meniscal root detachment and the associated complications resulting in poor patient outcomes from this iatrogenic injury. Clinicians treating patients with a history of cruciate ligament reconstruction presenting with postoperative pain and instability should consider this pathology in their differential diagnosis.