Artificial intelligence improves resident detection of pediatric and young adult upper extremity fractures.

PURPOSE: We wished to evaluate if an open-source artificial intelligence (AI) algorithm ( https://www.childfx.com ) could improve performance of (1) subspecialized musculoskeletal radiologists, (2) radiology residents, and (3) pediatric residents in detecting pediatric and young adult upper extremity fractures. MATERIALS AND METHODS: A set of evaluation radiographs drawn from throughout the upper extremity (elbow, hand/finger, humerus/shoulder/clavicle, wrist/forearm, and clavicle) from 240 unique patients at a single hospital was constructed (mean age 11.3 years, range 0-22 years, 37.9% female). Two fellowship-trained musculoskeletal radiologists, three radiology residents, and two pediatric residents were recruited as readers. Each reader interpreted each case initially without and then subsequently 3-4 weeks later with AI assistance and recorded if/where fracture was present. RESULTS: Access to AI significantly improved area under the receiver operator curve (AUC) of radiology residents (0.768 [0.730-0.806] without AI to 0.876 [0.845-0.908] with AI, P < 0.001) and pediatric residents (0.706 [0.659-0.753] without AI to 0.844 [0.805-0.883] with AI, P < 0.001) in identifying fracture, respectively. There was no evidence of improvement for subspecialized musculoskeletal radiology attendings in identifying fracture (AUC 0.867 [0.832-0.902] to 0.890 [0.856-0.924], P = 0.093). There was no evidence of difference between overall resident AUC with AI and subspecialist AUC without AI (resident with AI 0.863, attending without AI AUC 0.867, P = 0.856). Overall physician radiograph interpretation time was significantly lower with AI (38.9 s with AI vs. 52.1 s without AI, P = 0.030). CONCLUSION: An openly accessible AI model significantly improved radiology and pediatric resident accuracy in detecting pediatric upper extremity fractures.

Patellar Tendon Injury: A Bibliometric Analysis of the Most-Cited Articles Demonstrates Relatively High Overall Level of Evidence.

Purpose: To identify and analyze the 50 most-cited articles in patellar tendon injury research. Methods: The ISI Web of Science and SCOPUS databases were used to conduct a search for articles pertaining to patellar tendon injury. For the top 50 most-cited articles, bibliometric data (title, first and senior author, citation count, journal, publication year, citation density, country of origin, Level of Evidence [LOE]) and topic of article were recorded. Results: The mean number of citations was 172.0 ± 88.2 (range 101-546). There was a statistically significant correlation between publication year and citation density (r = 0.61, P < .01). The earliest article was the third most-cited article (362 citations), published by Blazina et al. in 1973, which discussed the epidemiology of patellar tendinopathy. The first and second most-cited articles (546 and 466 citations, respectively) covered surgical outcomes of patellar tendinopathy and prevalence of patellar tendinopathy among elite athletes. A total of 14 articles (28%) discussed nonoperative management, whereas only 5 articles discussed surgical management (10%). The most frequent LOE category was a LOE of IV (n = 18, 36%), but 19 studies (38%) were LOE I or LOE II. Conclusions: Among the top 50 most-cited studies regarding patellar tendon injury, a relatively high number were of a high LOE (19 Level I or II, 38%), affirming that these articles in patellar tendon injury research are not only influential, but also of high-quality evidence. Clinical Relevance: This bibliometric analysis provides an efficient tool for educators, researchers, and evidence-based practitioners to identify and evaluate the most influential articles in patellar tendon injury research.

A Machine Learning Algorithm Outperforms Traditional Multiple Regression to Predict Risk of Unplanned Overnight Stay Following Outpatient Medial Patellofemoral Ligament Reconstruction.

Purpose: To determine whether conventional logistic regression or machine learning algorithms were more precise in identifying the risk factors for unplanned overnight admission after medial patellofemoral ligament (MPFL) reconstruction. Methods: A retrospective review of the prospectively collected National Surgical Quality Improvement Program database was performed to identify patients who underwent outpatient MPFL reconstruction from 2006-2018. Patients admitted overnight were identified as those with length of stay of 1 or more days. Models were generated using random forest, extreme gradient boosting, adaptive boosting, or elastic net penalized logistic regression, and an additional model was produced as a weighted ensemble of the 4 final algorithms. The predictive capacity of these models was compared to that of logistic regression. Results: Of the 1307 patients identified, 221 (16.9%) required at least one overnight stay after MPFL reconstruction. Multivariate logistic regression found the following variables to be predictors of inpatient admission: age (odds ratio [OR] = 1.03 [95% confidence interval {CI} 1.02-1.04]; P <.001), spinal anesthesia (OR = 3.42 [95% CI 1.98-6.08]; P < .001), American Society of Anesthesiologists (ASA) class 3/4 (OR = 1.96 [95% CI 1.25-3.06]; P < .001), history of chronic obstructive pulmonary disease (COPD) (OR = 6.44 [95% CI 1.58-26.17]; P = .02), and body mass index (BMI) (OR = 1.03 [95% CI 1.01-1.05]; P < .001). The ensemble model achieved the best performance based on discrimination assessed via internal validation (area under the curve = 0.722). The variables determined most important by the ensemble model were increasing BMI, increasing age, ASA class, anesthesia, smoking, hypertension, lateral release, and history of COPD. Conclusions: An internally validated machine learning algorithm outperformed logistic regression modeling in predicting the need for unplanned overnight hospitalization after MPFL reconstruction. In this model, the most significant risk factors for admission were age, BMI, ASA class, smoking status, hypertension, lateral release, and history of COPD. This tool can be deployed to augment provider assessment to identify high-risk candidates and appropriately set postoperative expectations for patients. Clinical Relevance: Identifying and mitigating patient risk factors to prevent adverse surgical outcomes and hospitalizations is one of our primary goals. There may be a key role for machine learning algorithms to help successfully and efficiently risk stratify patients to decrease costs, appropriately set postoperative expectations, and increase the quality of delivered care.

Delaying ACL reconstruction beyond 6 months from injury impacts likelihood for clinically significant outcome improvement.

BACKGROUND: The effect of surgical latency on outcomes of anterior cruciate ligament reconstruction (ACLR) is a topic that is heavily debated. Some studies report increased benefit when time from injury to surgery is decreased while other studies report no benefit. The purpose of our analysis was to compare achievement of clinically significant outcomes (CSOs) in patients with greater than six months of time from injury to ACLR to those with less than or equal to six months of time to surgery. METHODS: Patients undergoing primary ACLR between January 2017 and January 2018 with minimum one year follow-up were included. International Knee Documentation Committee (IKDC) score and Knee Injury and Osteoarthritis Outcomes Score (KOOS) were collected. Multivariate logistic regression was performed for outcome achievement and risk of revision ACLR and Weibull parametric survival analysis was performed for relative time to outcome achievement. The level of significance was set at α = 0.05. RESULTS: 379 patients were included of which, 140 patients sustained ACL injury greater than six months prior to surgery. This group of patients experienced reduced likelihood to achieve patient-acceptable symptomatic state (PASS) on the IKDC (p = 0.03), KOOS Pain (p = 0.01) and a greater likelihood to undergo revision ACLR (p = 0.001). There was no impact of surgical timing on minimal clinically important difference (MCID). CONCLUSION: Patients with greater than 6 months from injury to ACLR reported reduced likelihood to achieve CSOs, delayed achievement of CSOs, and increased rates of revision surgery.

Biological sex impacts perioperative complications after reverse shoulder arthroplasty for proximal humeral fracture.

BACKGROUND: The purpose of this study was to determine the difference in complication rates between males and females undergoing reverse shoulder arthroplasty for proximal humerus fractures. We hypothesized that (1) females were more likely to undergo reverse shoulder arthroplasty for fracture, and (2) males were more likely to sustain a perioperative complication. METHODS: The National Surgical Quality Improvement Program database was queried to identify patients who underwent reverse shoulder arthroplasty for proximal humerus fracture between 2011 and 2018. Patients were stratified based on biological sex. Patient demographics, comorbidities, and 30-day perioperative complication rates were collected. Univariate analyses and multiple variable logistic regression modeling were performed. RESULTS: About 905 patients were included in the analysis-175 (19.3%) were male and 730 (80.7%) were female. Males were more likely to sustain perioperative complications (26.3% vs. 14.1%; P < .001)-pneumonia (2.9% vs. 0.5%; P = .016), unplanned intubation (2.3% vs. 0.4%; P = .029), and unplanned reoperation (9.1% vs. 1.1%; P < .001). On multivariate analysis, males were at a 2.4-fold increase risk of developing any complication (OR = 2.38 [95% CI 1.55-3.65]; P < .001) and a 10-fold increase risk of returning to the operating room for an unplanned reoperation (OR = 10.59 [95% CI 4.23-27.49]; P < .001) compared with females. CONCLUSION: Females were more likely to undergo reverse shoulder arthroplasty for proximal humerus fracture, but males were at increased risk of sustaining short-term complications. This study provides useful information for clinicians to consider when counseling their patients during the perioperative period.