The Number of Patients Lost to Follow-Up May Exceed the Fragility Index of a Randomized Controlled Trial Without Reversing Statistical Significance: A Systematic Review and Statistical Model.

PURPOSE: To (1) analyze trends in the publishing of statistical fragility index (FI)-based systematic reviews in the orthopaedic literature, including the prevalence of misleading or inaccurate statements related to the statistical fragility of randomized controlled trials (RCTs) and patients lost to follow-up (LTF), and (2) determine whether RCTs with relatively "low" FIs are truly as sensitive to patients LTF as previously portrayed in the literature. METHODS: All FI-based studies published in the orthopaedic literature were identified using the Cochrane Database of Systematic Reviews, Web of Science Core Collection, PubMed, and MEDLINE databases. All articles involving application of the FI or reverse FI to study the statistical fragility of studies in orthopaedics were eligible for inclusion in the study. Study characteristics, median FIs and sample sizes, and misleading or inaccurate statements related to the FI and patients LTF were recorded. Misleading or inaccurate statements-defined as those basing conclusions of trial fragility on the false assumption that adding patients LTF back to a trial has the same statistical effect as existing patients in a trial experiencing the opposite outcome-were determined by 2 authors. A theoretical RCT with a sample size of 100, P = .006, and FI of 4 was used to evaluate the difference in effect on statistical significance between flipping outcome events of patients already included in the trial (FI) and adding patients LTF back to the trial to show the true sensitivity of RCTs to patients LTF. RESULTS: Of the 39 FI-based studies, 37 (95%) directly compared the FI with the number of patients LTF. Of these 37 studies, 22 (59%) included a statement regarding the FI and patients LTF that was determined to be inaccurate or misleading. In the theoretical RCT, a reversal of significance was not observed until 7 patients LTF (nearly twice the FI) were added to the trial in the distribution of maximal significance reversal. CONCLUSIONS: The claim that any RCT in which the number of patients LTF exceeds the FI could potentially have its significance reversed simply by maintaining study follow-ups is commonly inaccurate and prevalent in orthopaedic studies applying the FI. Patients LTF and the FI are not equivalent. The minimum number of patients LTF required to flip the significance of a typical RCT was shown to be greater than the FI, suggesting that RCTs with relatively low FIs may not be as sensitive to patients LTF as previously portrayed in the literature; however, only a holistic approach that considers the context in which the trial was conducted, potential biases, and study results can determine the merits of any particular RCT. CLINICAL RELEVANCE: Surgeons may benefit from re-examining their interpretation of prior FI reviews that have made claims of substantial RCT fragility based on comparisons between the FI and patients LTF; it is possible the results are more robust than previously believed.

Root Repair Has Superior Radiological and Clinical Outcomes Than Partial Meniscectomy and Nonoperative Treatment in the Management of Meniscus Root Tears: A Systematic Review.

PURPOSE: To compile and analyze structural and clinical outcomes after meniscus root tear treatment as currently described in the literature. METHODS: A review was conducted to identify studies published since 2011 on efficacy of repair, meniscectomy, and nonoperative management in the treatment of meniscus root tears. Patient cohorts were grouped into treatment categories, with medial and lateral root tears analyzed separately; data were collected on patient demographics, structural outcomes including joint space width, degree of medial meniscal extrusion, progression to total knee arthroplasty, and patient-reported outcome measures. Risk of bias was assessed using the MINORS (methodological index for non-randomized studies) criteria. Heterogeneity was measured using the I-statistic, and outcomes were summarized using forest plots without pooled means. RESULTS: The 56 included studies comprised a total of 3,191 patients. Mean age among the included studies ranged from 24.6 to 65.6 years, whereas mean follow-up ranged from 12 to 125.9 months. Heterogeneity analysis identified significant differences between studies. Change in joint space width ranged from -2.4 to -0.6 mm (i.e., decreased space) after meniscectomy (n = 186) and -0.9 to -0.1 mm after root repair (n = 209); change in medial meniscal extrusion ranged from -0.6 to 6.5 mm after root repair (n = 521) and 0.2 to 4.2 mm after meniscectomy (n = 66); and event rate for total knee arthroplasty ranged from 0.00 to 0.22 after root repair (n = 205), 0.35 to 0.60 after meniscectomy (n = 53), and 0.27 to 0.35 after nonoperative treatment (n = 93). Root repair produced the greatest numerical increase in International Knee Documentation Committee and Lysholm scores of the 3 treatment arms. In addition, root repair improvements in Knee Injury and Osteoarthritis Outcome Score Pain (range: 22-32), Sports and Recreational Activities (range: 23-36), Quality of Life (range: 22-42), and Symptoms subscales (range: 10-19), in studies with low risk of bias. CONCLUSIONS: The literature reporting on the treatment of meniscus root tears is heterogenous and largely limited to Level III and IV studies. Current evidence suggests root repair may be the most effective treatment strategy in lessening joint space narrowing of the knee and producing improvements in patient-reported outcomes. LEVEL OF EVIDENCE: Level IV, systematic review of Level II-IV studies.

A Machine Learning Model Demonstrates Excellent Performance in Predicting Subscapularis Tears Based on Pre-Operative Imaging Parameters Alone.

PURPOSE: To develop a machine learning model capable of identifying subscapularis tears before surgery based on imaging and physical examination findings. METHODS: Between 2010 and 2020, 202 consecutive shoulders underwent arthroscopic rotator cuff repair by a single surgeon. Patient demographics, physical examination findings (including range of motion, weakness with internal rotation, lift/push-off test, belly press test, and bear hug test), and imaging (including direct and indirect signs of tearing, biceps status, fatty atrophy, cystic changes, and other similar findings) were included for model creation. RESULTS: Sixty percent of the shoulders had partial or full thickness tears of the subscapularis verified during surgery (83% of these were upper third). Using only preoperative imaging-related parameters, the XGBoost model demonstrated excellent performance at predicting subscapularis tears (c-statistic, 0.84; accuracy, 0.85; F1 score, 0.87). The top 5 features included direct signs related to the presence of tearing as evidenced on magnetic resonance imaging (MRI) (changes in tendon morphology and signal), as well as the quality of the MRI and biceps pathology. CONCLUSIONS: In this study, machine learning was successful in predicting subscapularis tears by MRI alone in 85% of patients, and this accuracy did not decrease by isolating the model to the top features. The top five features included direct signs related to the presence of tearing as evidenced on MRI (changes in tendon morphology and signal), as well as the quality of the MRI and biceps pathology. Last, in advanced modeling, the addition of physical examination or patient characteristics did not make a significant difference in the predictive ability of this model. LEVEL OF EVIDENCE: Level III, diagnostic case-control study.

Elbow Ulnar Collateral Ligament Tears in 2023: Evaluation and Management.

The ulnar collateral ligament, also called the medial collateral ligament of the elbow, is the primary stabilizer against valgus loads. This ligament can be traumatically torn, such as in an elbow dislocation, or can tear through attritional damage with overhead sports. Although baseball pitching is the most common contributor, these injuries also occur with volleyball, gymnastics, and javelin throwing. Patients most commonly report a history of medial elbow pain with associated loss of command, control, and throw velocity. The ulnar nerve lies directly superficial to the posterior band of the ulnar collateral ligament and ulnar neuritis is commonly associated with ulnar collateral ligament pathology. Nonsurgical treatment, including rest from activity, flexor-pronator strengthening, and possible platelet-rich plasma injections, can be considered for partial-thickness tears. Surgical treatment can be considered for patients in whom nonsurgical treatment fails and full-thickness tears. Historically, surgical treatment involved reconstruction of the ligament with a tendon graft. Ipsilateral palmaris longus autograft has been the most commonly used graft, but contralateral palmaris, autograft hamstring tendons, and allograft tendon have also been used. This procedure has a high rate of return to play and a low complication rate, but most athletes require 12 to 18 months to fully return. More recently, repair of the ligament, with the addition of a biologic ingrowth ligament augmentation suture, has demonstrated similarly high rates of return to play and low complication rates, with a full return to play in 6 months.

High incidence of medial meniscus root/radial tears and extrusion in 253 patients with subchondral insufficiency fractures of the knee.

PURPOSE: The demographic and radiological risk factors of subchondral insufficiency fractures of the knee (SIFK) continue to be a subject of debate. The purpose of this study was to associate patient-specific factors with SIFK in a large cohort of patients. METHODS: Inclusion criteria consisted of patients with SIFK as verified on magnetic resonance imaging (MRI). All radiographs and MRIs were reviewed to assess characteristics such as meniscus tear presence and type, subchondral oedema presence and location, location of SIFK, mechanical limb alignment, osteoarthritis as assessed by Kellgren-Lawrence grade and ligamentous injury. A total of 253 patients (253 knees) were included, with 171 being female. The average body mass index (BMI) was 32.1 ± 7.0 kg/m2. RESULTS: SIFK was more common in patients with medial meniscus tears (77.1%, 195/253) rather than tears of the lateral meniscus (14.6%, 37/253) (p < 0.001). Medial meniscus root and radial tears of the posterior horn were present in 71.1% (180/253) of patients. Ninety-one percent (164/180) of medial meniscus posterior root and radial tears had an extrusion ≥3.0 mm. Eighty-one percent (119/147) of patients with SIFK on the medial femoral condyle and 86.8% (105/121) of patients with SIFK on the medial tibial plateau had a medial meniscus tear. Varus knees had a significantly increased rate of SIFK on the medial femoral condyle in comparison to valgus knees (p = 0.016). CONCLUSION: In this large cohort of patients with SIFK, there was a high association with medial meniscus root and radial tears of the posterior horn, meniscus extrusion ≥3.0 mm as well as higher age, female gender and higher BMI. Additionally, there was a particularly strong association of medial compartment SIFK with medial meniscus tears. As SIFK is frequently undiagnosed, identifying patient-specific demographic and radiological risk factors will help achieve a prompt diagnosis. LEVEL OF EVIDENCE: Level IV.

A practical guide to the development and deployment of deep learning models for the orthopaedic surgeon: Part III, focus on registry creation, diagnosis, and data privacy.

Deep learning is a subset of artificial intelligence (AI) with enormous potential to transform orthopaedic surgery. As has already become evident with the deployment of Large Language Models (LLMs) like ChatGPT (OpenAI Inc.), deep learning can rapidly enter clinical and surgical practices. As such, it is imperative that orthopaedic surgeons acquire a deeper understanding of the technical terminology, capabilities and limitations associated with deep learning models. The focus of this series thus far has been providing surgeons with an overview of the steps needed to implement a deep learning-based pipeline, emphasizing some of the important technical details for surgeons to understand as they encounter, evaluate or lead deep learning projects. However, this series would be remiss without providing practical examples of how deep learning models have begun to be deployed and highlighting the areas where the authors feel deep learning may have the most profound potential. While computer vision applications of deep learning were the focus of Parts I and II, due to the enormous impact that natural language processing (NLP) has had in recent months, NLP-based deep learning models are also discussed in this final part of the series. In this review, three applications that the authors believe can be impacted the most by deep learning but with which many surgeons may not be familiar are discussed: (1) registry construction, (2) diagnostic AI and (3) data privacy. Deep learning-based registry construction will be essential for the development of more impactful clinical applications, with diagnostic AI being one of those applications likely to augment clinical decision-making in the near future. As the applications of deep learning continue to grow, the protection of patient information will become increasingly essential; as such, applications of deep learning to enhance data privacy are likely to become more important than ever before. Level of Evidence: Level IV.

Platelet-Rich Plasma and Marrow Venting May Serve as Cost-Effective Augmentation Techniques for Isolated Meniscal Repair: A Decision-Analytical Markov Model-Based Analysis.

PURPOSE: To evaluate the cost-effectiveness of 3 isolated meniscal repair (IMR) treatment strategies: platelet-rich plasma (PRP)-augmented IMR, IMR with a marrow venting procedure (MVP), and IMR without biological augmentation. METHODS: A Markov model was developed to evaluate the baseline case: a young adult patient meeting the indications for IMR. Health utility values, failure rates, and transition probabilities were derived from the published literature. Costs were determined based on the typical patient undergoing IMR at an outpatient surgery center. Outcome measures included costs, quality-adjusted life-years (QALYs), and the incremental cost-effectiveness ratio (ICER). RESULTS: Total costs of IMR with an MVP were $8,250; PRP-augmented IMR, $12,031; and IMR without PRP or an MVP, $13,326. PRP-augmented IMR resulted in an additional 2.16 QALYs, whereas IMR with an MVP produced slightly fewer QALYs, at 2.13. Non-augmented repair produced a modeled gain of 2.02 QALYs. The ICER comparing PRP-augmented IMR versus MVP-augmented IMR was $161,742/QALY, which fell well above the $50,000 willingness-to-pay threshold. CONCLUSIONS: IMR with biological augmentation (MVP or PRP) resulted in a higher number of QALYs and lower costs than non-augmented IMR, suggesting that biological augmentation is cost-effective. Total costs of IMR with an MVP were significantly lower than those of PRP-augmented IMR, whereas the number of additional QALYs produced by PRP-augmented IMR was only slightly higher than that produced by IMR with an MVP. As a result, neither treatment dominated over the other. However, because the ICER of PRP-augmented IMR fell well above the $50,000 willingness-to-pay threshold, IMR with an MVP was determined to be the overall cost-effective treatment strategy in the setting of young adult patients with isolated meniscal tears. LEVEL OF EVIDENCE: Level III, economic and decision analysis.

A Number of Modifiable and Nonmodifiable Factors Increase the Risk for Elbow Medial Ulnar Collateral Ligament Injury in Baseball Players: A Systematic Review.

PURPOSE: To analyze the current literature regarding risk factors associated with medial ulnar collateral ligament (MUCL) injury in baseball players and to serve as a robust source for identifying modifiable risk factors that once optimized, have the potential to reduce injury risk. METHODS: Comprehensive search of the available literature was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Studies were included if they evaluated risk factors for MUCL injuries in the elbow of baseball players. Risk of bias assessment was performed via Methodological Index for Non-randomized Studies (MINORS) scoring system. The Oxford Centre for Evidence-Based Medicine was used to determine level of evidence. Variables of interest; player age, position, shoulder motion, humeral retrotorsion, joint laxity, strength, balance, geography, velocity, pitch count, pitch types, throwing volumes, and throwing mechanics were recorded. RESULTS: Twenty-one studies were included in this systematic review. MINORS scores ranged from 75 to 87%, and variables demonstrated significant heterogeneity. Performance-based risk factors for MUCL injury included: increased pitch count (both annual and per game), higher percentage of fastballs thrown, smaller pitch repertoire, and/or a loss of pitching velocity. Biomechanical studies demonstrated the relationship between decreased shoulder range of motion (total ROM, ER, IR, and abduction), increased humeral retrotorsion, increased elbow valgus opening in the throwing arm, lower Y-Balance score, and increased lateral release position to increased MUCL injury. CONCLUSIONS: Risk factors for MUCL injury can generally be categorized into 4 primary groups: 1) various player demographics and characteristics, 2) throwing too hard (high velocity), 3) throwing too much (pitch count/volume), and 4) throwing with poor mechanics. In this systematic review, the most significant nonmodifiable risk factors for MUCL injuries included: increased glenohumeral retrotorsion and elbow valgus opening. The most consistent modifiable risk factors included: total shoulder range of motion, pitch count, pitch selection, Y balance score, and lateral release position. Pitch velocity was inconsistent in literature, but most studies found this as a risk for injury. These risk factors may serve as appropriate targets for future evidence-based injury mitigation strategies. LEVEL OF EVIDENCE: Level IV, systematic review of Level II-IV studies.

Improved Yet Varied Clinical Outcomes Observed With Comparison of Arthroscopic Superior Capsular Reconstruction Versus Arthroscopy-Assisted Lower Trapezius Transfer for Patients With Irreparable Rotator Cuff Tears.

PURPOSE: To evaluate the outcomes of arthroscopic superior capsular reconstruction (SCR) and arthroscopy-assisted lower trapezius tendon transfer (LTT) for posterosuperior irreparable rotator cuff tears (IRCTs). METHODS: Over an almost 6-year period (October 2015 to March 2021), all patients who underwent IRCT surgery with a minimum 12-month follow-up period were identified. For patients with a substantial active external rotation (ER) deficit or lag sign, LTT was preferentially selected. Patient-reported outcome scores included the visual analog scale (VAS) pain score, strength score, American Shoulder and Elbow Surgeons Standardized Shoulder Assessment Form (ASES) score, Single Assessment Numeric Evaluation (SANE) score, and Quick Disabilities of the Arm, Shoulder and Hand (QuickDASH) score. RESULTS: We included 32 SCR patients and 72 LTT patients. Preoperatively, LTT patients had more advanced teres minor fatty infiltration (0.3 vs 1.1, P = .009), a higher global fatty infiltration index (1.5 vs 1.9, P = .035), and a higher presence of the ER lag sign (15.6% vs 48.6%, P < .001). At a mean follow-up of 2.9 ± 1.3 years (range, 1.0-6.3 years), no differences in patient-reported outcome scores were observed. Postoperatively, SCR patients had a lower VAS score (0.3 vs 1.1, P = .017), higher forward elevation (FE) (156° vs 143°, P = .004), and higher FE strength (4.8 vs 4.5, P = .005) and showed greater improvements in the VAS score (6.8 vs 5.1, P = .009), FE (56° vs 31°, P = .004), and FE strength (1.0 vs 0.4, P < .001). LTT patients showed greater improvement in ER (17° vs 29°, P = .026). There was no statistically significant between-cohort difference in complication rate (9.4% vs 12.5%, P = .645) or reoperation rate (3.1% vs 10%, P = .231). CONCLUSIONS: With adequate selection criteria, both SCR and LTT provided improved clinical outcomes for posterosuperior IRCTs. Additionally, SCR led to better pain relief and restoration of FE whereas LTT provided more reliable improvement in ER. LEVEL OF EVIDENCE: Level III, treatment study with retrospective cohort comparison.

Autologous Osteochondral Transfer of the Knee Demonstrates Continued High Rates of Return to Sport and Low Rates of Conversion to Arthroplasty at Long-Term Follow-Up: A Systematic Review.

PURPOSE: To perform a systematic review of the literature to evaluate (1) activity level and knee function, (2) reoperation and failure rates, and (3) risk factors for reoperation and failure of autologous osteochondral transfer (AOT) at long-term follow-up. METHODS: A comprehensive review of the long-term outcomes of AOT was performed. Studies reported on activity-based outcomes (Tegner Activity Scale) and clinical outcomes (Lysholm score and International Knee Documentation Committee score). Reoperation and failure rates as defined by the publishing authors were recorded for each study. Modified Coleman Methodology Scores were calculated to assess study methodological quality. RESULTS: Twelve studies with a total of 495 patients and an average age of 32.5 years at the time of surgery and a mean follow-up of 15.1 years (range, 10.4-18.0 years) were included. The mean defect size was 3.2 cm2 (range, 1.9-6.9 cm2). The mean duration of symptoms before surgery was 5.1 years. Return to sport rates ranged from 86% to 100%. Conversion to arthroplasty rates ranged from 0% to 16%. The average preoperative International Knee Documentation Committee scores ranged from 32.9 to 36.8, and the average postoperative International Knee Documentation Committee scores at final follow-up ranged from 66.3 to 77.3. The average preoperative Lysholm scores ranged from 44.5 to 56.0 and the average postoperative Lysholm scores ranged from 70.0 to 96.5. The average preoperative Tegner scores ranged from 2.5 to 3.0, and the average postoperative scores ranged from 4.1 to 7.0. CONCLUSIONS: AOT of the knee resulted in high rates of return to sport with correspondingly low rates of conversion to arthroplasty at long-term follow-up. In addition, AOT demonstrated significant improvements in long-term patient-reported outcomes from baseline. LEVEL OF EVIDENCE: Level IV, systematic review of Level I-IV studies.

Machine learning can accurately predict risk factors for all-cause reoperation after ACLR: creating a clinical tool to improve patient counseling and outcomes.

PURPOSE: Identifying predictive factors for all-cause reoperation after anterior cruciate ligament reconstruction could inform clinical decision making and improve risk mitigation. The primary purposes of this study are to (1) determine the incidence of all-cause reoperation after anterior cruciate ligament reconstruction, (2) identify predictors of reoperation after anterior cruciate ligament reconstruction using machine learning methodology, and (3) compare the predictive capacity of the machine learning methods to that of traditional logistic regression. METHODS: A longitudinal geographical database was utilized to identify patients with a diagnosis of new anterior cruciate ligament injury. Eight machine learning models were appraised on their ability to predict all-cause reoperation after anterior cruciate ligament reconstruction. Model performance was evaluated via area under the receiver operating characteristics curve. To explore modeling interpretability and radiomic feature influence on the predictions, we utilized a game-theory-based method through SHapley Additive exPlanations. RESULTS: A total of 1400 patients underwent anterior cruciate ligament reconstruction with a mean postoperative follow-up of 9 years. Two-hundred and eighteen (16%) patients experienced a reoperation after anterior cruciate ligament reconstruction, of which 6% of these were revision ACL reconstruction. SHapley Additive exPlanations plots identified the following risk factors as predictive for all-cause reoperation: diagnosis of systemic inflammatory disease, distal tear location, concomitant medial collateral ligament repair, higher visual analog scale pain score prior to surgery, hamstring autograft, tibial fixation via radial expansion device, younger age at initial injury, and concomitant meniscal repair. Pertinent negatives, when compared to previous studies, included sex and timing of surgery. XGBoost was the best-performing model (area under the receiver operating characteristics curve of 0.77) and outperformed logistic regression in this regard. CONCLUSIONS: All-cause reoperation after anterior cruciate ligament reconstruction occurred at a rate of 16%. Machine learning models outperformed traditional statistics and identified diagnosis of systemic inflammatory disease, distal tear location, concomitant medial collateral ligament repair, higher visual analog scale pain score prior to surgery, hamstring autograft, tibial fixation via radial expansion device, younger age at initial injury, and concomitant meniscal repair as predictive risk factors for reoperation. Pertinent negatives, when compared to previous studies, included sex and timing of surgery. These models will allow surgeons to tabulate individualized risk for future reoperation for patients undergoing anterior cruciate ligament reconstruction. LEVEL OF EVIDENCE: III.

Risk factors for secondary meniscus tears can be accurately predicted through machine learning, creating a resource for patient education and intervention.

PURPOSE: This study sought to develop and internally validate a machine learning model to identify risk factors and quantify overall risk of secondary meniscus injury in a longitudinal cohort after primary ACL reconstruction (ACLR). METHODS: Patients with new ACL injury between 1990 and 2016 with minimum 2-year follow-up were identified. Records were extensively reviewed to extract demographic, treatment, and diagnosis of new meniscus injury following ACLR. Four candidate machine learning algorithms were evaluated to predict secondary meniscus tears. Performance was assessed through discrimination using area under the receiver operating characteristics curve (AUROC), calibration, and decision curve analysis; interpretability was enhanced utilizing global variable importance plots and partial dependence curves. RESULTS: A total of 1187 patients underwent ACLR; 139 (11.7%) experienced a secondary meniscus tear at a mean time of 65 months post-op. The best performing model for predicting secondary meniscus tear was the random forest (AUROC = 0.790, 95% CI: 0.785-0.795; calibration intercept = 0.006, 95% CI: 0.005-0.007, calibration slope = 0.961 95% CI: 0.956-0.965, Brier's score = 0.10 95% CI: 0.09-0.12), and all four machine learning algorithms outperformed traditional logistic regression. The following risk factors were identified: shorter time to return to sport (RTS), lower VAS at injury, increased time from injury to surgery, older age at injury, and proximal ACL tear. CONCLUSION: Machine learning models outperformed traditional prediction models and identified multiple risk factors for secondary meniscus tears after ACLR. Following careful external validation, these models can be deployed to provide real-time quantifiable risk for counseling and timely intervention to help guide patient expectations and possibly improve clinical outcomes. LEVEL OF EVIDENCE: III.

A practical guide to the development and deployment of deep learning models for the orthopedic surgeon: part II.

Deep learning has the potential to be one of the most transformative technologies to impact orthopedic surgery. Substantial innovation in this area has occurred over the past 5 years, but clinically meaningful advancements remain limited by a disconnect between clinical and technical experts. That is, it is likely that few orthopedic surgeons possess both the clinical knowledge necessary to identify orthopedic problems, and the technical knowledge needed to implement deep learning-based solutions. To maximize the utilization of rapidly advancing technologies derived from deep learning models, orthopedic surgeons should understand the steps needed to design, organize, implement, and evaluate a deep learning project and its workflow. Equipping surgeons with this knowledge is the objective of this three-part editorial review. Part I described the processes involved in defining the problem, team building, data acquisition, curation, labeling, and establishing the ground truth. Building on that, this review (Part II) provides guidance on pre-processing and augmenting the data, making use of open-source libraries/toolkits, and selecting the required hardware to implement the pipeline. Special considerations regarding model training and evaluation unique to deep learning models relative to "shallow" machine learning models are also reviewed. Finally, guidance pertaining to the clinical deployment of deep learning models in the real world is provided. As in Part I, the focus is on applications of deep learning for computer vision and imaging.

A practical guide to the development and deployment of deep learning models for the Orthopedic surgeon: part I.

Deep learning has a profound impact on daily life. As Orthopedics makes use of this rapid escalation in technology, Orthopedic surgeons will need to take leadership roles on deep learning projects. Moreover, surgeons must possess an understanding of what is necessary to design and implement deep learning-based project pipelines. This review provides a practical guide for the Orthopedic surgeon to understand the steps needed to design, develop, and deploy a deep learning pipeline for clinical applications. A detailed description of the processes involved in defining the problem, building the team, acquiring and curating the data, labeling the data, establishing the ground truth, pre-processing and augmenting the data, and selecting the required hardware is provided. In addition, an overview of unique considerations involved in the training and evaluation of deep learning models is provided. This review strives to provide surgeons with the groundwork needed to identify gaps in the clinical landscape that deep learning models may be able to fill and equips them with the knowledge needed to lead an interdisciplinary team through the process of creating novel deep-learning-based solutions to fill those gaps.

Incidence and 30- and 90-day readmission rates after primary shoulder arthroplasty in the United States: an analysis using the National Readmissions Database.

BACKGROUND: The field of shoulder arthroplasty has experienced a substantial increase in the number of procedures performed annually and a shift toward more common implantation of reverse shoulder arthroplasties (RSAs). Same-day discharge is perceived as beneficial for most patients as well as our health care system, and the number of shoulder procedures performed as same-day surgery has increased substantially. However, the potential benefits of same-day discharge after shoulder arthroplasty may be negatively influenced by unexpected readmissions. As such, an in-depth analysis of readmission rates after primary shoulder arthroplasty is particularly timely. METHODS: The National Readmissions Database was queried for primary shoulder arthroplasty procedures performed in the United States between 2016 and 2018. National incidences were calculated, and indications, patient demographic characteristics, comorbidities, facility characteristics, and rates and causes of 30- and 90-day readmissions were determined for all procedures and compared between anatomic total shoulder arthroplasty (TSA), anatomic hemiarthroplasty (HA), and RSA. RESULTS: During the study period, 336,672 primary shoulder arthroplasties were performed (37% TSAs, 57% RSAs, and 6% HAs). In 2018, national incidences per 100,000 inhabitants were 22.64 for RSA, 12.70 for TSA, and 1.50 for HA. The utilization of these procedures between 2016 and 2018 increased for RSA, decreased for HA, and remained constant for TSA, but these changes did not reach the level of statistical significance. The average all-cause 30-day readmission rates were 3.63%, 1.92%, and 3.81% for RSA, TSA, and HA, respectively, and the average all-cause 90-day readmission rates were 7.76%, 4.37%, and 9.18%, respectively. For both RSA and HA, the most common surgical diagnosis for 30-day and 90-day readmissions was dislocation (0.45% and 0.99%, respectively, for RSA and 0.21% and 0.67%, respectively, for HA). For TSA, the most common surgical diagnosis for 30-day readmission was infection (0.11%); however, this was surpassed by dislocation (0.28%) at 90 days. CONCLUSION: RSA surpassed TSA as the most frequently performed shoulder arthroplasty procedure in the United States between 2016 and 2018. During this period, the 90-day readmission rate was not negligible, with dislocation and infection as the leading orthopedic causes of readmission.

What are the indications for medial ulnar collateral ligament surgery in baseball players? An MRI case-based study.

BACKGROUND: Ulnar collateral ligament (UCL) tears are common in baseball players. When nonoperative management fails; reconstruction or repair may be necessary to restore physical function. There is no clear consensus regarding the indications for surgery based on magnetic resonance imaging (MRI) tear characteristics or the indications for selecting repair over reconstruction. The purpose of this study was to define the indications for UCL surgery based on MRI and to elucidate indications for UCL repair vs. reconstruction. METHODS: Twenty-six orthopedic surgeons who treat baseball players were surveyed. Forty-five MRIs were reviewed: 15 without UCL tears, 15 with intraoperatively confirmed partial-thickness tears, and 15 with full-thickness tears. Factors investigated included ligament characteristics (periligamentous or osseous edema, ligament hypertrophy, calcification, partial or full-thickness tearing) and location (proximal, midsubstance, or distal). Surgeons were given a clinical scenario and asked whether 1) surgery was indicated and 2) whether repair or reconstruction was recommended. Odds ratios (OR) and 95% confidence intervals (95% CI) helped identify significant predictors for both queries. RESULTS: The odds of recommending surgical treatment compared to nonoperative treatment were 2.4× more likely for a proximal partial-thickness tear, 3.2× for distal partial-thickness tear, 5.1× for distal full-thickness tear, and 7.0× for proximal full-thickness tear (P < .001). Significant indications for repair included distal partial (OR = 1.6, 95% CI 1.0, 2.1, P < .001) and full-thickness tears (OR = 1.7, 95% CI 1.1, 2.3, P < .001). Repair was 3× less likely recommended for midsubstance full-thickness tears (OR = 3.0, 95% CI -5.0, -1.0, P = .004). Ultrasound stress testing was requested in 78% of partial tears. CONCLUSIONS: Among surgeons surveyed, the highest odds for recommending operative treatment were proximal full-thickness tears, then distal full-thickness, distal partial-thickness, and proximal partial-thickness tears. Repair was most appropriate for partial and full-thickness distal tears, but relatively contraindicated for complete midsubstance UCL tears. Ultrasound stress testing was frequently requested for partial tears. Given the lack of consensus among surgeons, future prospective registries are necessary to determine whether these factors associate with clinical outcomes.

Understanding risk for early dislocation resulting in reoperation within 90 days of reverse total shoulder arthroplasty: extreme rare event detection through cost-sensitive machine learning.

BACKGROUND: Reliable prediction of postoperative dislocation after reverse total shoulder arthroplasty (RSA) would inform patient counseling as well as surgical and postoperative decision making. Understanding interactions between multiple risk factors is important to identify those patients most at risk of this rare but costly complication. To better understand these interactions, a game theory-based approach was undertaken to develop machine learning models capable of predicting dislocation-related 90-day readmission following RSA. MATERIAL & METHODS: A retrospective review of the Nationwide Readmissions Database was performed to identify patients who underwent RSA between 2016 and 2018 with a subsequent readmission for prosthetic dislocation. Of the 74,697 index procedures included in the data set, 740 (1%) experienced a dislocation resulting in hospital readmission within 90 days. Five machine learning algorithms were evaluated for their ability to predict dislocation leading to hospital readmission within 90 days of RSA. Shapley additive explanation (SHAP) values were calculated for the top-performing models to quantify the importance of features and understand variable interaction effects, with hierarchical clustering used to identify cohorts of patients with similar risk factor combinations. RESULTS: Of the 5 models evaluated, the extreme gradient boosting algorithm was the most reliable in predicting dislocation (C statistic = 0.71, F2 score = 0.07, recall = 0.84, Brier score = 0.21). SHAP value analysis revealed multifactorial explanations for dislocation risk, with presence of a preoperative humerus fracture; disposition involving discharge or transfer to a skilled nursing facility, intermediate care facility, or other nonroutine facility; and Medicaid as the expected primary payer resulting in strong, positive, and unidirectional effects on increasing dislocation risk. In contrast, factors such as comorbidity burden, index procedure complexity and duration, age, sex, and presence or absence of preoperative glenohumeral osteoarthritis displayed bidirectional influences on risk, indicating potential protective effects for these variables and opportunities for risk mitigation. Hierarchical clustering using SHAP values identified patients with similar risk factor combinations. CONCLUSION: Machine learning can reliably predict patients at risk for postoperative dislocation resulting in hospital readmission within 90 days of RSA. Although individual risk for dislocation varies significantly based on unique combinations of patient characteristics, SHAP analysis revealed a particularly at-risk cohort consisting of young, male patients with high comorbidity burdens who are indicated for RSA after a humerus fracture. These patients may require additional modifications in postoperative activity, physical therapy, and counseling on risk-reducing measures to prevent early dislocation after RSA.

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

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

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

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

The Nonoperative Instability Severity Index Score: Is It Predictive in a Larger Shoulder Instability Population at Long-Term Follow-Up?

PURPOSE: To evaluate the effect of the Nonoperative Instability Severity Index Score (NISIS) criteria on an established US-geographic population-based cohort of patients with anterior shoulder instability. METHODS: An established geographically based medical record system was used to identify patients <40 years of age with anterior shoulder instability between 1994 and 2016. Medical records were reviewed to obtain patient demographics and instability characteristics. Patient-specific risk factors were individually incorporated into the 10-point NISIS criteria: age (>15 years), bone loss, type of instability (dislocation vs subluxation), type of sport (collision vs noncollision), male sex, and dominant arm involvement. High risk was considered a score of ≥7 points and low risk as <7 points. Failure was defined as either progression to surgery or recurrent instability diagnosed by a consulting physician at any point after initial consultation. RESULTS: The study population consisted of 405 patients with a mean follow-up time of 9.6 ± 5.9 years. Failure was defined as recurrent instability or progression to surgery, and the overall failure rate was 52.8% (214/405). The rate of recurrent instability after initial consultation was 34.6% (140/405), and the rate of conversion to surgery was 37.8% (153/405). A total of 264 (65.2%) patients were considered low risk (NISIS < 7), and 141 (34.8%) patients were considered high risk (NISIS ≥ 7). Patients in the high-risk group were more likely to fail nonoperative management than those in the low-risk group (60.3% vs 48.9%; P = .028). CONCLUSIONS: The NISIS has been proposed as a potentially useful tool in clinical decision-making regarding the appropriate use of nonoperative treatment in scholastic athletes. When applied to an established US-geographic population-based cohort consisting of competitive and recreational athletes under the age of 40 with longer-term follow-up, the NISIS high-risk cutoff was able to predict overall failure with 60.3% accuracy. LEVEL OF EVIDENCE: III, retrospective observation trial.