Systematic evaluation of common natural language processing techniques to codify clinical notes.

Proper codification of medical diagnoses and procedures is essential for optimized health care management, quality improvement, research, and reimbursement tasks within large healthcare systems. Assignment of diagnostic or procedure codes is a tedious manual process, often prone to human error. Natural Language Processing (NLP) has been suggested to facilitate this manual codification process. Yet, little is known on best practices to utilize NLP for such applications. With Large Language Models (LLMs) becoming more ubiquitous in daily life, it is critical to remember, not every task requires that level of resource and effort. Here we comprehensively assessed the performance of common NLP techniques to predict current procedural terminology (CPT) from operative notes. CPT codes are commonly used to track surgical procedures and interventions and are the primary means for reimbursement. Our analysis of 100 most common musculoskeletal CPT codes suggest that traditional approaches can outperform more resource intensive approaches like BERT significantly (P-value = 4.4e-17) with average AUROC of 0.96 and accuracy of 0.97, in addition to providing interpretability which can be very helpful and even crucial in the clinical domain. We also proposed a complexity measure to quantify the complexity of a classification task and how this measure could influence the effect of dataset size on model's performance. Finally, we provide preliminary evidence that NLP can help minimize the codification error, including mislabeling due to human error.

Prevalence and Predictors of Concomitant Meniscal Surgery During Pediatric and Adolescent ACL Reconstruction: Analysis of 4729 Patients Over 20 Years at a Tertiary-Care Regional Children's Hospital.

Background: The rate of concomitant meniscal procedures performed in conjunction with anterior cruciate ligament (ACL) reconstruction is increasing. Few studies have examined these procedures in high-risk pediatric cohorts. Hypotheses: That (1) the rates of meniscal repair compared with meniscectomy would increase throughout the study period and (2) patient-related factors would be able to predict the type of meniscal operation, which would differ according to age. Study Design: Cohort study (prevalence); Level of evidence, 2. Methods: Natural language processing was used to extract clinical variables from notes of patients who underwent ACL reconstruction between 2000 and 2020 at a single institution. Patients were stratified to pediatric (5-13 years) and adolescent (14-19 years) cohorts. Linear regression was used to evaluate changes in the prevalence of concomitant meniscal surgery during the study period. Logistic regression was used to determine predictors of the need for and type of meniscal procedure. Results: Of 4729 patients (mean age, 16 ± 2 years; 54.7% female) identified, 2458 patients (52%) underwent concomitant meniscal procedures (55% repair rate). The prevalence of lateral meniscal (LM) procedures increased in both pediatric and adolescent cohorts, whereas the prevalence of medial meniscal (MM) repair increased in the adolescent cohort (P = .02). In the adolescent cohort, older age was predictive of concomitant medial meniscectomy (P = .031). In the pediatric cohort, female sex was predictive of concomitant MM surgery and of undergoing lateral meniscectomy versus repair (P≤ .029). Female sex was associated with decreased odds of concomitant LM surgery in both cohorts (P≤ .018). Revision ACLR was predictive of concomitant MM surgery and of meniscectomy (medial and lateral) in the adolescent cohort (P < .001). Higher body mass index was associated with increased odds of undergoing medial meniscectomy versus repair in the pediatric cohort (P = .03). Conclusion: More than half of the young patients who underwent ACLR had meniscal pathology warranting surgical intervention. The prevalence of MM repair compared with meniscectomy in adolescents increased throughout the study period. Patients who underwent revision ACLR were more likely to undergo concomitant meniscal surgeries, which were more often meniscectomy. Female sex had mixed effects in both the pediatric and adolescent cohorts.

Changes in Functional Meniscal Morphology During Skeletal Growth and Maturation.

Background: Little is known on how meniscal morphology develops during skeletal growth and maturation and its subsequent relationship with the corresponding bony anatomy. Hypotheses: (1) Meniscal dimensions and morphology would change by age during skeletal growth and maturation in different ways in boys compared with girls. (2) Morphological features of the medial and lateral menisci would correlate to medial and lateral femoral condyle curvatures. Study Design: Cross-sectional study; Level of evidence, 3. Methods: Anatomic features of the medial and lateral menisci were measured on magnetic resonance imaging scans from 269 unique knees (age, 3-18 years; 51% female) with no prior history of injury, congenital or growth-related skeletal disorders, or bony deformities. Morphological shape-based measurements were normalized to tibial plateau width or determined as ratios of meniscal dimensions. The association between age and anatomy was analyzed with linear regression. Two-way analysis of variance with the Holm-Sídák post hoc method was used to compare anatomy between sexes in different age groups. Linear regression was used to evaluate the relationship between femoral condyle curvature radius and meniscal morphology in each compartment after adjusting for age and sex. Results: Meniscal length, width, horn distance, mean cross-sectional area (CSA), and mean height increased with age in both sexes (R2 > 0.1; P < .001). Age-related changes in meniscal morphology were seen in normalized length, width, horn distance, and mean height; width-to-length ratio; horn distance-to-length ratio (lateral meniscus only); normalized mean CSA (except lateral meniscus in girls); and mean tip angle (R2 > 0.04; P < .02). Sex-based differences were also found, with some morphological differences (normalized length and height) throughout development (P < .03) and size differences (length, width, and mean CSA) in later development (P < .01). After adjusting for age and sex, there were significant correlations between medial condyle curvature radius and normalized width, width-to-length ratio, horn distance, horn distance-to-length ratio, mean CSA, and mean height of the medial meniscus (P≤ .041) and between lateral condyle curvature radius and normalized length, mean height, and mean tip angle of the lateral meniscus (P≤ .004). Conclusion: Age-related changes in meniscal dimensions and morphology, most notably a nonuniform growth pattern in meniscal geometry, occurred during skeletal growth and maturation, with different trends in boys than in girls.

Telehealth Potential in Pediatric Orthopaedics and Sports Medicine Care is Comparable to In-Person Care But Disparities Remain.

BACKGROUND: Understanding the challenges and potential of telehealth visits (THVs) in a large population can inform future practice and policy discussion for pediatric orthopaedic and sports medicine (OSM) care. We comprehensively assess telehealth challenges and potential in a large pediatric OSM population based on access, visit completion, patient satisfaction, and technological challenges. METHODS: Demographics, address, insurance, visit information, patient feedback, experience with video visits, and technical challenges of all 2019 to 2020 visits at our hospital were assessed (3,278,006 visits). We evaluated the differences in rate of telehealth utilization, rate of patient adherence, disparities in care access and patient satisfaction, and technological issues. RESULTS: Compared with in-person prepandemic visits, THVs had lower ratios of non-White patients (by 5.8%; P<0.001), Hispanic patients (by 2.8%; P<0.001) and patients with public insurance (by 1.8%; P<0.001), and a higher mean distance between the patient's residence and clinic (by 18.8 miles; P<0.001). There were minimal differences in median household income (average $2297 less in THV; P<0.001) and social vulnerability index (average 0.01 points lower in THV; P<0.001) between groups. THVs had comparable patient satisfaction to in-person visits. Non-White patients, Hispanics, and those with public insurance had lower ratings for both in-person visits and THVs and had more technical difficulties during their THV. CONCLUSIONS: Telehealth is a viable method of care for a range of pediatric OSM conditions, providing a similar quality of care as in-person visits with a greater geographic reach. However, in its current format, reduced disparities were not observed in pediatric OSM THVs. LEVEL OF EVIDENCE: Level III.

Comprehensive evaluation of magnetic resonance imaging sequences for signal intensity based assessment of anterior cruciate ligament healing following surgical treatment.

Normalized signal intensity (SI) obtained from magnetic resonance imaging (MRI) has been used to track anterior cruciate ligament (ACL) postoperative remodeling. We aimed to assess the effect of MRI sequence (PD: proton density-weighted; T2: T2-weighted; CISS: constructive interference in steady state) on postoperative changes in healing ACLs/grafts. We hypothesized that CISS is better at detecting longitudinal SI and texture changes of the healing ACL/graft compared to the common clinical sequences (PD and T2). MR images of patients who underwent ACL surgery were evaluated and separated into groups based on surgical procedure (Bridge-Enhanced ACL Repair (BEAR; n = 50) versus ACL reconstruction (ACLR; n = 24)). CISS images showed decreasing SI across all timepoints in both the BEAR and ACLR groups (p < 0.01), PD and T2 images showed decreasing SI in the 6-to-12- and 12-to-24-month postoperative timeframes in the BEAR group (p < 0.02), and PD images additionally showed decreasing SI between 6- and 24-months postoperation in the ACLR group (p = 0.02). CISS images showed texture changes in both the BEAR and ACLR groups, showing increases in energy and decreases in entropy in the 6-to-12- and 6-to-24-month postoperative timeframes in the BEAR group (p < $\lt $ 0.04), and increases in energy, decreases in entropy, and increases in homogeneity between 6 and 24 months postoperation in the ACLR group (p < 0.04). PD images showed increases in energy and decreases in entropy between 6- and 24-months postoperation in the ACLR group (p < 0.008). Finally, CISS was estimated to require a smaller sample size than PD and T2 to detect SI differences related to postoperative remodeling.

Protocol and validity testing of femoroacetabular posterior translation with dynamic hip ultrasonography.

OBJECTIVE: To describe femoroacetabular posterior translation (FAPT) using dynamic hip ultrasonography (DHUS), and to determine the inter- and intra-rater reliability of hip ultrasound measurements of FAPT. MATERIALS AND METHODS: The study design was a feasibility study of 13 healthy young adults (26 hips) using test-retest analysis. The data was collected prospectively over a 2-week time period. Three DHUS measurements (posterior neutral (PN), flexion, adduction, and internal rotation (PFADIR), and stand and load (PStand) were measured by four independent raters (2 senior who divided the cohort, 1 intermediate, 1 junior) at two time points for bilateral hips of each participant. Reliability was assessed by calculating the intraclass correlation coefficient (ICC) along with 95% confidence intervals (CIs) for each rater and across all raters. RESULTS: A total of 468 US scans were completed. The mean age of the cohort was 25.7 years (SD 5.1 years) and 54% were female. The inter-rater reliability was excellent for PFADIR (ICC 0.85 95% CI 0.76-0.91), good for PN (ICC 0.69 95% CI 0.5-0.81), and good for PStand (ICC 0.72 95% CI 0.55-0.83). The intra-rater reliability for all raters was good for PFADIR (ICC 0.60 95% CI 0.44-0.73), fair for PN (ICC 0.42 95% CI 0.21-0.59), and fair for PStand (ICC 0.42 95% CI 0.22-0.59). CONCLUSION: This is the first study to present a protocol using dynamic ultrasonography to measure FAPT. DHUS measure for FAPT was shown to be reliable across raters with varying levels of ultrasound experience.

Prevalence and Predictors of Concomitant Meniscal and Ligamentous Injuries Associated With ACL Surgery: An Analysis of 20 Years of ACL Reconstruction at a Tertiary Care Children's Hospital.

BACKGROUND: There is an increasing rate of procedures being performed for concomitant injuries during anterior cruciate ligament (ACL) surgery. Few studies have examined risk factors for these associated injuries in young patients. HYPOTHESIS: There are patient-related factors predictive of concomitant knee pathology that differ between age-based cohorts. STUDY DESIGN: Cross-sectional study; Level of evidence, 3. METHODS: Natural language processing was used to extract clinical variables from available notes of patients undergoing ACL surgery between 2000 and 2020 at a single institution (5174 ACL surgeries; mean age, 17 ± 4 years; 53.1% female; accuracy, >98%). Patients were stratified to pediatric (5-13 years), adolescent (14-19 years), and young adult (20-35 years) cohorts. Logistic regression was used to determine predictors of concomitant injury to the menisci, medial collateral ligament (MCL), posterolateral corner (PLC), and posterior cruciate ligament (PCL). RESULTS: Between 2000 and 2020, 54% of pediatric, 71% of adolescent, and 70% of adult patients had ≥1 concomitant soft tissue injury. In children and adolescents, increased age was consistently predictive of sustaining a concomitant injury (P < .02). Female children had increased odds of concomitant medial meniscal injury, while female adults had decreased odds (P≤ .046). Adolescent and adult female patients had decreased odds of concomitant lateral meniscal injury (P≤ .027). Female children had increased odds of injury to the MCL (P = .015), whereas female children and adolescents had decreased odds of PCL injury (P≤ .044). Adolescents undergoing revision ACL surgery had increased odds of meniscal injury (P≤ .001) and decreased odds of concomitant MCL injury (P = .028). Increased body mass index (BMI) was associated with increased odds of concomitant medial meniscal injury in all cohorts (P≤ .041), lateral meniscal injury in adults (P = .045), and PLC injury in children (P = .016). Contact injuries were associated with increased odds of MCL injury in adolescents (P = .017) and PLC injury in adolescents and adults (P < .014). CONCLUSION: These findings support the hypothesis, as there were multiple factors that significantly affected the risk of concomitant injuries that differed between cohorts. Increased age, BMI, and contact injury history were generally associated with increased odds of sustaining a concomitant injury, whereas female sex and revision ACL surgery had mixed effects. Further studies are essential to investigate the sex-based differences in risk for concomitant injuries and to develop tailored treatment plans that minimize the risk of secondary ACL injury.

The Effects of Residual Femoral Deformity on Computed Contact Mechanics in Patients Treated With In Situ Fixation for Slipped Capital Femoral Epiphysis.

OBJECTIVE: In situ fixation for treatment of slipped capital femoral epiphysis (SCFE) can stabilize the epiphysis and prevent further joint deformation but often leaves residual deformity that may adversely affect intra-articular contact mechanics. The purpose of this study was to investigate the relationship between residual deformity and contact mechanics in the post-SCFE hip. METHODS: Patient-specific hip models were created for 19 patients with SCFE treated with in situ fixation. For each model, discrete element analysis was used to compute cumulative acetabular and femoral contact stress exposure during a walking gait cycle. Slip severity was evaluated for each patient using the two-dimensional Southwick angle and a novel three-dimensional (3D) assessment of multiplanar femoral deformity (3D slip angle). RESULTS: Of the SCFE cases, 2/7 mild (Southwick angle ≤30 degrees) had peak cumulative femoral exposures equivalent to that of severe (Southwick angle ≥60 degrees) cases. Severe SCFE cases had higher peak ( P = 0.015) and mean ( P = 0.028) femoral contact stress exposure and lower cumulative femoral contact area ( P = 0.003) than mild (Southwick angle ≤30 degrees) SCFE cases. Mean femoral contact stress exposure was also higher in severe SCFE cases than in moderate SCFE cases ( P = 0.027). Acetabular and femoral contact mechanics metrics typically demonstrated stronger correlations with 3D slip angle than two-dimensional Southwick angle. CONCLUSIONS: Increased slip severity adversely impacts intra-articular femoral contact mechanics. Contact mechanics metrics demonstrate higher correlations with 3D slip angle, indicating that this novel measurement may better describe global deformity and its relationship to intra-articular mechanics; however, the modest strength of these correlations may also imply that global impingement-generating deformity is not the primary factor driving contact mechanics in the post-SCFE hip. CLINICAL RELEVANCE: Greater slip severity adversely impacts contact mechanics in the post-SCFE hip. However, focal regions of high contact stress were seen even in mild SCFE deformities, suggesting some type of deformity correction should be considered even for mild slips to alleviate secondary impingement, address focal incongruities, and reduce osteoarthritis development/progression.

Comparison of Size of Posterior Tibial Slope and Medial Tibial Depth in Patients With an Isolated Meniscal Tear Requiring Surgery and Matched Uninjured Controls.

BACKGROUND: Meniscal injuries are extremely common. Several anatomic features of the knee, including the tibial plateau morphology, have been shown to influence knee biomechanics and the risk of ligamentous injuries. Little is known, however, how these morphological features influence the risk of isolated meniscal injuries in the anterior cruciate ligament (ACL)-intact knee. HYPOTHESIS: There are differences in the slopes and concavity of the tibial plateau between patients with isolated meniscal tears and matched uninjured controls. STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: In total, 89 patients with first-instance isolated medial (n = 37) or lateral (n = 52) meniscal injuries requiring surgical treatment (mean age, 16 ± 1 years; 35% female) were matched to 89 controls with uninjured knees and no previous injuries (mean age, 16 ± 2 years; 35% female) based on age and sex. Magnetic resonance imaging scans (preoperative for injured group) were used to measure the coronal slope of the tibial plateau, posterior slope of the medial and lateral tibial plateaus, and maximum depth of the medial tibial plateau. General linear models were used to evaluate the differences in tibial plateau morphology between the knees with and without meniscal injuries, with and without adjustment for age and sex. RESULTS: Compared with matched controls, patients with surgically treated isolated meniscal tears had a smaller lateral tibial slope (by 2.2° [medial meniscal injury] and 1.6° [lateral meniscal injury]; P < .02), a smaller medial tibial slope (by 2.3° [medial meniscal injury] and 2.4° [lateral meniscal injury]; P < .001) and a larger medial tibial depth (by 0.8 mm [medial meniscal injury] and 0.9 mm [lateral meniscal injury]; P < .001). There were no differences in coronal tibial slope between the injured and uninjured groups. There were no differences in quantified anatomic features between the isolated medial and lateral meniscal injury groups. The same trends were observed after adjusting for age and sex. CONCLUSION: This study suggests that patients with an isolated meniscal tear requiring surgery have a smaller posterior tibial slope and a larger medial tibial depth (more concave medial tibial plateau) than matched uninjured controls. This is contrary to what is known for ACL tears, in which a steeper posterior tibial slope and a shallower medial tibial depth have been associated with an increased risk of ACL tear.

LigaNET: A multi-modal deep learning approach to predict the risk of subsequent anterior cruciate ligament injury after surgery.

Anterior cruciate ligament (ACL) injuries are a common cause of soft tissue injuries in young active individuals, leading to a significant risk of premature joint degeneration. Postoperative management of such injuries, in particular returning patients to athletic activities, is a challenge with immediate and long-term implications including the risk of subsequent injury. In this study, we present LigaNET, a multi-modal deep learning pipeline that predicts the risk of subsequent ACL injury following surgical treatment. Postoperative MRIs (n=1,762) obtained longitudinally between 3 to 24 months after ACL surgery from a cohort of 159 patients along with 11 non-imaging outcomes were used to train and test: 1) a 3D CNN to predict subsequent ACL injury from segmented ACLs, 2) a 3D CNN to predict injury from the whole MRI, 3) a logistic regression classifier predict injury from non-imaging data, and 4) a multi-modal pipeline by fusing the predictions of each classifier. The CNN using the segmented ACL achieved an accuracy of 77.6% and AUROC of 0.84, which was significantly better than the CNN using the whole knee MRI (accuracy: 66.6%, AUROC: 0.70; P<.001) and the non-imaging classifier (accuracy: 70.1%, AUROC: 0.75; P=.039). The fusion of all three classifiers resulted in highest classification performance (accuracy: 80.6%, AUROC: 0.89), which was significantly better than each individual classifier (P<.001). The developed multi-modal approach had similar performance in predicting the risk of subsequent ACL injury from any of the imaging sequences (P>.10). Our results demonstrate that a deep learning approach can achieve high performance in identifying patients at high risk of subsequent ACL injury after surgery and may be used in clinical decision making to improve postoperative management (e.g., safe return to sports) of ACL injured patients.

MRI Analysis of Knee Bony Morphology Variations in Children and Adolescents With Lateral Discoid Meniscus Compared With Asymptomatic Healthy Controls.

BACKGROUND: Lateral discoid meniscus accounts for most meniscal tears in children 10 years of age and younger. The role of bony morphology in discoid meniscus has been previously studied in a limited capacity using radiographs. PURPOSE: To use magnetic resonance imaging to measure features of the femoral condyles and tibial plateaus in patients with discoid meniscus to assess potential determinants of symptoms and subsequent surgery and to compare with matched controls to investigate age-related changes in bony features. STUDY DESIGN: Cross-sectional study; Level of evidence, 3. METHODS: After institutional review board approval, detailed morphology of the femoral condyles and tibial plateau was measured in 177 patients (3-18 years of age; 56% female) with confirmed lateral discoid meniscus. Measurements from 269 participants (3-18 years of age; 55% female) with asymptomatic knees were used as controls. Two-way analysis of variance with Holm-Sídák post hoc was used to compare measurements between discoid menisci and matched controls. Independent t tests were used to compare aspects of bony morphology within the discoid meniscus cohort. RESULTS: Compared with controls, patients with a lateral discoid meniscus had a larger bicondylar width and notch width (7- to 10-year-old and 15- to 18-year-old age groups; P < .05), larger tibial plateau width (11- to 14-year-old and 15- to 18-year-old age groups; P < .001), and smaller lateral (P < .02) and coronal (P < .02) tibial slopes across all age groups. Among patients with a discoid meniscus, larger bicondylar width, larger tibial plateau width, larger notch width, and a flatter lateral femoral condyle were associated with pain (P < .005) and lateral meniscal tears (P < .02). Larger notch width and notch width index were also associated with subsequent surgery (P < .05). CONCLUSION: There are clinically significant abnormalities in bony morphology in patients with a discoid meniscus, including larger femoral condyles and tibial plateaus and a flatter tibial plateau. Additionally, femoral size, femoral curvature, and tibial plateau size may influence the likelihood of knee pain, meniscal tear, and need for surgery. These findings highlight the importance of bony morphology in discoid meniscus pathophysiology in children and adolescents. Such measurements may also aid radiographic detection of discoid meniscus and guide decisions regarding the timing of potential surgical intervention.

Disparities in cannabis use and documentation in electronic health records among children and young adults.

The legalizations of medical and recreational cannabis have generated a great deal of interest in studying the health impacts of cannabis products. Despite increases in cannabis use, its documentation during clinical visits is not yet mainstream. This lack of information hampers efforts to study cannabis's effects on health outcomes. A clear and in-depth understanding of current trends in cannabis use documentation is necessary to develop proper guidelines to screen and document cannabis use. Here we have developed and used a natural language processing pipeline to evaluate the trends and disparities in cannabis documentation. The pipeline includes a screening step to identify clinical notes with cannabis use documentation which is then fed into a BERT-based classifier to confirm positive use. This pipeline is applied to more than 23 million notes from a large cohort of 370,087 patients seen in a high-volume multi-site pediatric and young adult clinic over a period of 21 years. Our findings show a very low but growing rate of cannabis use documentation (<2%) in electronic health records with significant demographic and socioeconomic disparities in both documentation and positive use, which requires further attention.

Excessive Femoral Anteversion Leading to Symptomatic Posterior Femoroacetabular Impingement, Cam Deformity of the Posterior Femoral Head-Neck Junction, and Anterior Hip Instability in a Dancer: A Case Report.

CASE: An adolescent female dancer with excessive femoral anteversion presented with posterior and anterior hip pain aggravated by poses that required extension and external rotation. Imaging revealed an atypical cam deformity of the posterior head-neck junction. During surgery, the posterior head-neck junction was observed to impinge on the posterior acetabulum with anterior subluxation of the hip. After a derotational femoral osteotomy, the patient experienced resolution of her symptoms. CONCLUSION: Excessive femoral anteversion can lead to reactive cam deformity, posterior intra-articular impingement, and anterior hip instability in patients who require repetitive hip extension and external rotation, such as ballet dancers.

Development of Anatomic Risk Factors for ACL Injuries: A Comparison Between ACL-Injured Knees and Matched Controls.

BACKGROUND: Several tibiofemoral anatomic features have been repeatedly associated with increased anterior cruciate ligament (ACL) injury risk. Previous studies have highlighted age and sex differences among these anatomic risk factors, but little is known about the normal and pathologic development of these differences during skeletal maturation. PURPOSE: To investigate differences in anatomic risk factors at various stages of skeletal maturation between ACL-injured knees and matched controls. STUDY DESIGN: Cross-sectional study; Level of evidence, 3. METHODS: After institutional review board approval, magnetic resonance imaging scans from 213 unique ACL-injured knees (age, 7-18 years, 48% female) and 239 unique asymptomatic ACL-intact knees (age, 7-18 years, 50% female) were used to measure femoral notch width, posterior slope of the lateral and medial tibial plateau, medial and lateral tibial spinal height (MTSH, LTSH), medial tibial depth, and posterior lateral meniscus-bone angle. Linear regression was performed to assess change in quantified anatomic indices with age for male and female patients in the ACL-injured cohort. Two-way analysis of variance with Holm-Sidak post hoc testing was performed to compare anatomic indices between ACL-injured knees and ACL-intact controls in each age group. RESULTS: In the ACL-injured cohort, notch width, notch width index and medial tibial depth increased with age (R2 > 0.1; P < .001) in both sexes. MTSH and LTSH increased with age only in boys (R2≥ 0.09; P≤ .001), whereas meniscus-bone angle decreased with age only in girls (R2 = 0.13; P < .001). There were no other age differences in quantified anatomic indices. Patients with ACL injury consistently had a significantly higher lateral tibial slope (P < .01) and smaller LTSH (P < .001) as compared with ACL-intact controls across all age groups and sexes. When compared with age- and sex-matched ACL-intact controls, ACL-injured knees had a smaller notch width (boys, 7-18 years; girls, 7-14 years; P < .05), larger medial tibial slope (boys and girls, 15-18 years; P < .01), smaller MTSH (boys, 7-14 years; girls, 11-14 years; P < .05), and larger meniscus-bone angle (girls, 7-10 years; P = .050). CONCLUSION: The consistent morphologic differences throughout skeletal growth and maturation suggest a developmental role in high-risk knee morphology. The observed high-risk knee morphology at an earlier age preliminarily suggests the potential of knee anatomy measurements in identifying those with a predisposition toward ACL injury.

Predicting anterior cruciate ligament failure load with T2* relaxometry and machine learning as a prospective imaging biomarker for revision surgery.

Non-invasive methods to document healing anterior cruciate ligament (ACL) structural properties could potentially identify patients at risk for revision surgery. The objective was to evaluate machine learning models to predict ACL failure load from magnetic resonance images (MRI) and to determine if those predictions were related to revision surgery incidence. It was hypothesized that the optimal model would demonstrate a lower mean absolute error (MAE) than the benchmark linear regression model, and that patients with a lower estimated failure load would have higher revision incidence 2 years post-surgery. Support vector machine, random forest, AdaBoost, XGBoost, and linear regression models were trained using MRI T2* relaxometry and ACL tensile testing data from minipigs (n = 65). The lowest MAE model was used to estimate ACL failure load for surgical patients at 9 months post-surgery (n = 46) and dichotomized into low and high score groups via Youden's J statistic to compare revision incidence. Significance was set at alpha = 0.05. The random forest model decreased the failure load MAE by 55% (Wilcoxon signed-rank test: p = 0.01) versus the benchmark. The low score group had a higher revision incidence (21% vs. 5%; Chi-square test: p = 0.09). ACL structural property estimates via MRI may provide a biomarker for clinical decision making.

Effects of joint loading on the development of capital femoral epiphysis morphology.

INTRODUCTION: The deleterious influence of increased mechanical forces on capital femoral epiphysis development is well established; however, the growth of the physis in the absence of such forces remains unclear. The hips of non-ambulatory cerebral palsy (CP) patients provide a weight-restricted (partial weightbearing) model which can elucidate the influence of decreased mechanical forces on the development of physis morphology, including features related to development of slipped capital femoral epiphysis (SCFE). Here we used 3D image analysis to compare the physis morphology of children with non-ambulatory CP, as a model for abnormal hip loading, with age-matched native hips. MATERIALS AND METHODS: CT images of 98 non-ambulatory CP hips (8-15 years) and 80 age-matched native control hips were used to measure height, width, and length of the tubercle, depth, width, and length of the metaphyseal fossa, and cupping height across different epiphyseal regions. The impact of age on morphology was assessed using Pearson correlations. Mixed linear model was used to compare the quantified morphological features between partial weightbearing hips and full weightbearing controls. RESULTS: In partial weightbearing hips, tubercle height and length along with fossa depth and length significantly decreased with age, while peripheral cupping height increased with age (r > 0.2, P < 0.04). Compared to normally loaded (full weightbearing) hips and across all age groups, partially weightbearing hips' epiphyseal tubercle height and length were smaller (P < .05), metaphyseal fossa depth was larger (P < .01), and posterior, inferior, and anterior peripheral cupping heights were smaller (P < .01). CONCLUSIONS: Smaller epiphyseal tubercle and peripheral cupping with greater metaphyseal fossa size in partial weightbearing hips suggests that the growing capital femoral epiphysis requires mechanical stimulus to adequately develop epiphyseal stabilizers. Deposit low prevalence and relevance of SCFE in CP, these findings highlight both the role of normal joint loading in proper physis development and how chronic abnormal loading may contribute to various pathomorphological changes of the proximal femur (i.e., capital femoral epiphysis).

Smaller epiphyseal tubercle in hips with slipped capital femoral epiphysis compared to the uninvolved contralateral hip.

Recent investigations suggest that physeal morphologic features have a major role in the capital femoral epiphysis stability and slipped capital femoral epiphysis (SCFE) pathology, with a smaller epiphyseal tubercle and larger peripheral cupping of the femoral epiphysis being present in hips with progressive SCFE compared to healthy controls. Yet, little is known on the causal versus remodeling nature of these associations. This study aimed to use preoperative magnetic resonance imaging (MRI) of patients with unilateral SCFE to perform a comparison of the morphology of the epiphyseal tubercle, metaphyseal fossa, and peripheral cupping in hips with SCFE versus the contralateral uninvolved hips. Preoperative MRIs from 22 unilateral SCFE patients were used to quantify the morphological features of the epiphyseal tubercle (height, width, and length), metaphyseal fossa (depth, width, and length), and peripheral cupping height in three dimension. The quantified anatomical features were compared between hips with SCFE and the contralateral uninvolved side across the whole cohort and within SCFE severity subgroups using paired t-test. We found significantly smaller epiphyseal tubercle heights (p < 0.001) across all severities of SCFE when compared to their uninvolved contralateral side. There was a marginally smaller metaphyseal fossa length (p = 0.05) in SCFE hips compared to their contralateral uninvolved hips, with mild SCFE hips specifically having smaller fossa and epiphyseal lengths (p < 0.05) than their contralateral uninvolved side. There were no side-to-side differences in any other features of the epiphyseal tubercle, metaphyseal fossa and peripheral cupping across all severities (p > 0.05). These findings suggest a potential causal role of epiphyseal tubercle in SCFE pathogenesis.

Quantitative MRI Biomarkers to Predict Risk of Reinjury Within 2 Years After Bridge-Enhanced ACL Restoration.

BACKGROUND: Quantitative magnetic resonance imaging (qMRI) methods were developed to establish the integrity of healing anterior cruciate ligaments (ACLs) and grafts. Whether qMRI variables predict risk of reinjury is unknown. PURPOSE: To determine if qMRI measures at 6 to 9 months after bridge-enhanced ACL restoration (BEAR) can predict the risk of revision surgery within 2 years of the index procedure. STUDY DESIGN: Cohort study; Level of evidence, 2. METHODS: Originally, 124 patients underwent ACL restoration as part of the BEAR I, BEAR II, and BEAR III prospective trials and had consented to undergo an MRI of the surgical knee 6 to 9 months after surgery. Only 1 participant was lost to follow-up, and 4 did not undergo MRI, leaving a total of 119 patients for this study. qMRI techniques were used to determine the mean cross-sectional area; normalized signal intensity; and a qMRI-based predicted failure load, which was calculated using a prespecified equation based on cross-sectional area and normalized signal intensity. Patient-reported outcomes (International Knee Documentation Committee subjective score), clinical measures (hamstring strength, quadriceps strength, and side-to-side knee laxity), and functional outcomes (single-leg hop) were also measured at 6 to 9 months after surgery. Univariate and multivariable analyses were performed to determine the odds ratios (ORs) for revision surgery based on the qMRI and non-imaging variables. Patient age and medial posterior tibial slope values were included as covariates. RESULTS: In total, 119 patients (97%), with a median age of 17.6 years, underwent MRI between 6 and 9 months postoperatively. Sixteen of 119 patients (13%) required revision ACL surgery. In univariate analyses, higher International Knee Documentation Committee subjective score at 6 to 9 months postoperatively (OR = 1.66 per 10-point increase; P = .035) and lower qMRI-based predicted failure load (OR = 0.66 per 100-N increase; P = .014) were associated with increased risk of revision surgery. In the multivariable model, when adjusted for age and posterior tibial slope, the qMRI-based predicted failure load was the only significant predictor of revision surgery (OR = 0.71 per 100 N; P = .044). CONCLUSION: Quantitative MRI-based predicted failure load of the healing ACL was a significant predictor of the risk of revision within 2 years after BEAR surgery. The current findings highlight the potential utility of early qMRI in the postoperative management of patients undergoing the BEAR procedure.

Automated segmentation of the healed anterior cruciate ligament from T2 * relaxometry MRI scans.

Collagen organization of the anterior cruciate ligament (ACL) can be evaluated using T2 * relaxometry. However, T2 * mapping requires manual image segmentation, which is a time-consuming process and prone to inter- and intra- segmenter variability. Automating segmentation would address these challenges. A model previously trained using Constructive Interference in Steady State (CISS) scans was applied to T2 * segmentation via transfer learning. It was hypothesized that there would be no significant differences in the model's segmentation performance between T2 * and CISS, structural measures versus ground truth manual segmentation, and reliability versus independent and retest manual segmentation. Transfer learning was conducted using 54 T2 * scans of the ACL. Segmentation performance was assessed with Dice coefficient, precision, and sensitivity, and structurally with T2 * value, volume, subvolume proportions, and cross-sectional area. Model performance relative to independent manual segmentation and repeated segmentation by the ground truth segmenter (retest) were evaluated on a random subset. Segmentation performance was analyzed with Mann-Whitney U tests, structural measures with Wilcoxon signed-rank tests, and performance relative to manual segmentation with repeated-measures analysis of variance/Tukey tests (α = 0.05). T2 * segmentation performance was not significantly different from CISS on all measures (p > 0.35). No significant differences were detected in structural measures (p > 0.50). Automatic segmentation performed as well as the retest on all segmentation measures, whereas independent segmentations were lower than retest and/or automatic segmentation (p < 0.023). Structural measures were not significantly different between segmenters. The automatic segmentation model performed as well on the T2 * sequence as on CISS and outperformed independent manual segmentation while performing as well as retest segmentation.

Three-dimensional magnetic resonance imaging analysis shows sex-specific patterns in changes in anterior cruciate ligament cross-sectional area along its length.

Smaller anterior cruciate ligament (ACL) size in females has been hypothesized to be a key contributor to a higher incidence of ACL tears in that population, as a lower cross-sectional area (CSA) directly corresponds to a larger stress on the ligament for a given load. Prior studies have used a mid-length CSA measurement to quantify ACL size. In this study, we used magnetic resonance imaging to quantify the CSA along the entire length of the intact ACL. We hypothesized that changes in the ACL CSA along its length would have different patterns in males and females. We also hypothesized that changes in ACL CSA along its length would be associated with body size or knee size with different associations in females and males. MR images of contralateral ACL-intact knees of 108 patients (62 females, 13-35 years) undergoing ACL surgery were used to measure the CSA along the ACL length, using a custom program. For both females and males, the largest CSA was located at 37%-39% of ACL length from the tibial insertion. Compared to females, males had a significantly larger CSA only within the distal 41% of the ACL (p < 0.001). ACL CSA was associated with patient height and weight in males (r > 0.3; p < 0.05), whereas it was associated with intercondylar notch width in females (r > 0.3; p < 0.05). These findings highlight the importance of standardizing the location of measurement of ACL CSA.