An Artificial Intelligence Approach to Predicting Unplanned Intubation Following Anterior Cervical Discectomy and Fusion.

STUDY DESIGN: Level III retrospective database study. OBJECTIVES: The purpose of this study is to determine if machine learning algorithms are effective in predicting unplanned intubation following anterior cervical discectomy and fusion (ACDF). METHODS: The National Surgical Quality Initiative Program (NSQIP) was queried to select patients who had undergone ACDF. Machine learning analysis was conducted in Python and multivariate regression analysis was conducted in R. C-Statistics area under the curve (AUC) and prediction accuracy were used to measure the classifier's effectiveness in distinguishing cases. RESULTS: In total, 54 502 patients met the study criteria. Of these patients, .51% underwent an unplanned re-intubation. Machine learning algorithms accurately classified between 72%-100% of the test cases with AUC values of between .52-.77. Multivariable regression indicated that the number of levels fused, male sex, COPD, American Society of Anesthesiologists (ASA) > 2, increased operating time, Age > 65, pre-operative weight loss, dialysis, and disseminated cancer were associated with increased risk of unplanned intubation. CONCLUSIONS: The models presented here achieved high accuracy in predicting risk factors for re-intubation following ACDF surgery. Machine learning analysis may be useful in identifying patients who are at a higher risk of unplanned post-operative re-intubation and their treatment plans can be modified to prophylactically prevent respiratory compromise and consequently unplanned re-intubation.

Graft Choice for Anterior Cruciate Ligament Reconstruction in Women Aged 25 Years and Younger: A Systematic Review.

CONTEXT: Although anterior cruciate ligament (ACL) tears are relatively common in athletic populations, few studies have systematically reviewed graft choice in young women. OBJECTIVE: To quantitatively and qualitatively examine reported outcomes for graft choice in women aged 25 years and younger undergoing primary ACL reconstruction. DATA SOURCE: A systematic review was performed using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. An electronic search in the PubMed (includes MEDLINE) and EMBASE databases was completed using a combination of key terms. STUDY SELECTION: Studies were included if they reported graft choice outcomes in women aged 25 years and younger. STUDY DESIGN: Systematic review. LEVEL OF EVIDENCE: Level 4. DATA EXTRACTION: The following information was extracted: title, author, year of publication, number of female patients and age, graft type, follow-up, and patient-reported outcome measures. The following outcome scores were identified as being reported or not reported by each study: graft failure, contralateral ACL (CACL) rupture, IKDC (International Knee Documentation Committee), graft survival (Kaplan-Meier), Lysholm, Tegner, KT-1000, kneeling pain, return to sport, and Lachman. RESULTS: Of 1170 identified articles, 16 met inclusion criteria, reporting on 1385 female patients aged 25 years and younger. Comparison of 655 bone-patellar tendon-bone (BPTB) versus 525 hamstring tendon (HT) autografts showed significant differences in mean failure rate between BPTB autografts (6.13% ± 2.58%) and HT autografts (17.35% ± 8.19%), P = 0.001. No statistically significant differences in CACL failure rates were found between BPTB autografts and HT autografts (P = 0.25). Pooled results for IKDC were possible in 3 of the HT autograft studies, showing a mean score of 88.31 (95% CI 83.53-93.08). Pooled Lysholm score results were possible in 2 of the HT autograft studies, showing a mean score of 93.46 (95% CI 91.90-95.01). CONCLUSION: In female patients aged 25 years and younger, BPTB autografts showed significantly less graft failure compared with HT autografts. However, BPTB autografts had comparable patient-reported outcomes compared with HT autografts with the available data. The overall state of evidence for graft choice in female patients aged 25 years and younger is low. Future studies should report statistics by age and sex to allow for further analysis of graft choice for this specific population that is known to be more vulnerable to ACL injury.

Epidemiology of rugby-related fractures in high school- and college-aged players in the United States: an analysis of the 1999-2018 NEISS database.

OBJECTIVES: Rugby is a high-impact collision sport with identical competition rules by sex. The aim of this study was to analyze the trend of rugby-related fractures by body site, sex, and age in amateur athletes from 1999 to 2018. METHODS: The National Electronic Injury Surveillance System (NEISS) database was queried to characterize rugby-related injuries from 1999 to 2018 in patients aged 14-23 years old. National injury estimates were calculated using sample weights. Chi-square analysis and one-way ANOVA were performed to compare categorical variables. RESULTS: Out of a total of 43,722 weighted cases of rugby-related fractures over the 19-year period, 70.9% were among high school- and college-aged males and females between the ages of 14-23 years (N = 30,996). Males constituted 79.3% of cases whereas females composed 20.7% of the cases. The proportion of upper extremity fractures was similar in both males and females, yet facial fractures were significantly more common among males than females (27.9% vs. 14.6%, P < 0.001). Among facial fractures, nasal fractures represented 74.4% of the sample, yet facial fractures only resulted in hospital admittance in 1.3% of cases. Lower extremity fractures were more likely to be severe, with 11.3% of LE cases being admitted to the hospital. CONCLUSION: Rugby players in the US diagnosed in the ED with fractures consisted largely of male, high school- and college-aged athletes. Males and females experienced upper and lower-extremity fractures at comparable rates, yet lower extremity injuries were more likely to be admitted to a hospital. Men were significantly more likely to experience a facial fracture in which a majority were nasal fractures.

A quality assessment of YouTube content on shoulder instability.

OBJECTIVES: The Internet is a widely used resource for patients seeking health information, yet little editing or regulations are imposed on posted material. We sought to assess the quality and accuracy of information presented on shoulder instability on the online video platform YouTube. We hypothesize that YouTube videos concerning shoulder instability will be of little quality, accuracy, and reliability. METHODS: The first 50 YouTube videos resulting from the keyword query 'shoulder instability' were analyzed. The Journal of American Medical Association (JAMA) benchmark criteria (score range, 0-4) was used to assess video accuracy and reliability, and the Global Quality Score (GQS; score range, 0-5) was used to assess the quality of the video's educational content along with a generated Shoulder-Specific Score (SSS). RESULTS: The 50 videos observed collectively had 5,007,486 views, with the mean number of views being 100,149.72 ± 227,218.04. Of all videos observed, 32% were from a medical source and 56% had content relating to pathology information. The mean JAMA score was 2.84 ± 0.74, with the highest scores coming from academic sources. The mean GQS and SSS scores were 2.68 ± 0.84 and 5.30 ± 3.78. The mean GQS score was highest in videos from medical sources (3.3 ± 0.8) and videos about surgical technique/approach (3.2 ± 1.1). Advertisements were negative predictors of the JAMA score (ß = -0.324, P = 0.014), and academic (ß = 0.322, P = 0.015) and physician sources (ß = 0.356, P = 0.008) were positive predictors. CONCLUSION: YouTube videos on shoulder instability are of low quality and accuracy and are not reliable. Care providers should be aware of the overall low quality of information available on YouTube regarding shoulder instability.

Supervised Machine Learning for Predicting Length of Stay After Lumbar Arthrodesis: A Comprehensive Artificial Intelligence Approach.

INTRODUCTION: Few studies have evaluated the utility of machine learning techniques to predict and classify outcomes, such as length of stay (LOS), for lumbar fusion patients. Six supervised machine learning algorithms may be able to predict and classify whether a patient will experience a short or long hospital LOS after lumbar fusion surgery with a high degree of accuracy. METHODS: Data were obtained from the National Surgical Quality Improvement Program between 2009 and 2018. Demographic and comorbidity information was collected for patients who underwent anterior, anterolateral, or lateral transverse process technique arthrodesis procedure; anterior lumbar interbody fusion (ALIF); posterior, posterolateral, or lateral transverse process technique arthrodesis procedure; posterior lumbar interbody fusion/transforaminal lumbar interbody fusion (PLIF/TLIF); and posterior fusion procedure posterior spine fusion (PSF). Machine learning algorithmic analyses were done with the scikit-learn package in Python on a high-performance computing cluster. In the total sample, 85% of patients were used for training the models, whereas the remaining patients were used for testing the models. C-statistic area under the curve and prediction accuracy (PA) were calculated for each of the models to determine their accuracy in correctly classifying the test cases. RESULTS: In total, 12,915 ALIF patients, 27,212 PLIF/TLIF patients, and 23,406 PSF patients were included in the algorithmic analyses. The patient factors most strongly associated with LOS were sex, ethnicity, dialysis, and disseminated cancer. The machine learning algorithms yielded area under the curve values of between 0.673 and 0.752 (PA: 69.6% to 80.1%) for ALIF, 0.673 and 0.729 (PA: 66.0% to 81.3%) for PLIF/TLIF, and 0.698 and 0.749 (PA: 69.9% to 80.4%) for PSF. CONCLUSION: Machine learning classification algorithms were able to accurately predict long LOS for ALIF, PLIF/TLIF, and PSF patients. Supervised machine learning algorithms may be useful in clinical and administrative settings. These data may additionally help inform predictive analytic models and assist in setting patient expectations. LEVEL III: Diagnostic study, retrospective cohort study.

Player age and initial helmet contact among American football players.

OBJECTIVE: Concussions and chronic traumatic encephalopathy (CTE) related to professional football has received much attention within emergency care and sports medicine. Research suggests that some of this may be due to a greater likelihood of initial helmet contact (IHC), however this association has not been studied across all age groups. This study aims to investigate the association between player age and IHC in American football. METHODS: Retrospective review of championship games between 2016 and 2018 at 6 levels of amateur tackle football as well as the National Football League (NFL). Trained raters classified plays as IHC using pre-specified criteria. A priori power analysis established the requisite impacts needed to establish non-inferiority of the incidence rate of IHC across the levels of play. RESULTS: Thirty-seven games representing 2912 hits were rated. The overall incidence of IHC was 16% across all groups, ranging from 12.6% to 18.9%. All but 2 of the non-NFL divisions had a statistically reduced risk of IHC when compared with the NFL, with relative risk ratios ranging from 0.55-0.92. IHC initiated by defensive participants were twice as high as offensive participants (RR 2.04, p < 0.01) while 6% [95% CI 5.4-7.2] of all hits were helmet-on-helmet contact. CONCLUSIONS: There is a high rate of IHC with a lower relative risk of IHC at most levels of play compared to the NFL. Further research is necessary to determine the impact of IHC; the high rates across all age groups suggests an important role for education and prevention.

Foundational Health for Runners: Is it the Key to Minimizing Injury?

BACKGROUND: Injury rates in runners are as high as 80%. Here, we focus on the concept of foundational health including sleep, recovery, nutrition, stress and physical health and how it can reduce injuries. METHODS: The literature was reviewed to find papers linking running injuries and athletic performance to the foundational health topics discussed. RESULTS: There are many factors that can improve athletic performance and reduce injuries in runners other than the often-discussed topics: training philosophies, footwear, and running form. This paper shows how a multidisciplinary approach including education on sleep, rest, stress, nutrition, strength, and mobility all can improve performance and reduce injuries. CONCLUSIONS: The care and management of an injured runner is multifactorial and the treatment should be as well. By optimizing foundational health, the sports medicine professional will not only reduce injury risk, but also improve performance and overall health.

Arthroscopic Versus Open Bankart Repairs in Recurrent Anterior Shoulder Instability: A Systematic Review of the Association Between Publication Date and Postoperative Recurrent Instability in Systematic Reviews.

PURPOSE: To systematically review the results of systematic studies regarding open versus arthroscopic Bankart repairs for recurrent anterior shoulder instability and quantitatively analyze the effect of primary-literature publication dates on reported outcomes in these systematic studies. METHODS: A systematic search was conducted to identify systematic studies reporting outcomes of both arthroscopic and open Bankart repairs for recurrent anterior shoulder instability. Patient-reported outcome measures, recurrent instability rates, definitions of instability, and procedure types reported by included study characteristics were qualitatively analyzed. Correlation coefficient analyses were performed to investigate if a systematic study's proportion of included primary literature published after 1999, 2000, 2001, or 2002 affected that study's reported mean difference in instability recurrence between open and arthroscopic procedures. The Assessment of Multiple Systematic Reviews criteria were used to assess the risk of bias of the included studies. RESULTS: Of 130 identified articles, 6 met the inclusion criteria. Patient-reported outcome measures were poorly reported. Among mean differences in instability recurrence rates, the results were indeterminate: Although 5 studies reported arthroscopic surgical procedures as having a higher recurrence rate, only 1 reported a statistically significant difference. Within the 5 included systematic reviews reporting the number of included studies, 37 of 56 observations were published after 2000. The proportion of studies published after 2000 (Pearson r = 0.88, P = .052) was positively associated with differences in instability recurrence rates between open and arthroscopic procedures. CONCLUSIONS: Systematic studies that included newer studies (published after 2000) were associated with more favorable arthroscopic outcomes. LEVEL OF EVIDENCE: Level IV, systematic review of Level III and IV studies.

Epidemiology of Upper Extremity Soccer Injuries Among High School- and College-Aged Players in the United States: An Analysis of the 1999-2016 NEISS Database.

BACKGROUND:: Although lower extremity injuries are more common than upper extremity injuries in high school- and college-aged soccer players, upper extremity injuries may be equally severe. The epidemiology of upper extremity injuries is poorly characterized in this population. HYPOTHESIS:: Upper extremity injuries are an important contributor to soccer-related morbidity among high school- and college-aged players. STUDY DESIGN:: Descriptive epidemiology study. LEVEL OF EVIDENCE:: Level 3. METHODS:: The National Electronic Injury Surveillance System (NEISS) is a nationally representative sample of 100 hospital emergency departments (EDs). Each record contains demographic and injury information. Records from 1999 to 2016 were analyzed, including patients between the ages of 14 and 23 years with a soccer-related injury sustained at school or during an athletic event. RESULTS:: A total of 1,299,008 high school- or college-aged patients presented to the ED for a soccer-related injury from 1999 to 2016, of which 20.4% were in the upper extremity. Patients were predominantly male (58.0%) and high school-aged (81.4%). Males constituted a greater proportion of upper extremity injuries when compared with other injury locations (63.5% male for upper extremity). Upper extremity injuries were more likely to be fractures (43.7% vs 13.9%) and dislocations (7.1% vs 3.4%) and less likely to be strains/sprains (27.8% vs 56.6%). Males suffered more shoulder dislocations (81.8% males among patients with shoulder dislocation vs 57.8% among those with other injuries), finger dislocations (72.0% vs 58.0%), upper arm fractures (74.9% vs 57.6%), and forearm fractures (68.3% vs 57.3%). CONCLUSION:: Upper extremity injuries are frequent in high school- and college-aged soccer players presenting to the ED. Efforts to reduce soccer-related injuries should include strategies targeting the upper extremity, perhaps reducing the incidence of high-energy falls. CLINICAL RELEVANCE:: Efforts to reduce soccer-related injuries should include strategies targeting upper extremity injuries, particularly among males and college-aged players.

Shoulder and elbow injuries in soccer goalkeepers versus field players in the National Collegiate Athletic Association, 2009-2010 through 2013-2014.

OBJECTIVES: Examination of the incidence of shoulder and elbow injuries in the collegiate soccer player population is limited, as is comparison between goalkeepers and field players. We hypothesized that goalkeepers would have a higher incidence of shoulder and elbow injuries than field players. Furthermore, we sought to determine the incidence of shoulder and elbow injuries among National Collegiate Athletic Association (NCAA) soccer players, and to determine injury risk factors. METHODS: The NCAA Injury Surveillance Program database was analyzed for injuries to NCAA men's and women's soccer players during the 2009-2010 through 2013-2014 academic years. The incidence of injury was calculated per 10,000 athletic exposures (AE) for goalkeepers versus field players, activity, and injury characteristics, and compared using univariate analysis and risk-ratios to determine injury risk factors. RESULTS: While the overall incidence of shoulder and elbow injuries in soccer players was 2.7/10,000AE [95% CI 2.62-2.78], the incidence among goalkeepers was 4.6-fold higher (8.3 vs. 1.8/10,000AE, p < 0.0001). Goalkeepers had significantly higher incidences of injury in practice (21.3-fold) and in the preseason (16.1-fold) than field players. Women goalkeepers were disproportionately affected, with injury incidences 7.7-fold higher than women field players, and 1.9-fold higher than male goalkeepers. Acromioclavicular joint injuries, rotator cuff tears/sprains, and elbow and shoulder instability constituted the majority of the goalkeeper injuries. CONCLUSIONS: Shoulder and elbow injuries in NCAA soccer players are significantly more common in goalkeepers than field players. Incidence varies widely by position and injury, with a number of associated risk factors. Soccer players sustaining these injuries, along with their coaches and medical providers, may benefit from this injury data to best manage expectations and outcomes. Soccer governing bodies may use this to track injury incidence and response to preventative measures.