Arthroscopy-The Journal of Arthroscopic and Related Surgery最新文献

{"title":"Editorial Commentary: The Importance of Rigorous Testing for Artificial Intelligence Solutions: Don't Forget to Flip Over the Page and Answer All the Questions!","authors":"Tyler Khilnani, Kyle N Kunze","doi":"10.1002/arj.70568","DOIUrl":"10.1002/arj.70568","url":null,"abstract":"<p><p>Manual Current Procedural Terminology coding for billing purposes is labor-intensive, error-prone, and imposes a substantial administrative burden on physicians and care teams. As interest in artificial intelligence applied to health care inefficiencies grows, appropriately designed solutions may optimize billing and coding workflows by improving efficiency and accuracy. Recent locally deployed models have shown promise in providing scalable function while protecting patient data. However, these models have shown success only when provided contextual clues in the setting of verification, with performance dropping to near chance when such context is withheld. In addition, the current evaluation has been limited to verification rather than prospective code generation from operative reports. These models also have not been shown to distinguish closely related codes or apply multiple codes to a single procedure, severely limiting their applicability to real-world practice. Future investigations must therefore focus on developing models that prospectively generate Current Procedural Terminology codes, independently verify and flag incorrect codes, and achieve external validity across multiple institutions, disciplines, and documentation styles before they are ready for clinical implementation.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2746-2748"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial Commentary: Does Size Matter? Evaluating Hill-Sachs Lesion Size in Shoulder Instability.","authors":"Joseph S Tramer, Vincent A Lizzio, Lafi S Khalil","doi":"10.1002/arj.70654","DOIUrl":"10.1002/arj.70654","url":null,"abstract":"<p><p>Does the size of a Hill-Sachs lesion (HSL) matter? Since its original description in 1940, understanding of the HSL's contribution to recurrent shoulder instability has evolved from a binary engaging/nonengaging framework under the glenoid track concept to more nuanced concepts of bipolar bone loss on a continuum. Although much attention has been centered on glenoid bone loss, the contribution of an HSL and, perhaps more importantly, the distance to dislocation of the HSL have gained increasing attention. How to evaluate at-risk patients with chronic shoulder instability and multiple, recurrent instability events remains problematic, especially when their shoulder fits a classic on-track, nonengaging biomechanical profile. Do patients with chronic and recurrent instability events have worse, larger, or more medialized HSL? Should we do more than isolated arthroscopic Bankart repair in these patients? The paradigm appears to shift along with the location of the HSL.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2454-2456"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149066043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recovery Curves After Hip Arthroscopy for Femoroacetabular Impingement Are Slower for Patients With Severe Ligamentous Laxity: A Propensity-Matched Study.","authors":"Dharma H Patel, Roger Quesada-Jimenez, Wonjin Ko, Absolon Reyes, Ady H Kahana-Rojkind, Benjamin D Kuhns, Benjamin G Domb","doi":"10.1002/arj.70526","DOIUrl":"10.1002/arj.70526","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the patient-reported outcome recovery trajectories of generalized ligamentous laxity (GLL) patients undergoing hip arthroplasty for femoroacetabular impingement and labral tears from preoperative to short- to mid-term follow-up and to compare these results to a propensity-matched control group without GLL.</p><p><strong>Methods: </strong>Patients from a single-institution database who underwent primary hip arthroplasty for femoroacetabular impingement syndrome and labral tears between October 2012 and August 2022 were retrospectively reviewed. Included patients had preoperative and minimum 2-year follow-up patient-reported outcomes, including modified Harris Hip Score, Nonarthritic Hip Score, International Hip Outcome Tool-12, Hip Outcome Score-Sport Scale, and Visual Analogue Scale for pain. Patients with Beighton score ≥4 were propensity-matched to patients with Beighton score <4. A subanalysis was conducted comparing individuals with high Beighton (HB) scores of 8 or 9 to a non-GLL control group. Rates of achieving clinically relevant outcome thresholds including the patient acceptable symptomatic state (PASS) and minimum clinically important difference were collected.</p><p><strong>Results: </strong>Three hundred forty-five GLL patients were successfully matched to 345 control patients. There were no differences in patient-reported outcomes at any time point. There were no differences in reoperation rates and a high percentage of minimum clinically important difference and PASS threshold achievement across both groups. Subanalysis comparing the HB and non-GLL groups showed a slower recovery for the HB group, with significantly higher pain scores at the 3-month (2.83 ± 2.15 vs 1.53 ± 1.37; P = .02) and 1-year (2.95 ± 1.99 vs 1.75 ± 2.50; P = .03) time points but reaching similar long-term outcomes. Patients in the HB group also had lower rates of PASS threshold achievement at 3 months (52.2% vs 76.0%; P = .02) compared with the control group but had comparable long-term outcomes.</p><p><strong>Conclusions: </strong>Hip arthroplasty in patients with GLL yielded significant improvements at short- to mid-term follow-up, with a recovery trajectory comparable to that of patients without GLL. However, patients with higher Beighton scores of 8 or 9 exhibited a slower recovery curve with higher pain levels and lower rates of PASS threshold achievement, which then normalized in the mid-term.</p><p><strong>Level of evidence: </strong>Level III, retrospective comparative control study.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2563-2574"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148914488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Platelet-Rich Products Can Have Variable Effects on Outcomes After Arthroscopic Full-Thickness Rotator Cuff Repair: A Meta-analysis of Randomized Controlled Trials.","authors":"WeiYi Chen, WanQing Qi, YunQing Su, MengYang Jia, QianRu Yao, XianXiang Xiang","doi":"10.1002/arj.70234","DOIUrl":"10.1002/arj.70234","url":null,"abstract":"<p><strong>Purpose: </strong>To determine the effects of different platelet-rich products on the clinical outcomes of patients undergoing arthroscopic full-thickness rotator cuff repair.</p><p><strong>Methods: </strong>We searched the MEDLINE, EMBASE, and Cochrane databases for randomized controlled trials. Data included the retear rate and functional outcomes and subgroup analyses were performed to investigate the effect of 7 characterized platelet-rich products. Risks of bias of all trials were assessed using a Cochrane risk of bias tool, and data analysis was performed using RevMan 5.3 and Stata 15 software.</p><p><strong>Results: </strong>Fifteen randomized controlled trials were included. Platelet-rich products resulted in significant improvements in retear rates and Constant scores, visual analog scale scores, and the University of California, Los Angeles scores (P < .05). However, there was no significant effect on the American Shoulder and Elbow Surgeons scores. Subgroups showed lower retear rates with platelet-rich products having either poor leukocytes (P < .0001) or higher platelet concentrations (P = .0005), liquid form (P = .0005), platelet-rich plasma type (P < .0001), and tendon-bone interface (P = .0006) or intratendinous application (P = .030) during surgery (P < .0001) compared with controls. Higher Constant scores occurred with platelet-rich products having either poor leukocytes (P = .004) or higher platelet concentrations (P = .05), liquid form (P = .01) or platelet-rich plasma type (P = .008), and single (P = .02) intratendinous (P = .04) application during surgery (P = .02).</p><p><strong>Conclusions: </strong>The use of platelet-rich products as augmentation in rotator cuff surgical repair significantly reduces the retear rate and improves the functional scores, though the clinical significance appears not to be meaningful. If used, we recommend platelet-rich products with poor leukocytes and high platelet concentrations, or liquid platelet-rich products in platelet-rich plasma type with a single intratendinous injection during surgery.</p><p><strong>Level of evidence: </strong>Level II, meta-analysis of Level I and II randomized controlled trials.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2763-2776"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148037910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Residual Midbody Meniscal Widths >13 mm Immediately After Surgery Decreased Faster and Had Greater Complication Rates in Discoid Lateral Menisci Treated With Saucerization and Repair.","authors":"Yusuke Hashimoto, Nozomi Aibara, Shinya Yamasaki, Yohei Nishida, Tomihara Tomohiro, Hidetomi Terai","doi":"10.1002/arj.70378","DOIUrl":"10.1002/arj.70378","url":null,"abstract":"<p><strong>Purpose: </strong>To estimate the adequate residual midbody meniscal width immediately after surgery saucerization with repair for discoid lateral meniscus (DLM) and at subsequent follow-up, and to evaluate the complication rate.</p><p><strong>Methods: </strong>A retrospective analysis was conducted on complete DLM cases that underwent saucerization with repair from August 2017 to January 2023, with a minimum follow-up of 2 years. Knees were classified into 3 groups based on midbody meniscal width immediately after surgery: large (>13 mm), normal (9 to ≤13 mm), and small (<9 mm). Changes in residual meniscal width over time and complications such as retear, revision surgery, and postoperative osteochondritis dissecans were assessed. The minimum clinically important difference of the Lysholm score was calculated. Demographic data and meniscal width immediately after surgery were analyzed for associations with greater than a 50% reduction in residual midbody width from 0 to 24 months using logistic regression analyses.</p><p><strong>Results: </strong>Seventy-seven knees of 72 patients were reviewed in this study. The minimum clinically important difference achievement rate was 98.7%, with no significant difference among the 3 groups. The complication rate in the large group was significantly higher than in the normal group (P = .026). On multivariate analysis, greater midbody meniscal width at 0 months (odds ratio, 1.38; P = .006) was identified as a risk factor for >50% reduction in residual midbody width, with a cutoff value of 11.5 mm.</p><p><strong>Conclusions: </strong>Although clinical outcomes showed favorable minimum clinically important difference achievement regardless of meniscus size, a residual midbody meniscal width >13 mm immediately after surgery decreased faster than smaller widths and had greater complication rate in DLM treated with saucerization and repair.</p><p><strong>Level of evidence: </strong>Level IV, retrospective case series.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2590-2602"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148363997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Direct Comparison Between Loss-to-Follow-Up and Statistical Fragility Is Methodologically Inappropriate, and Fragility Reflects the P Value, Not Trial Robustness: A Simulation Analysis of 300,000 Randomized Controlled Trials.","authors":"Prushoth Vivekanantha, Helena Son, Jeffrey Kay, Satyavenkata Kotipalli, Marc Daniel Bouchard, Kim Madden, Nicole Simunovic, Olufemi R Ayeni","doi":"10.1002/arj.70457","DOIUrl":"10.1002/arj.70457","url":null,"abstract":"<p><strong>Purpose: </strong>To assess the relation between the fragility index (FI) and reverse fragility index (RFI) with the minimum number of patients needed to reverse statistical significance (e.g. henceforth termed the lost to follow-up index (LTFI) and reverse LTFI (R-LTFI), respectively) and apply machine learning to identify which trial parameters are most important in FI, RFI, and continuous fragility index composition given the nonlinearity of these metrics.</p><p><strong>Methods: </strong>A total of 300,000 randomized controlled trials (100,000 for each metric) were simulated using common trial parameter value ranges. For FI and RFI, LTFI and R-LTFI values, respectively, were calculated as the minimum number of patients lost to follow-up to reverse significance in either direction. Machine learning models were trained to assess the relative importance of P value, sample size, and event numbers in FI and RFI composition and P value, group means, group standard deviations, and group sizes for continuous fragility index composition.</p><p><strong>Results: </strong>Among their respective cohorts of 100,000, the LTFI and R-LTFI were greater than FI and RFI in 84.9% and 95.5% of simulated randomized controlled trials, respectively. Random Forest and XGBoost machine learning models had near perfect accuracy in modeling fragility metrics (R² ≥ 0.98), justifying its use over standard linear regression models in identifying trial parameters that are most important in determining fragility values. Feature importance analysis showed that the P value accounted for 79.8%, 71.9%, and 64.5% of variability in FI, RFI, and continuous fragility index values.</p><p><strong>Conclusions: </strong>Fragility metrics are primarily mathematical reflections of standard trial parameters and are heavily driven by the P value. Direct comparisons between fragility metrics and lost to follow-up are statistically inappropriate because LTFI and R-LTFI routinely exceed FI and RFI, respectively, and should be avoided in future fragility-based studies.</p><p><strong>Clinical relevance: </strong>Understanding that statistical fragility metrics are mathematical transformations of trial parameters, and not independent measures of robustness, can prevent trial misinterpretation. Additionally, recognizing that the number of patients required to be lost to follow-up to reverse trial significance often exceeds fragility metrics should discourage inappropriate comparisons in future orthopaedic research.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2749-2758"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148763822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Approximately 30% of Patients Undergoing Knee Cartilage Biopsy Subsequently Undergo Matrix-Induced Autologous Chondrocyte Implantation at a Mean 4.3-Year Follow-Up.","authors":"Louis S Kang, Jason G Ina, Marieke Kietselaer, Christopher V Nagelli, Adam J Tagliero, Mario Hevesi, Aaron J Krych, Daniel B F Saris","doi":"10.1002/arj.70429","DOIUrl":"10.1002/arj.70429","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate implantation rates, time to implantation, and predictors of implantation following matrix-induced autologous chondrocyte implantation (MACI) biopsy for knee chondral defects.</p><p><strong>Methods: </strong>Patients undergoing MACI biopsy or implantation for symptomatic knee chondral defects from 2017 to 2024 at a single institution were reviewed. At a minimum 1-year follow-up, the decision to proceed with implantation, recurrent symptoms, complications, and reoperations were assessed. Kaplan-Meier analysis estimated time to implantation, and multivariable logistic regression identified predictors of MACI implantation.</p><p><strong>Results: </strong>A total of 208 knees in 202 patients (mean age 28.0 ± 10.9 years, range 11-59) underwent MACI biopsy for 243 chondral defects (patella [38%], femoral condyle [34%], and trochlea [26%]). At a mean follow-up of 4.3 years (range 1.0-8.3), 64 knees (31%) proceeded to second-stage MACI implantation. Among 144 knees not implanted, 87 (60%) reported symptom improvement, and 26 (18%) had persistent symptoms. The remaining 22% did not undergo implantation due to another cartilage procedure, insurance denial, or pending scheduling. Patients who underwent biopsy at the home institution had a shorter time from biopsy to implantation compared with those biopsied at outside institutions (6.1 vs 13.1 months, P = .001). Median time to implantation was 9.4 months (95% confidence level: 7.2-12.2) for home biopsies. Lower body mass index was associated with progression to implantation after adjusting for covariates (odds ratios 0.92, P = .019). Patients implanted within 4 months had larger chondral defects (4.0 vs 3.0 cm², P = .045). At a mean 4.1-year follow-up, 6 patients (8%) experienced postoperative complications, including 3 (4%) who required revision chondroplasty.</p><p><strong>Conclusions: </strong>MACI biopsy for knee chondral defects resulted in approximately one-third of patients proceeding to MACI implantation, at a median of 9.4 months after biopsy. Lower body mass index was associated with higher likelihood of progression to implantation, larger chondral defects with earlier implantation, and among patients who did not proceed to implantation, approximately 60% reported symptom improvement following concomitant chondroplasty at the time of biopsy.</p><p><strong>Level of evidence: </strong>Level IV, retrospective case series.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2661-2671"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148851966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Repair-Tension Sweet Zone Maximizes Tendon-to-Bone Healing in a Rat Rotator Cuff Model.","authors":"Qiaonan Liu, Lang Bai, Xiangyang Li, Yixiang Ai, Yukuan Wu, Meiguang Xu, Baojun Chen, Jintao Xiu, Jing Zhang, Zhanhai Yin","doi":"10.1002/arj.70471","DOIUrl":"10.1002/arj.70471","url":null,"abstract":"<p><strong>Purpose: </strong>To define a sweet zone of repair tension that maximizes tendon-to-bone healing while maintaining early functional safety in a rat model of rotator cuff repair.</p><p><strong>Methods: </strong>Forty-eight rats were used to create a graded-tension supraspinatus repair model with four discrete repair tensions: minimal-tension (MinT), low-tension (LowT), medium-tension (MedT), and high-tension (HiT) at two postoperative time points (n = 6 per group per time point). Intraoperative peak tension was measured during supraspinatus tendon reattachment using a digital tension gauge and normalized to tendon cross-sectional area (N/mm²). Functional recovery was assessed by gait analysis at 2 and 4 weeks; magnetic resonance imaging evaluated edema and tendon continuity; biomechanical testing quantified failure load, stiffness, and stress; histology assessed enthesis organization, fibrocartilage formation, and collagen fiber alignment.</p><p><strong>Results: </strong>Measured repair stresses were 0.015, 0.060, 0.110, and 0.305 N/mm² for MinT, LowT, MedT, and HiT groups, respectively. At 4 weeks, MedT showed superior biomechanical healing, achieving the highest LowT ultimate failure load (23.24 ± 2.08 N) versus MinT (14.78 ± 1.40 N, P = .001) and HiT (14.90 ± 0.94 N, P < .001) and the greatest stiffness (11.63 ± 0.46 N/mm) versus LowT (8.44 ± 0.13 N/mm, P < .001), MinT (6.35 ± 1.36 N/mm, P = .003), and HiT (3.05 ± 0.04 N/mm, P < .001). Histologic healing was also best in MedT and worst in HiT (MedT 14.00 ± 1.10 vs. MinT 10.17 ± 0.75, LowT 11.17 ± 0.98, and HiT 8.83 ± 0.75; overall P < .001). Overall, outcomes followed a bell-shaped relationship with repair stress, defining a sweet zone centered at 0.10 to 0.12 N/mm².</p><p><strong>Conclusions: </strong>This study identifies a sweet zone of repair tension (0.10-0.12 N/mm²) that maintains early functional safety and achieves superior late structural and mechanical outcomes compared with under- or over-tensioned repairs.</p><p><strong>Clinical relevance: </strong>Rotator cuff repairs should aim not only to avoid excessive tension but also to target the sweet zone to optimize enthesis regeneration.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2431-2441"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148868014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial Commentary: The Femoral Impingement Index: Can Composite Morphology Better Capture Femoroacetabular Impingement Syndrome?","authors":"Niv Marom","doi":"10.1002/arj.70538","DOIUrl":"10.1002/arj.70538","url":null,"abstract":"<p><p>Hip arthroscopy has undergone remarkable evolution over the past 2 decades. Improvements in patient selection, advanced imaging, labral preservation, capsular management, and osseous correction of femoroacetabular impingement syndrome have translated into consistently favorable outcomes for appropriately selected patients. Yet, despite these advances, one fundamental challenge remains largely unresolved: Why do patients with apparently similar diagnoses and technically successful procedures experience substantially different degrees of postoperative improvement? It is becoming increasingly clear that the painful hip does not function according to isolated radiographic values. Rather, hip biomechanics emerge from the interaction between osseous morphology, dynamic motion, soft-tissue restraints, muscular control, and patient-specific functional demands. Understanding these complex relations may help guide future care, and bone-morphology interactions are an important place to begin.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2560-2562"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148957103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial Commentary: Calling Balls and Strikes: For Artificial Intelligence Models to Accurately Predict Rotator Cuff Retear, We Must Carefully Define the Strike Zone.","authors":"Krish S Sardesai, Kyle N Kunze","doi":"10.1002/arj.70483","DOIUrl":"10.1002/arj.70483","url":null,"abstract":"<p><p>Early retear is a devastating complication following arthroscopic rotator cuff repair. The ability to predict early retear in patients undergoing rotator cuff repair may allow for interventions targeted at mitigating the risk of this complication, thereby improving surgical outcomes. Transfer learning, wherein labeled datasets are used to repurpose pretrained convolutional neural networks, represents an important approach for potentially improving the accuracy of these predictions through using artificial intelligence and deep learning. Leveraging deep learning provides an alternative approach to using tabular data for predictions by extracting important and subtle data from imaging (such as arthroscopic photographs) to provide insight into how the appearance of a surgical construct may predict outcomes. However, the value of such pipelines depends highly on preprocessing and generalizability of the training datasets. When labeling datasets, characteristics such as tendon integrity may be partially subjective, so surgeon-versus-surgeon (interrater) reliability or surgeon-versus-model analysis is crucial towards reducing bias. Clinical adoption of these pipelines requires generalizability of models, and convolutional neural networks trained on single surgeon datasets introduces bias variability. Clinical adoption requires trust and fairness as well as governance by artificial intelligence regulatory committees or \"umpires;\" and, if we are to trust DL models to call balls and strikes with respect to rotator cuff integrity in the real-world, it is important to have a clearly defined strike-zone.</p>","PeriodicalId":55459,"journal":{"name":"Arthroscopy-The Journal of Arthroscopic and Related Surgery","volume":" ","pages":"2405-2407"},"PeriodicalIF":6.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148898524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}