Machine Learning Can Accurately Predict Overnight Stay, Readmission, and 30-Day Complications Following Anterior Cruciate Ligament Reconstruction.

PURPOSE: This study aimed to develop machine learning (ML) models to predict hospital admission (overnight stay) as well as short-term complications and readmission rates following anterior cruciate ligament reconstruction (ACLR). Furthermore, we sought to compare the ML models with logistic regression models in predicting ACLR outcomes. METHODS: The American College of Surgeons National Surgical Quality Improvement Program database was queried for patients who underwent elective ACLR from 2012 to 2018. Artificial neural network ML and logistic regression models were developed to predict overnight stay, 30-day postoperative complications, and ACL-related readmission, and model performance was compared using the area under the receiver operating characteristic curve. Regression analyses were used to identify variables that were significantly associated with the predicted outcomes. RESULTS: A total of 21,636 elective ACLR cases met inclusion criteria. Variables associated with hospital admission included White race, obesity, hypertension, and American Society of Anesthesiologists classification 3 and greater, anesthesia other than general, prolonged operative time, and inpatient setting. The incidence of hospital admission (overnight stay) was 10.2%, 30-day complications was 1.3%, and 30-day readmission for ACLR-related causes was 0.9%. Compared with logistic regression models, artificial neural network models reported superior area under the receiver operating characteristic curve values in predicting overnight stay (0.835 vs 0.589), 30-day complications (0.742 vs 0.590), reoperation (0.842 vs 0.601), ACLR-related readmission (0.872 vs 0.606), deep-vein thrombosis (0.804 vs 0.608), and surgical-site infection (0.818 vs 0.596). CONCLUSIONS: The ML models developed in this study demonstrate an application of ML in which data from a national surgical patient registry was used to predict hospital admission and 30-day postoperative complications after elective ACLR. ML models developed performed well, outperforming regression models in predicting hospital admission and short-term complications following elective ACLR. ML models performed best when predicting ACLR-related readmissions and reoperations, followed by overnight stay. LEVEL OF EVIDENCE: IV, retrospective comparative prognostic trial.

Common Orthopaedic Injuries in CrossFit Athletes.

CrossFit is a high-intensity exercise program that has gained popularity over the past few decades. CrossFit combines movements from Olympic weight lifting, gymnastics, powerlifting, and high-intensity interval training. As CrossFit continues to expand, knowledge of the associated orthopaedic injuries to aid providers in diagnosis, treatment, and prevention will be increasingly important. The most common CrossFit injuries occur in the shoulder (25% of all injuries), spine (14%), and knee (13%). Male athletes are markedly more likely to experience injuries than female athletes, and injuries occur markedly less when there is supervised coaching of the athletes. The most common causes of injury in CrossFit include improper form and exacerbation of a prior injury. The purpose of this article was to review the literature to aid clinicians in identifying and treating common orthopaedic injuries in CrossFit athletes. Understanding the injury patterns, treatment, and prevention options is important for a successful recovery and return to sport.

Comparing Skill Acquisition and Validity of Immersive Virtual Reality with Cadaver Laboratory Sessions in Training for Reverse Total Shoulder Arthroplasty.

Immersive virtual reality (iVR) allows surgical trainees to practice skills without risking harm to patients or the need for cadaveric training resources. However, iVR has never been directly compared with cadaver training, the longtime gold standard for surgical skill training. We aimed to compare skill acquisition using cadaver laboratory and iVR training methods for augmented baseplate implantation during reverse total shoulder arthroplasty (rTSA). Methods: In a randomized controlled trial, junior orthopaedic surgery residents were assigned to a 1-hour training with either iVR or a cadaveric laboratory session with shoulder specimens. Before training, all participants viewed an overview lecture and technique video demonstrating key steps of augmented baseplate implantation for rTSA. Participants were assessed by a blinded evaluator using validated competency checklists during cadaveric glenoid baseplate implantation. Continuous and categorial variables were analyzed using the 2-sample t test and Fisher exact test. Results: Fourteen junior residents (3 incoming matched postgraduate year [PGY1], 6 PGY1s, 1 PGY2, and 4 PGY3s) were randomized to training with either iVR (n = 6) or cadaver laboratory (n = 8). There were no significant differences in demographic data, previous experience with rTSA, or previous use of iVR (p > 0.05). There were no significant difference in total Objective Structured Assessment of Technical Skill score (91.2% [15.2] vs. 93.25% [6.32], -0.1406 to 0.1823, p = 0.763), Global Rating Scale score (4.708 [0.459] vs. 4.609 [0.465], -0.647 to 0.450, p = 0.699), or time to completion (546 seconds [158] vs. 591 seconds [192], -176.3 to 266.8, p = 0.655) in cadaveric glenoid baseplate implantation. Average cost of iVR hardware and a 1-year software license was $4,900, and average cost of a single cadaver laboratory was $1,268.20 per resident. Conclusions: Among junior orthopaedic residents, there is similar skill acquisition when training with either cadaver laboratory or iVR. Although additional research into this field is needed, iVR may provide an important and cost-effective tool in surgical education. Clinical Relevance: Emerging simulation and iVR technology simulation in surgical training programs can increase access to effective and high-level surgical training across the globe and improve quality of care.

Determining the True Incidence of Glenohumeral Instability Among Players in the National Football League: An Epidemiological Study of Non-Missed Time Shoulder Instability Injuries.

Background: Shoulder instability encompasses a spectrum of glenohumeral pathology ranging from subluxation to dislocation. While dislocation frequently leads to removal from play, athletes are often able to play through subluxation. Previous research on glenohumeral instability among athletes has largely focused on missed-time injuries, which has likely disproportionately excluded subluxation injuries and underestimated the overall incidence of shoulder instability. Purpose: To describe the epidemiology of shoulder instability injuries resulting in no missed time beyond the date of injury (non-missed time injuries) among athletes in the National Football League (NFL). Study Design: Descriptive epidemiology study. Methods: The NFL's electronic medical record was retrospectively reviewed to identify non-missed time shoulder instability injuries during the 2015 through 2019 seasons. For each injury, player age, player position, shoulder laterality, instability type, instability direction, injury timing, injury setting, and injury mechanism were recorded. For injuries that occurred during games, incidence rates were calculated based on time during the season as well as player position. The influence of player position on instability direction was also investigated. Results: Of the 546 shoulder instability injuries documented during the study period, 162 were non-missed time injuries. The majority of non-missed time injuries were subluxations (97.4%), occurred during games (70.7%), and resulted from a contact mechanism (91.2%). The overall incidence rate of game-related instability was 1.6 injuries per 100,000 player-plays and was highest during the postseason (3.5 per 100,000 player-plays). The greatest proportion of non-missed time injuries occurred in defensive secondary players (28.4%) and offensive linemen (19.8%), while kickers/punters and defensive secondary players had the highest game incidence rates (5.5 and 2.1 per 100,000 player-plays, respectively). In terms of direction, 54.3% of instability events were posterior, 31.9% anterior, 8.5% multidirectional, and 5.3% inferior. Instability events were most often anterior among linebackers and wide receivers (50% and 100%, respectively), while posterior instability was most common in defensive linemen (66.7%), defensive secondary players (58.6%), quarterbacks (100.0%), running backs (55.6%), and tight ends (75.0%). Conclusion: The majority of non-missed time shoulder instability injuries (97.4%) were subluxations, which were likely excluded from or underreported in previous shoulder instability studies due to the inherent difficulty of detecting and diagnosing shoulder subluxation.

Effects of Malpositioning of the Knee on Radiographic Measurements: The Influence of Adduction, Abduction, and Malrotation on Measured Tibial Slope.

Background: Increased posterior tibial slope (PTS) is a risk factor for knee pathology. Accurate measurement of PTS is predicated on a quality lateral knee radiograph; however, little is known about how the quality of the radiograph affects the measured PTS. Purposes: To (1) describe a method for measuring malalignment on lateral knee radiographs, (2) assess the effects of malpositioning of the knee on radiographic measures of malalignment, and (3) determine any correlations between malalignment and the measured PTS. Study Design: Descriptive laboratory study. Methods: Using a setup similar to that of a standard radiology suite, 25 sets of radiographs were taken using 5 sawbone models. Each set included a true lateral view and separate malpositioned radiographs at 5°, 10°, and 15° of adduction, abduction, internal rotation, and external rotation. Malalignment for each radiograph was quantified as the anterior-posterior distance (APD) and proximal-distal distance (PDD) between femoral condyles. The medial PTS was measured in duplicate, and the interrater reliability was calculated. Results: The interrater reliability was excellent, with intraclass correlation coefficients of 0.92, 0.91, and 0.96 for the APD, PDD, and PTS, respectively. Malrotation significantly affected the APD (P < .001), with a mean change of 5.6 mm per 5°. Malpositioning in abduction/adduction significantly affected the PDD (P < .001), with a mean change of 5.1 mm per 5°. There was no significant impact of rotation or APD on the PTS. Abduction/adduction did affect the PTS (P < .001) above a threshold of 5° of malpositioning. The PTS decreased as the PDD increased, moving from adduction to abduction (R2 = 0.5687). Conclusion: The measured PTS was more sensitive to malpositioning by abduction/adduction than by malrotation. Malrotation affected the APD, while abduction/adduction affected the PDD. Thus, the accuracy of the measured PTS was compromised more by poorly aligned distal femoral condyles than it was by poorly aligned posterior femoral condyles. Clinical Relevance: To minimize the effects of malpositioning, we recommend utilizing radiographs with a |PDD| of <5 mm and an |APD| of <15 mm when measuring the PTS.

Clinical Outcomes Following Percutaneous Ankle Fusion With Bone Graft Substitute.

Background: Percutaneous ankle fusion is an emerging technique with minimal published outcome data. The goal of the present study is to retrospectively review clinical and radiographic outcomes following percutaneous ankle fusion and provide technique tips to perform percutaneous ankle fusion. Methods: Patients >18 years of age, treated by a single surgeon, from February 2018 to June 2021, who underwent primary isolated percutaneous ankle fusion supplemented with platelet-derived growth factor B (rhPDGF-BB) and beta-tricalcium phosphate, with at least 1-year follow-up were included. Surgical technique consisted of percutaneous ankle preparation followed by fixation with 3 headless compression screws. Pre- and postoperative visual analog scale (VAS) and Foot Function Index (FFI) were compared using paired t tests. Fusion was assessed radiographically by the surgeon on postoperative radiographs and computed tomography (CT) at 3 months postoperatively. Results: Twenty-seven consecutive adult patients were included in the study. Mean follow-up was 21 months. Mean age was 59.8 years. Mean preoperative and postoperative VAS scores were 7.4 and 0.2, respectively (P < .01). Mean preoperative FFI pain domain, disability domain, activity restriction domain, and total score were 20.9, 16.7, 18.5, and 56.4, respectively. Mean postoperative FFI pain domain, disability domain, activity restriction domain, and total score were 4.3, 4.7, 6.7, and 15.8, respectively (P < .01). Fusion was achieved in 26 of 27 patients (96.3%) at 3 months. Four patients (14.8%) had complications. Conclusion: We found in this cohort with surgery performed by a surgeon highly experienced in minimally invasive surgery that percutaneous ankle fusion augmented with a bone graft supplement achieved a high rate of fusion (96.3%) and a significant improvement in pain and function postoperatively while associated with minimal complications. Level of Evidence: Level IV, case series.

Revision Lateral Ankle Reconstruction 40 Years After Chrisman-Snook Procedure: A Case Report.

CASE: A 70-year-old active woman presented with lateral ankle instability 40 years after a lateral ankle reconstruction procedure. Examination demonstrated gross instability, and advanced imaging revealed attenuation of her previous graft. She underwent anatomic reconstruction through a modified Brostrom-Gould technique and was able to return to hiking without pain. CONCLUSION: Recurrent lateral ankle instability after reconstruction represents a unique challenge for orthopaedic surgeons. Utilization of a modified Brostrom-Gould procedure with suture tape augmentation is a promising alternative to allograft or autograft reconstruction for patients with active lifestyle goals in the context of recurrent instability.

Using machine learning methods to predict nonhome discharge after elective total shoulder arthroplasty.

BACKGROUND: Machine learning has shown potential in accurately predicting outcomes after orthopedic surgery, thereby allowing for improved patient selection, risk stratification, and preoperative planning. This study sought to develop machine learning models to predict nonhome discharge after total shoulder arthroplasty (TSA). METHODS: The American College of Surgeons National Surgical Quality Improvement Program database was queried for patients who underwent elective TSA from 2012 to 2018. Boosted decision tree and artificial neural networks (ANN) machine learning models were developed to predict non-home discharge and 30-day postoperative complications. Model performance was measured using the area under the receiver operating characteristic curve (AUC) and overall accuracy (%). Multivariate binary logistic regression analyses were used to identify variables that were significantly associated with the predicted outcomes. RESULTS: There were 21,544 elective TSA cases identified in the National Surgical Quality Improvement Program registry from 2012 to 2018 that met inclusion criteria. Multivariate logistic regression identified several variables associated with increased risk of nonhome discharge including female sex (odds ratio [OR] = 2.83; 95% confidence interval [CI] = 2.53-3.17; P < .001), age older than 70 years (OR = 3.19; 95% CI = 2.86-3.57; P < .001), American Society of Anesthesiologists classification 3 or greater (OR = 2.70; 95% CI = 2.41-2.03; P < .001), prolonged operative time (OR = 1.38; 95% CI = 1.20-1.58; P < .001), as well as history of diabetes (OR = 1.56; 95% CI = 1.38-1.75; P < .001), chronic obstructive pulmonary disease (OR = 1.71; 95% CI = 1.46-2.01; P < .001), congestive heart failure (OR = 2.65; 95% CI = 1.72-4.01; P < .001), hypertension (OR = 1.35; 95% CI = 1.20-1.52; P = .004), dialysis (OR = 3.58; 95% CI = 2.01-6.39; P = .002), wound infection (OR = 5.67; 95% CI = 3.46-9.29; P < .001), steroid use (OR = 1.43; 95% CI = 1.18-1.74; P = .010), and bleeding disorder (OR = 1.84; 95% CI = 1.45-2.34; P < .001). The boosted decision tree model for predicting nonhome discharge had an AUC of 0.788 and an overall accuracy of 90.3%. The ANN model for predicting nonhome discharge had an AUC of 0.851 and an overall accuracy of 89.9%. For predicting the occurrence of 1 or more postoperative complications, the boosted decision tree model had an AUC of 0.795 and an overall accuracy of 95.5%. The ANN model yielded an AUC of 0.788 and an overall accuracy of 92.5%. CONCLUSIONS: Both the boosted decision tree and ANN models performed well in predicting nonhome discharge with similar overall accuracy, but the ANN had higher discriminative ability. Based on the findings of this study, machine learning has the potential to accurately predict nonhome discharge after elective TSA. Surgeons can use such tools to guide patient expectations and to improve preoperative discharge planning, with the ultimate goal of decreasing hospital length of stay and improving cost-efficiency.

Performance in Collegiate-Level Baseball Players After Elbow Ulnar Collateral Ligament Reconstruction.

BACKGROUND: The increase in ulnar collateral ligament (UCL) elbow reconstructions over the past 20 years has affected younger athletes more than any other age group. Although return to play and postoperative performance have been extensively studied in professional baseball players, outcomes in collegiate baseball players are less known. PURPOSE/HYPOTHESIS: The purpose of this study was to characterize return to play and changes in performance after UCL reconstruction (UCLR) in collegiate baseball players. We hypothesized that collegiate baseball players would have similar return-to-play rates compared with professional athletes and no significant differences in performance compared with matched controls. STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: Collegiate athletes undergoing UCLR by a single surgeon were identified. Postoperatively, individual collegiate career paths were analyzed through use of publicly available data from team websites, injury reports, and press releases. Data obtained included time to return to competition, number of collegiate seasons played after surgery, total games started and played, seasonal wins, losses, saves, innings played, hits, earned run average (ERA), home runs, shutouts, strikeouts, walks, and walks plus hit per inning pitched (WHIP). The UCLR group was compared with a matched control group of collegiate pitchers without elbow injury. RESULTS: Of the 58 collegiate baseball players analyzed (mean ± SD age, 19.95 ± 1.19 years), 84.5% returned to play at the collegiate level. Players returned to competition at 16.98 ± 6.16 months postoperatively and competed for 1.60 ± 0.84 seasons postoperatively. In terms of career longevity, 81.0% of collegiate pitchers either completed their collegiate eligibility or remained on active rosters, and 2 players (4.1%) ultimately played at the professional level after UCLR. Compared with a matched cohort, the UCLR group had no significant differences in collegiate pitching performance statistics after surgery. CONCLUSION: College baseball players returned to play at a rate comparable with the rate published in prior literature on professional pitchers and often completed their collegiate playing eligibility postoperatively. Compared with controls, the UCLR group had no statistically significant differences in pitching performance postoperatively. Further studies are needed to determine the exact reasons why college players retire despite having endured extensive surgical and postoperative rehabilitation processes related to UCLR. Younger populations are experiencing elbow injuries at an increasing rate secondary to increased workloads at the amateur level. As these athletes matriculate into the collegiate ranks, they are at continued risk of sustaining UCL injury, and little explicit information is available on their prospects of return to play and career longevity after UCLR.

Exercise as a Treatment for Schizophrenia: A Review.

Schizophrenia is a mental disorder that is characterized by progressive cognitive impairment in areas of attention, working memory, and executive functioning. Although no clear etiology of schizophrenia has been discovered, many factors have been identified that contribute to the development of the disease, such as neurotransmitter alterations, decreased synaptic plasticity, and diminished hippocampal volume. Historically, antipsychotic medications have targeted biochemical alterations in the brains of patients with schizophrenia but have been ineffective in alleviating cognitive and hippocampal deficits. Other modalities, such as exercise therapy, have been proposed as adjuvant or primary therapy options. Exercise therapy has been shown to improve positive and negative symptoms, quality of life, cognition, and hippocampal plasticity, and to increase hippocampal volume in the brains of patients with schizophrenia. This article will briefly review the clinical signs, symptoms and proposed etiologies of schizophrenia, and describe the current understanding of exercise programs as an effective treatment in patients with the disease.

Early Sports Specialization Is Associated With Upper Extremity Injuries in Throwers and Fewer Games Played in Major League Baseball.

BACKGROUND: Single-sport athletes who specialize in baseball at a young age may have a greater predisposition to overuse injury, burnout, and decreased career longevity when compared with multiple-sport athletes. The effect of sport specialization has not been studied in professional baseball players. HYPOTHESIS: Major League Baseball (MLB) players who played multiple sports in high school would experience fewer injuries, spend less time on the disabled list, play more games, and have a longer career than athletes who played only baseball in high school. STUDY DESIGN: Descriptive epidemiology study. METHODS: First- and second-round MLB draft picks from 2008 to 2016 who played in at least 1 professional game were included in this study. Athletes who participated in 1 or more sports in addition to baseball during high school were considered multisport athletes, and athletes who participated in only baseball were considered single-sport athletes. For each athlete, participation in high school sports, injuries sustained in MLB and Minor League Baseball, number of days on the disabled list for each injury, number of games played in both leagues, and whether the athlete was still active were collected from publicly available records. RESULTS: A total of 746 athletes were included in this study: 240 (32%) multisport and 506 (68%) single sport. Multisport athletes played in significantly more mean total games (362.8 vs 300.8; P < .01) as well as more mean MLB games (95.9 vs 71.6; P = .04) than single-sport athletes. There was no difference in the mean number of seasons played in the major leagues (1.8 vs 1.6; P = .15) or minor league (5.25 vs 5.20; P = .23) between multisport and single-sport athletes. Single-sport athletes had a significantly higher prevalence of upper extremity injuries compared with multisport athletes (136 [63%] vs 55 [50%]; P = .009). Single-sport pitchers also had a higher prevalence of shoulder and elbow injuries (86 vs 27; P = .008) and were more likely to have recurrent elbow injuries (33% vs 17% recurrence; P = .002) compared with multisport pitchers. CONCLUSION: Professional baseball players who participated in multiple sports in high school played in more major league games and experienced lower rates of upper and lower extremity injuries than players who played only baseball in high school.

Role of social media and the Internet in pathways to care for adolescents and young adults with psychotic disorders and non-psychotic mood disorders.

AIMS: Although psychosis often occurs during adolescence, there has been little research on how the ubiquitously used Internet and social media could impact pathways to care. We examined how youth with psychotic spectrum disorders (PSD) versus non-psychotic mood disorders (NPMD) use online resources in the early illness stages. METHODS: Social media use and pathways to care data were collected using a semi-structured interview from 80 youth (PSD = 40 and NPMD = 40) aged 12-21 years within 2 years of symptom onset. RESULTS: A total of 97.5% of participants (mean age = 18.3 years) regularly used social media, spending approximately 2.6 ± 2.5 h per day online. There were 22.4% of our sample (PSD = 19.4%, NPMD = 25.0%, P = 0.56) who reported waiting to reach out for help believing that symptoms would disappear. A total of 76.5% (PSD = 67.5%, NPMD = 85.0%, P = 0.06) noticed social media habit changes during symptom emergence. Thirty per cent reported discussing their symptoms on social media (PSD = 22.5%, NPMD = 37.5%, P = 0.14). NPMD patients sought information most on how to stop symptoms (40.0% vs. 13.5%, P = 0.01), while PSD youth were more commonly interested in what caused their symptoms (21.6% vs. 15.0%, P = 0.45). More PSD patients (42.9% vs. 25.0%, P = 0.10) would prefer to receive mental health information via the Internet. Altogether, 63.6% (PSD = 64.9%, NPMD = 62.5%, P = 0.83) were amenable to clinicians proactively approaching them via social media during symptom emergence. A total of 74.3% (PSD = 78.4%, NPMD = 70.0%, P = 0.40) liked the idea of obtaining help/advice from professionals via social media. CONCLUSIONS: The Internet and social media provide an unparalleled opportunity to supplement and potentially transform early intervention services, and acceptance of this approach appears to be high.