No significant difference in thick versus thin osteochondral flap trochleoplasty in the treatment of trochlear dysplasia: A systematic review.

PURPOSE: Trochleoplasty has become increasingly utilised to address patellar instability in the setting of severe trochlear dysplasia. There remains a paucity of literature on the outcomes of 'thick'- versus 'thin'-osteochondral flap trochleoplasty. The purpose of this study is to compare clinical and radiographic outcomes between patients with patellar instability with symptomatic trochlear dysplasia treated using a 'thick' versus 'thin' osteochondral flap trochleoplasty. METHODS: A systematic review and meta-analysis were conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines using a PRISMA checklist. Quality assessment of final articles was conducted by two blinded reviewers. Articles were separated based on the use of a 'thick' versus 'thin' flap trochleoplasty. Data collection consisted of recording the following variables: patient demographics, indications for trochleoplasty, mean follow-up time, additional procedures performed during trochleoplasty, patient-reported outcome measures (PROMs), radiographic outcomes (tibial tubercle-trochlear groove [TT-TG] distance, Caton-Deschamps Index [CDI] and sulcus angle [SA]) and the incidence of any postoperative complications and patellar redislocation rates. RESULTS: A total of 24 studies, consisting of 927 patients, were identified as meeting inclusion criteria. A total of five papers described a 'thick' flap technique, while 19 papers described the use of a 'thin' flap technique. No significant difference in the mean improvement of Kujala scores was appreciated when comparing 'thick' versus 'thin' techniques (p > 0.05). Improvements in mean radiographic outcomes based on TT-TG, CDI and SA were observed in both 'thick' and 'thin' flap trochleoplasty groups. The overall redislocation rate was 0.35%. CONCLUSION: No significant difference in Kujala scores was observed in patients undergoing trochleoplasty utilising 'thick' versus 'thin' technique, while improvements in mean TT-TG, CDI and SA were noted in both technique groups, with an overall redislocation rate of 0.35%. LEVEL OF EVIDENCE: Level IV.

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.

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.

Lateral meniscus posterior root repair in the setting of anterior cruciate ligament reconstruction restores joint mechanics to the intact state and improves clinical function: a systematic review of biomechanical and clinical outcomes.

PURPOSE: To perform a systematic review of biomechanical and clinical outcomes following lateral meniscus posterior root (LMPR) repair with concomitant anterior cruciate ligament reconstruction (ACLR). METHODS: A literature search was performed systematically using PubMed, Embase, and Medline databases in April 2022. The search included the following terms combined with Boolean operators: 'Meniscus repairs', 'Meniscal Repair', 'Posterior Horn', 'Root', 'Radial'. Inclusion criteria consisted of level I-IV human clinical and biomechanical studies reporting biomechanical data and/or outcomes following LMPR repair in the setting of ACLR. RESULTS: Three biomechanical studies, all utilizing a transtibial pullout technique, were identified, all of which reported significant improvement in joint contact pressures and mechanics and 3/4 of which reported significant improvement in anterior or rotational stability with LMPR repair. Five clinical studies, consisting of 146 patients (mean age 28.5 ± 1.1 years) undergoing LMPR repair, were identified with an average follow-up of 19.1 months (range 6.2-46 months). Across all clinical studies, Lysholm and International Knee Documentation Committee (IKDC) scores were found to improve postoperatively, with 3/4 reporting significant improvement in Lysholm (all, p ≤ 0.001) scores and 3/5 reporting significant improvement in IKDC scores when compared to preoperative values (all, p ≥ 0.004). Meniscal extrusion decreased significantly following repair in 2/4 studies (all, p ≤ 0.001). CONCLUSIONS: Biomechanically, transtibial pullout repair of the LMPR restored joint contact pressures and joint mechanics to intact levels when performed with concomitant ACLR. Clinically, LMPR repair with concurrent ACLR resulted in improved Lysholm and IKDC scores. These findings enable surgeons to determine optimal treatment plans and discuss realistic outcomes with patients when encountering LMPR injuries. LEVEL OF EVIDENCE: IV.

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.

High Rate of Return to Work by 3 Months Following Latarjet for Anterior Shoulder Instability.

PURPOSE: To evaluate the rate and duration of return to work in patients undergoing Latarjet for failed soft-tissue stabilization or glenoid bone loss. METHODS: Consecutive patients undergoing Latarjet from 2005 to 2015 at our institution were retrospectively reviewed at a minimum of 2 years postoperatively. Patients completed a standardized and validated work questionnaire, Western Ontario Shoulder Instability Index Survey, and a satisfaction survey. RESULTS: Of 89 eligible patients who had Latarjet, 67 patients (75.3%) responded to the questionnaire, of whom 51 patients (76.1%) were employed within 3 years before surgery (mean age: 29.9 ± 11.8 years; mean follow-up: 54.6 ± 11.9 months) and had an average glenoid bone loss of 14.5 ± 6.1%. Fifty patients (98.0%) returned to work by 2.7 ± 3.0 months postoperatively; 45 patients (88.2%) patients returned to the same level of occupational intensity. Those who held sedentary, light, moderate, or heavy intensity occupations returned to their previous occupation at a rate of 100.0%, 93.3%, 90.0%, and 66.7% (P = .2) at a duration of 1.2 ± 1.6 months, 1.8 ± 1.9 months, 3.1 ± 3.5 months, and 6.5 ± 4.1 months (P = .001), respectively. The average postoperative Western Ontario Shoulder Instability Index score was 70.9 ± 34.2. Fifty patients (98.0%) noted at least "a little improvement" in their quality of life following surgery, with 35 patients (68.6%) noting great improvement. Furthermore, 49 patients (96.1%) reported being satisfied with their procedure, with 25 patients (49.0%) reporting being very satisfied. Four patients (7.8%) returned to the operating room, with 1 patient (2.0%) requiring arthroscopic shoulder stabilization. CONCLUSIONS: Approximately 98% of patients who underwent Latarjet returned to work by 2.7 ± 3.0 months postoperatively. Patients with greater-intensity occupations had a longer duration of absence before returning to their preoperative level of occupational intensity. Information regarding return to work is imperative in preoperative patient consultation to manage expectations. LEVEL OF EVIDENCE: IV, case series.

Machine learning algorithms predict within one size of the final implant ultimately used in total knee arthroplasty with good-to-excellent accuracy.

PURPOSE: To develop a novel machine learning algorithm capable of predicting TKA implant sizes using a large, multicenter database. METHODS: A consecutive series of primary TKA patients from two independent large academic and three community medical centers between 2012 and 2020 was identified. The primary outcomes were final tibial and femoral implant sizes obtained from an automated inventory system. Five machine learning algorithms were trained using six routinely collected preoperative features (age, sex, height, weight, and body mass index). Algorithms were validated on an independent set of patients and evaluated through accuracy, mean absolute error (MAE), and root mean-squared error (RMSE). RESULTS: A total of 11,777 patients were included. The support vector machine (SVM) algorithm had the best performance for femoral component size(MAE = 0.73, RMSE = 1.06) with accuracies of 42.2%, 88.3%, and 97.6% for predicting exact size, ± one size, and ± two sizes, respectively. The elastic-net penalized linear regression (ENPLR) algorithm had the best performance for tibial component size (MAE 0.70, RMSE = 1.03) with accuracies of 43.8%, 90.0%, and 97.7% for predicting exact size, ± one size, and ± two sizes, respectively. CONCLUSION: Machine learning algorithms demonstrated good-to-excellent accuracy for predicting within one size of the final tibial and femoral components used for TKA. Patient height and sex were the most important factors for predicting femoral and tibial component size, respectively. External validation of these algorithms is imperative prior to use in clinical settings. LEVEL OF EVIDENCE: Case-control, III.

Establishing Clinically Significant Outcomes After Anterior Cruciate Ligament Reconstruction in Pediatric Patients.

PURPOSE: The purpose of this study was to establish clinically significant outcome values for the minimal clinically important difference (MCID) and patient acceptable symptomatic state (PASS) after anterior cruciate ligament reconstruction (ACLR) in the pediatric and adolescent populations and to assess factors that were associated with achieving these outcomes. METHODS: Patients between the age of 10 to 21 who underwent ACLR between 2016 and 2018 were identified and patient-reported outcomes (PROs) were collected preoperatively and postoperatively. Intraoperative variables collected included graft choice, graft size (diameter), graft fixation method, and concomitant procedures. PROs collected for analysis were the International Knee Documentation Committee Score (IKDC) and Knee Injury and Osteoarthritis Outcome Score (KOOS). MCID and PASS were calculated using receiver operating characteristic with area under the curve analyses for delta (ie, baseline-to-postoperative change) and absolute postoperative PRO scores, respectively. RESULTS: A total of 59 patients were included in the analysis. Of the entire study population, 53 (89.8%) reported satisfaction with their surgical outcome. The established MCID threshold values based on the study population were 33.3 for IKDC, 28.6 for (KOOS) Symptoms, 19.4 for Pain, 2.9 for activities of daily living (ADL), 45.0 for Sport, and 25.0 for Quality of Life (QoL). Postoperative scores greater than the following values corresponded to the PASS: 80.5 for IKDC, 75.0 (KOOS) Symptoms, 88.9 for Pain, 98.5 for ADL, 75.0 for Sport, and 68.8 for QoL. CONCLUSION: Clinically meaningful outcomes including MCID and PASS were established for pediatric ACLR surgery using selected PRO measures, IKDC, and KOOS. Patient age, sex, graft type, and graft size were not associated with greater achievement of these outcomes. In contrast, collision sports, fixed-object high-impact rotational landing sports, and concomitant meniscectomy surgery were associated with a decreased likelihood of achieving clinically significant improvement. However, findings must be interpreted with caution due to limitations in follow-up and sample size. LEVEL OF EVIDENCE: Level IV: case series.

Machine Learning Algorithms Predict Clinically Significant Improvements in Satisfaction After Hip Arthroscopy.

PURPOSE: To develop machine learning algorithms to predict failure to achieve clinically significant satisfaction after hip arthroscopy. METHODS: We queried a clinical repository for consecutive primary hip arthroscopy patients treated between January 2012 and January 2017. Five supervised machine learning algorithms were developed in a training set of patients and internally validated in an independent testing set of patients by discrimination, Brier score, calibration, and decision-curve analysis. The minimal clinically important difference (MCID) for the visual analog scale (VAS) score for satisfaction was derived by an anchor-based method and used as the primary outcome. RESULTS: A total of 935 patients were included, of whom 148 (15.8%) did not achieve the MCID for the VAS satisfaction score at a minimum of 2 years postoperatively. The best-performing algorithm was the neural network model (C statistic, 0.94; calibration intercept, -0.43; calibration slope, 0.94; and Brier score, 0.050). The 5 most important features to predict failure to achieve the MCID for the VAS satisfaction score were history of anxiety or depression, lateral center-edge angle, preoperative symptom duration exceeding 2 years, presence of 1 or more drug allergies, and Workers' Compensation. CONCLUSIONS: Supervised machine learning algorithms conferred excellent discrimination and performance for predicting clinically significant satisfaction after hip arthroscopy, although this analysis was performed in a single population of patients. External validation is required to confirm the performance of these algorithms. LEVEL OF EVIDENCE: Level III, therapeutic case-control study.

Development and Internal Validation of Supervised Machine Learning Algorithms for Predicting Clinically Significant Functional Improvement in a Mixed Population of Primary Hip Arthroscopy.

PURPOSE: To (1) develop and validate a machine learning algorithm to predict clinically significant functional improvements after hip arthroscopy for femoroacetabular impingement syndrome and to (2) develop a digital application capable of providing patients with individual risk profiles to determine their propensity to gain clinically significant improvements in function. METHODS: A retrospective review of consecutive hip arthroscopy patients who underwent cam/pincer correction, labral preservation, and capsular closure between January 2012 and 2017 from 1 large academic and 3 community hospitals operated on by a single high-volume hip arthroscopist was performed. The primary outcome was the minimal clinically important difference (MCID) for the Hip Outcome Score (HOS)-Activities of Daily Living (ADL) at 2 years postoperatively, which was calculated using a distribution-based method. A total of 21 demographic, radiographic, and patient-reported outcome measures were considered as potential covariates. An 80:20 random split was used to create training and testing sets from the patient cohort. Five supervised machine learning algorithms were developed using 3 iterations of 10-fold cross-validation on the training set and assessed by discrimination, calibration, Brier score, and decision curve analysis on an independent testing set of patients. RESULTS: A total of 818 patients with a median (interquartile range) age of 32.0 (22.0-42.0) and 69.2% female were included, of whom 74.3% achieved the MCID for the HOS-ADL. The best-performing algorithm was the stochastic gradient boosting model (c-statistic = 0.84, calibration intercept = 0.20, calibration slope = 0.83, and Brier score = 0.13). Of the initial 21 candidate variables, the 8 most important features for predicting the MCID for the HOS-ADL included in model training were body mass index, age, preoperative HOS-ADL score, preoperative pain level, sex, Tönnis grade, symptom duration, and drug allergies. The algorithm was subsequently transformed into a digital application using local explanations to provide customized risk assessment: https://orthoapps.shinyapps.io/HPRG_ADL/. CONCLUSIONS: The stochastic boosting gradient model conferred excellent predictive ability for propensity to gain clinically significant improvements in function after hip arthroscopy. An open-access digital application was created, which may augment shared decision-making and allow for preoperative risk stratification. External validation of this model is warranted to confirm the performance of these algorithms, as the generalizability is currently unknown. LEVEL OF EVIDENCE: IV, Case series.

Orthopaedic Randomized Controlled Trials Published in General Medical Journals Are Associated With Higher Altmetric Attention Scores and Social Media Attention Than Nonorthopaedic Randomized Controlled Trials.

PURPOSE: To (1) compare the Altmetric Attention Score (AAS) and citation rates between orthopaedic and nonorthopaedic randomized controlled trials (RCTs) from 5 high-impact medical journals and (2) identify general characteristics of these articles associated with greater exposure on social media platforms. METHODS: Articles published in The New England Journal of Medicine (NEJM), Lancet, The Journal of the American Medical Association (JAMA), Annals of Internal Medicine, and Archives of Internal Medicine between January 2011 and December 2016 were analyzed. These journals were selected based on retaining high impact factors with rigorous publication standards and availability of the AAS for their publications. The queried time frame was chosen to balance the inception of the AAS with an optimal period for citation accrual. A total of 14 article characteristics, in addition to number of Tweets, Facebook shares, news mentions, and the AAS, were extracted. Inclusion criteria were orthopaedic RCTs reporting on outcomes after surgical intervention. Linear regression was used to assess the relationship between publication characteristics and the AAS and social media attention. RESULTS: A total of 9 orthopaedic and 59 nonorthopaedic RCTs were included. The mean AASs were significantly different (574 ± 565.7 versus 256.9 ± 222.3, P = .003), whereas citation rate was not (192.2 ± 117.1 versus 382.3 ± 560.3, P = .317). Orthopaedic RCTs had a significantly greater number of mentions on Twitter and Facebook (P < .001). A higher AAS significantly associated with a greater number of citations (ß = 0.75, P = .019) for orthopaedic RCTs. The mean AAS of orthopaedic RCTs favoring nonoperative management (809.6 ± 676.3) was greater than those favoring operative treatment (292.0 ± 248.9) but was not statistically significant (P = .361). CONCLUSION: Orthopaedic RCTs published in 5 high-impact general medical journals had a significantly greater mean AAS relative to nonorthopaedic RCTs, with no differences in citation rates. Additionally, there was a strong association between the AAS and citation rate of orthopaedic RCTs. Orthopaedic RCTs had greater social media exposure on both Twitter and Facebook. CLINICAL RELEVANCE: Orthopaedic surgeons, researchers, and providers who publish RCTs in high-impact medical journals can anticipate extensive social media attention for their articles relative to other nonorthopaedic RCTs in the same journals. Social media attention may be related to operative versus nonoperative management topics. This study provides further evidence for the increasing use of the AAS and its association with citation accrual.

Regenerative Potential of Mesenchymal Stem Cells for the Treatment of Knee Osteoarthritis and Chondral Defects: A Systematic Review and Meta-analysis.

PURPOSE: To perform a systematic review and meta-analysis evaluating the effects of mesenchymal stem cells (MSCs) on cartilage regeneration and patient-reported pain and function. METHODS: A systematic review was conducted according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines using a PRISMA checklist. The Cochrane Database of Systematic Reviews, the Cochrane Central Register of Controlled Trials, PubMed (2008-2019), EMBASE (2008-2019), and MEDLINE (2008-2019) were queried in July 2019 for literature reporting use of stem cells to treat knee osteoarthritis or chondral defects. Data describing administered treatment, subject population, injection type, duration of follow-up, pain and functional outcomes, and radiographic and magnetic resonance imaging findings were extracted. Risk of bias was assessed using the Downs and Black scale. Meta-analyses adjusted for random effects were performed, calculating pooled effect sizes in terms of patient-reported pain and function, cartilage quality, and cartilage volume. RESULTS: Twenty-five studies with 439 subjects were identified. There was no significant difference in pain improvement between MSC treatment and controls (pooled standardized mean difference [SMD] = 0.23, P = .30). However, MSC treatment was significantly favored for functional improvement (SMD = 0.66, P < .001). There was improvement in cartilage volume after MSC treatment (SMD = 0.84, P < .001). Regarding cartilage quality, meta-analysis resulted in a small, nonsignificant effect size of 0.37 (95%, -0.03 to 0.77, P = .07). There was risk for potential bias among included studies, with 17 (68%) receiving either a grade of "poor" or "fair." CONCLUSIONS: The pooled SMD from meta-analyses showed statistically significant effects of MSC on self-reported physical function but not self-reported pain. MSCs provided functional benefit only in patients who underwent concomitant surgery. However, this must be interpreted with caution, as there was substantial variability in MSC composition and mode of delivery. MSC treatment provided significant improvement in cartilage volume but not cartilage quality. Preliminary data regarding therapeutic properties of MSC treatment suggest significant heterogeneity in the current literature, and risk of bias is not negligible. LEVEL OF EVIDENCE: II, Systematic Review and Meta-analysis.

The Patient Acceptable Symptomatic State in Primary Anterior Cruciate Ligament Reconstruction: Predictors of Achievement.

PURPOSE: To identify thresholds for patient acceptable symptomatic state (PASS) achievement in a cohort of primary anterior cruciate ligament reconstruction (ACLR) recipients, and to identify factors predictive of PASS achievement. METHODS: A prospective clinical registry was queried for primary ACLR patients from January 2014 to April 2017 with serial patient-reported outcome measure (PROM) completion at 6, 12, and 24 months. Exclusion criteria included significant concomitant procedures. Knee-based PROMs included the International Knee Documentation Committee (IKDC) score and Knee Injury and Osteoarthritis Outcome Score (KOOS) subscores. PASS threshold values were calculated using receiver operating characteristic (ROC) curves with area under the curve (AUC) analysis. A stepwise multivariate regression identified preoperative and operative predictors of PASS achievement. RESULTS: A total of 144 primary ACLR patients (30.86 ± 12.78 years, body mass index 25.51 ± 4.64, 41.0% male) were included in the analysis. PASS threshold values were established using ROC curve analysis, all of which exceeded 0.7 on AUC analysis (0.742 to 0.911). Factors impacting odds of PASS achievement in the ACLR cohort included preoperative exercises (odds ratio [OR] 2.95 to 4.74, P = .003 to .038), worker's compensation status (OR 0.25 to 0.28, P = .014 to .033), preoperative scores (OR 1.03 to 1.07, P = .005 to <.001), iliotibial band tenodesis (OR 11.08, P = .010), and anteromedial approach (OR 18.03 to 37.05, P < .001). CONCLUSION: Factors predictive of PASS achievement in recipients of primary ACLR include functional status (e.g., preoperative exercise, preoperative KOOS Sport/Recreation score), worker's compensation status, technique (e.g., anteromedial) and preoperative PROMs. The results of our study are important in better informing shared decision-making models and improving evidence-based guidelines to optimize patient outcomes.

Establishing the Minimal Clinically Important Difference and Patient-Acceptable Symptomatic State After Arthroscopic Meniscal Repair and Associated Variables for Achievement.

PURPOSE: To establish the minimal clinically important difference (MCID) and patient-acceptable symptomatic state (PASS) after arthroscopic meniscal repair and identify the factors associated with achieving these outcomes. METHODS: This is a retrospective study with prospectively collected data. Patient-reported outcome measures (PROMs) were collected from April 2017 to March 2020. All patients who underwent arthroscopic meniscal repair and completed both preoperative and postoperative PROMs were included in the analysis. MCID and PASS were calculated via half the standard deviation of the delta PRO change from baseline (for International Knee Documentation Committee Score [IKDC]) and via anchor-based methodology (Knee Injury and Osteoarthritis Outcome Score [KOOS] subscales). RESULTS: Sixty patients were included in the final analysis. The established MCID threshold values were 10.9 for IKDC, 12.3 for KOOS Symptoms, 11.8 for KOOS Pain, 11.4 for KOOS Activities of Daily Living (ADL), 16.7 for KOOS Sport, and 16.9 for KOOS Quality of Life (QoL). Postoperative scores greater than the following values corresponded to the PASS: 69.0 for IKDC, 75.0 for KOOS Symptoms, 80.6 for KOOS Pain, 92.7 for KOOS ADL, 80.0 for KOOS Sport, and 56.3 for KOOS QoL. Higher preoperative PRO scores were associated with lower likelihood of achieving MCID. Concomitant ligament procedures were associated with a higher likelihood of achieving PASS. Tears to both menisci were associated with decreased likelihood of achieving MCID and PASS for IKDC. Horizontal tears were associated with decreased likelihood of achieving PASS for IKDC and KOOS. Complex tears were associated with decreased likelihood of achieving MCID for KOOS. CONCLUSION: Clinically meaningful outcomes such as MCID and PASS were established for meniscal repair surgery using selected PROMs for IKDC and KOOS subscales. Variables more likely to be associated with achieving these outcomes include lower preoperative PRO score and concomitant ligament procedure, whereas higher preoperative PRO score, tearing of both medial and lateral menisci, and horizontal and complex tear classifications were associated with decreased likelihood of achieving these outcomes. LEVEL OF EVIDENCE: IV, retrospective case series.

Development of supervised machine learning algorithms for prediction of satisfaction at 2 years following total shoulder arthroplasty.

BACKGROUND: Patient satisfaction after primary anatomic and reverse total shoulder arthroplasty (TSA) represents an important metric for gauging patients' perception of their care and surgical outcomes. Although TSA confers improvement in pain and function for most patients, inevitably some will remain unsatisfied postoperatively. The purpose of this study was to (1) train supervised machine learning (SML) algorithms to predict satisfaction after TSA and (2) develop a clinical tool for individualized assessment of patient-specific risk factors. METHODS: We performed a retrospective review of primary anatomic and reverse TSA patients between January 2014 and February 2018. A total of 16 demographic, clinical, and patient-reported outcomes were evaluated for predictive value. Five SML algorithms underwent 3 iterations of 10-fold cross-validation on a training set (80% of cohort). Assessment by discrimination, calibration, Brier score, and decision-curve analysis was performed on an independent testing set (remaining 20% of cohort). Global and local model behaviors were evaluated with global variable importance plots and local interpretable model-agnostic explanations, respectively. RESULTS: The study cohort consisted of 413 patients, of whom 331 (82.6%) were satisfied at 2 years postoperatively. The support vector machine model demonstrated the best relative performance on the independent testing set not used for model training (concordance statistic, 0.80; calibration intercept, 0.20; calibration slope, 2.32; Brier score, 0.11). The most important factors for predicting satisfaction were baseline Single Assessment Numeric Evaluation score, exercise and activity, workers' compensation status, diagnosis, symptom duration prior to surgery, body mass index, age, smoking status, anatomic vs. reverse TSA, and diabetes. The support vector machine algorithm was incorporated into an open-access digital application for patient-level explanations of risk and predictions, available at https://orthopedics.shinyapps.io/SatisfactionTSA/. CONCLUSION: The best-performing SML model demonstrated excellent discrimination and adequate calibration for predicting satisfaction following TSA and was used to create an open-access, clinical decision-making tool. However, rigorous external validation in different geographic locations and patient populations is essential prior to assessment of clinical utility. Given that this tool is based on partially modifiable risk factors, it may enhance shared decision making and allow for periods of targeted preoperative health-optimization efforts.

Return to sport following Latarjet glenoid reconstruction for anterior shoulder instability.

BACKGROUND: Latarjet coracoid transfer reconstruction is the gold standard for the treatment of recurrent shoulder instability with anterior-inferior glenoid bone loss, and return to sport is often a primary outcome of interest in this patient population. The purpose of this study was to determine the rate of return to sport in patients undergoing the Latarjet procedure and variables that are associated with a higher likelihood of a successful return to sport. METHODS: A prospectively maintained institutional registry was retrospectively queried between August 2012 and August 2016 for all patients who underwent the Latarjet procedure. Patients were contacted electronically and via telephone to administer a previously validated and standardized return-to-sport survey. Patients self-reported return to sport, varying sports participation, recurrence of instability, and time to return to sport. Multivariate analysis was performed to determine variables associated with each outcome. RESULTS: Of 83 patients, 66 (75.3%) were available for final follow-up, of whom 60 participated in sports prior to surgery and were eligible for inclusion. The average follow-up period was 53.8 ± 11.8 months. The average age at surgery was 26.7 ± 11.3 years, and the average body mass index was 26.2 ± 4.0 kg/m2. There were 54 patients (90%) who were able to return to sport at an average of 8.6 ± 4.1 months following surgery. In total, 36 patients (60%) were able to return to sport at the same level or a better level of intensity, 19 of 28 patients (67.9%) were able to return to throwing sports without difficulty, and 31 of 60 patients (51.7%) reported that their shoulder was a hindrance to some activity. An increased likelihood of returning to sport was associated with increased body mass index (P = .016), male sex (P = .028), and decreased humeral bone loss volume (P = .034). An increased likelihood of returning to sport at the same level or a better level of intensity was associated with reduced humeral bone loss volume (P = .026). Recurrent instability was associated with humeral bone loss (P = .038). CONCLUSION: Although a large majority of patients were able to return to sport following the Latarjet procedure, some patients experienced limitation with throwing and return to sport at the preinjury level. Greater humeral bone loss was associated with inferior outcomes. These findings should be discussed with patients in the preoperative setting to manage expectations appropriately.

Patients undergoing anatomic total shoulder arthroplasty achieve clinically significant outcomes faster than those undergoing reverse shoulder arthroplasty.

BACKGROUND: Clinically significant outcome (CSO) benchmarks have been previously established for outcome assessment after total shoulder arthroplasty. However, the time required to achieve CSO improvement is not well understood. The purpose of this study was to (1) determine the time-dependent achievement of the minimal clinically important difference (MCID), substantial clinical benefit (SCB), and patient acceptable symptom state (PASS) in patients undergoing either anatomic total shoulder (TSA) or reverse total shoulder arthroplasty (RTSA) and compare the results of the 2 populations and (2) identify variables associated with earlier or delayed achievement of each CSO. METHODS: A prospectively maintained institutional registry was retrospectively queried for all patients receiving a primary TSA or RTSA between September 2, 2016-October 31, 2017. The American Shoulder and Elbow Surgeons Standardized Shoulder Assessment Form (ASES) was administered to all patients preoperatively and at standardized postoperative time periods: 5-7 months (6-month time point), 11-13 months (1-year time point), and 23-25 months (2-year time point). Cumulative percentages of CSO achievement were calculated using Kaplan-Meier survival curve analysis with interval censoring. A Weibull parametric survival regression analysis was used to investigate the influence of demographic and clinical variables on delayed or earlier CSO achievement. RESULTS: A total of 153 patients (157 shoulders) undergoing TSA (n = 76) and RTSA (n = 81) were included in the study population. The RTSA cohort was older (70.2 ± 7.5 vs. 61.0 ± 8.4, P < .001), had a lower BMI (28.8 ± 5.9 vs. 31.5 ± 6.5, P = .006), and a greater proportion of females (53.1% vs. 32.9%, P = .017) relative to TSA. For SCB, there was a significant difference in the cumulative percentage of TSA and RTSA patients reaching this threshold at both the 6-month (77.3% vs. 59.0%, P = .024) and 2-year (92.0% vs. 79.5%, P = .048) time periods, with similar findings demonstrated for PASS. There was a significant difference in the average time required to achieve the PASS (TSA: 6.1 months vs. rTSA: 11.6 months, P = .009), but not the MCID (P = .407) or SCB (P = .153). Factors significantly associated with earlier achievement of more than 1 of the CSO benchmarks were regular preoperative physical exercise and diagnosis of rotator cuff tear without osteoarthritis. CONCLUSION: Patients undergoing RTSA had lower rates of achieving SCB and PASS at both 6 months and 2 years compared to patients undergoing TSA. Patients undergoing RTSA on average required nearly double the time to achieve PASS compared with those undergoing TSA. In both groups, clinically significant improvement continued for the entire 2-year duration of study follow-up.

Establishing clinically significant outcome thresholds for the Single Assessment Numeric Evaluation 2 years following total shoulder arthroplasty.

BACKGROUND: Single Assessment Numerical Evaluation (SANE) is a simple, time-efficient patient-reported outcome measure (PROM) used to assess postoperative shoulder function. Clinically significant outcome values and ability to correlate with longer legacy PROM scores at 2 years following shoulder arthroplasty are unknown. METHODS: A retrospective analysis was performed using SANE, American Shoulder and Elbow Surgeons Standardized Shoulder Assessment Form (ASES), and Constant scores that were collected at a minimum 2-year follow-up. A total of 153 patients who underwent anatomic total shoulder arthroplasty (TSA) or reverse total shoulder arthroplasty (RTSA) were included. A distribution-based method was used to determine the minimal clinically important difference (MCID). An anchor-based method was used to determine substantial clinical benefit (SCB). The following anchor question was collected alongside the PROMs and graded on a 15-point Likert-type scale to establish the SCB: "Since your surgery, has there been any change in the pain in your shoulder?" Linear regression was used to assess correlations between PROMs. RESULTS: SANE showed moderate correlation with ASES (R2 = 0.493) and Constant (R2 = 0.586) scores (P < .001). The MCID value was 14.9, and the SCB absolute value was 80.4 (area under the curve = 0.663) for SANE. Multivariate logistic regression demonstrated that patients undergoing RTSA were less likely to achieve SCB on all 3 outcome measures (P < .02). CONCLUSIONS: This study establishes concurrent construct validity for SANE and suggests that it is a valid metric to assess the MCID and SCB at 2 years following anatomic TSA and RTSA. SANE demonstrated moderate correlations with ASES and Constant scores. Patients undergoing RTSA demonstrated a lower propensity to achieve SCB at 2 years postoperatively compared with anatomic TSA.

Validation and performance of a machine-learning derived prediction guide for total knee arthroplasty component sizing.

INTRODUCTION: Anticipation of patient-specific component sizes prior to total knee arthroplasty (TKA) is essential to avoid excessive cost associated with additional surgical trays and morbidity associated with imperfect sizing. Current methods of size prediction, including templating, are inconsistent and time-consuming. Machine learning (ML) algorithms may allow for accurate TKA component size prediction with the ability to make predictions in real-time. METHODS: Consecutive patients receiving primary TKA between 2012 and 2020 from two large tertiary academic and six community hospitals were identified. The primary outcomes were the final femoral and tibial component sizes extracted from automated inventory systems. Five ML algorithms were trained with routinely corrected demographic variables (age, height, weight, body mass index, and sex) using 80% of the study population and internally validated on an independent set of the remaining 20% of patients. Algorithm performance was evaluated through accuracy, mean absolute error (MAE), and root mean-squared error (RMSE). RESULTS: A total of 17,283 patients that received one of 9 TKA implants from independent manufacturers were included. The SGB model accuracy for predicting ± 4-mm of the true femoral anteroposterior diameter was 83.6% and for ± 1 size of the true femoral component size was 95.0%. The SGB model accuracy for predicting ± 4-mm of the true tibial medial/lateral diameter was 83.0% and for ± 1 size of the true tibial component size was 97.8%. Patient sex was the most influential feature in terms of informing the SGB model predictions for both femoral and tibial component sizing. A TKA implant sizing application was subsequently created. CONCLUSION: Novel machine learning algorithms demonstrated good to excellent performance for predicting TKA component size. Patient sex appears to contribute an important role in predicting TKA size. A web-based real-time prediction application was created capable of integrating patient specific data to predict TKA size, which will require external validation prior to clinical use.

No Differences in Hip Joint Space Measurements Between Weightbearing or Supine Anteroposterior Pelvic Radiographs.

PURPOSE: To to assess whether there are any significant differences in hip joint space width (JSW) between weight-bearing versus supine pelvic radiographs. METHODS: Standing and supine anteroposterior pelvic radiographs of 86 patients (146 hips) were included. Sample size was sufficiently powered to assess for equivalence between standing and supine films for JSW measurements made at the medial, lateral, and central aspects of the sourcil line. Measurements were made by 2 independent reviewers blinded to patient positioning. Each reviewer repeated a subset of the measurements to assess intra-rater reproducibility. Mean differences in joint space measurements between standing and supine radiographs were reported for each point of the sourcil. Intraclass correlation coefficients (ICCs) for inter and intra-rater reliability were also calculated. RESULTS: There were no significant differences between JSW measurements made on standing and supine pelvic radiographs (P = .468). Furthermore, equivalence testing demonstrated statistical equivalence between standing and supine JSW measurements made based on an equivalence threshold of ±0.5 mm. Inter-rater reliability demonstrated good agreement with an overall ICC of 0.775 (95% confidence interval [CI] 0.734-0.809). Intra-rater reliability also demonstrated good agreement with ICCs of 0.84 (95% CI 0.758-0.889) and 0.798 (95% CI 0.721-0.851) for the 2 reviewers, respectively. CONCLUSIONS: JSW measurements on standing and supine pelvic radiographs were not significantly different, and their inter-rater agreement and intra-rater reproducibility demonstrated good reliability and repeatability. Therefore, either may be used to assess JSW, including measurements that may impact treatment decisions for hip arthroscopy. LEVEL OF EVIDENCE: Level III; retrospective comparative study.