Predicting Severity of Head Collision Events in Elite Soccer Using Preinjury Data: A Machine Learning Approach.

OBJECTIVE: To develop machine learning (ML) models that predict severity of head collision events (HCEs) based on preinjury variables and to investigate which variables are important to predicting severity. DESIGN: Data on HCEs were collected with respect to severity and 23 preinjury variables to create 2 datasets, a male dataset using men's tournaments and mixed dataset using men's and women's tournaments, to perform ML analysis. Machine learning analysis used a random forest classifier based on preinjury variables to predict HCE severity. SETTING: Four elite international soccer tournaments. PARTICIPANTS: Elite athletes participating in analyzed tournaments. INDEPENDENT VARIABLES: The 23 preinjury variables collected for each HCE. MAIN OUTCOME MEASURES: Predictive ability of the ML models and association of important variables. RESULTS: The ML models had an average area under the receiver operating characteristic curve for predicting HCE severity of 0.73 and 0.70 for the male and mixed datasets, respectively. The most important variables for prediction were the mechanism of injury and the event before injury. In the male dataset, the mechanisms "head-to-head" and "knee-to-head" were together significantly associated ( P = 0.0244) with severity; they were not significant in the mixed dataset ( P = 0.1113). In both datasets, the events "corner kicks" and "throw-ins" were together significantly associated with severity (male, P = 0.0001; mixed, P = 0.0004). CONCLUSIONS: ML models accurately predicted the severity of HCE. The mechanism and event preceding injury were most important for predicting severity of HCEs. These findings support the use of ML to inform preventative measures that will mitigate the impact of these preinjury factors on player health.

Transforming the "SEAD": Evaluation of a Virtual Surgical Exploration and Discovery Program and its Effects on Career Decision-Making.

OBJECTIVE: The abrupt cessation of in-person education due to the COVID-19 pandemic has made it difficult for preclerkship students to explore a career in surgery. To supplement the lack of exposure, the Surgical Exploration and Discovery (SEAD) program was transitioned to an entirely virtual format. This study aims to describe the virtual SEAD program and evaluate its effectiveness as a career decision-making (CDM) intervention. DESIGN: The week-long program was delivered on Microsoft Teams, featured 11 surgical specialties, and comprised four activities: live demonstrations, virtual operating room observerships, career talks, and technical skills workshops. The program was evaluated using the four levels of the Kirkpatrick model: (1) reactions, (2) knowledge, (3) CDM behaviors - assessed using the Career Decision-making Difficulties Questionnaire (CDDQ) - and (4) results. The latter was indirectly assessed using CDDQ scores from an in-person SEAD program, where lower CDDQ scores indicate less difficulty with CDM. SETTING: Faculty of Medicine at the University of Ottawa in Ontario, Canada. PARTICIPANTS: Forty pre-clerkship students (27 first and 13 second year students) at the University of Ottawa RESULTS: Level 1: 97.5% of participants rated the program as good or very good. Live demonstration and technical skills workshops were the highest rated activities. Level 2: participants' scores on knowledge-based questions about a surgical career significantly increased following the program (pre: 9/25 vs post: 15/25, p = 0.008). Level 3: overall mean CDDQ scores (±SD) decreased difficulties with significantly following the program (pre: 45.6 ± 10.5 vs post: 38.8 ± 10.9, p < 0.001), which indicates decreased CDM difficulties. Level 4: Except for one sub-category, the difference in mean CDDQ scores between the virtual and in-person programs were not significantly different. CONCLUSION: The program received the positive reactions and significantly increased participants' knowledge. The change in CDDQ scores following the virtual program suggests it may reduce career decision-making difficulties in the short-term. In-person surgical exposure remains important; however, a hybrid model may be valuable in resource limited settings. WC: 300.

Effect of a new concussion substitute rule on medical assessment of head collision events in Premier League football.

OBJECTIVE: To investigate the utilisation of additional permanent concussion substitutes (APCSs) and its efficacy with regards to rate and duration of medical assessment of head collision events (HCEs) in the 2020-2021 Premier League season. The present APCS rule allows players with a suspected concussion to be removed from a match without counting towards a team's allocated substitutions. METHODS: Eighty Premier League matches, 40 prior to additional permanent concussion substitutes implementation (Pre-APCS) and 40 after (Post-APCS), were randomly selected and analysed by a team of trained reviewers for HCEs. Data on HCE incidence, rates of medical assessment, duration of medical assessment and return to play were collected for each match. Data for the Pre-APCS and Post-APCS groups were compared to analyse differences in assessment of HCEs. RESULTS: During the 2020-2021 Premier League season, three APCSs were used. There were 38 HCEs identified in the Pre-APCS group (0.95 per match, 28.79 per 1000 athlete-hours of exposure) and 42 in the Post-APCS group (1.05 per match, 31.82 per 1000 athlete-hours of exposure). Incidence of HCEs (p=0.657), rates of medical assessment (23.7% Pre-APCS vs 21.4% Post-APCS; p=0.545) and duration of medical assessment (median 81 s Pre-APCS vs 102 s Post-APCS; p=0.466) did not significantly differ between the two groups. CONCLUSIONS: The implementation of APCSs in the Premier League did not impact the rate or duration of medical assessement of HCEs. Despite the introduction of APCSs, the consensus protocols for HCE assessment were rarely followed. We recommend changes to APCS and its implementation that would be aimed at protecting player health.

Screening for alcohol and substance use in pediatric trauma patients: A retrospective review.

PURPOSE: Alcohol and drug use in adolescence is associated with traumatic injuries. This study aimed to assess the rates of screening for substance use in pediatric trauma patients presenting at a single Canadian center. METHODS: A retrospective chart review of pediatric trauma patients (aged 12-17) was performed. Injury specifics, rates of patients screened for alcohol and/or substance use, and screening outcomes were determined. Patients screened were compared to those not screened. Continuous variables were analyzed using independent samples t-tests and categorical using chi-square. Significance was set at p < 0.05. RESULTS: Three hundred twenty-seven patients were included, with 217(66%) being male. The average age was 14.6 years (±1.5). Traffic collisions accounted for 50% of injuries. A blood alcohol test was conducted for significantly more patients (199, 61%) than a urine drug screen (55, 17%; p < 0.001). Of those screened, 27/199(14%) tested positive for alcohol and 29/55(53%) for drugs. Older age and increased injury severity were associated with being screened for drugs (p = 0.000, p = 0.050). Only 39% of patients with positive screening tests were referred on to secondary services such as inpatient psychiatry or social work. CONCLUSION: Screening rates remain low. Institutional guidelines for alcohol and drug screening in trauma patients should be instituted to avoid random screening and underestimations of substance involvement. TYPE OF STUDY: Retrospective Chart Review. LEVEL OF EVIDENCE: III.

Professional assessment of potential concussions in elite football tournaments.

BACKGROUND: Potential concussive events (PCEs) are a major health concern in football. Though there are protocols set in place for assessments of PCEs, there has been no evidence of adherence in major football tournaments. METHODS: Our research goal is to determine if PCEs in elite football are professionally assessed according to the International Conference on Concussion in Sport (ICCS) consensus statement recommendations. Identification and analysis of PCEs in the 2018 World Cup (WC) were accomplished through standardised observation of video footage by trained observers. Results were contrasted with data from the 2014 WC and 2016 Euro Cup. Our primary outcomes include frequency and professional assessment of PCEs, signs of concussions and time stopped for assessments. FINDINGS: In the 64 games of the 2018 WC, 87 PCEs (1.36 per game) were identified. Thirty-one (35.6%) PCEs were professionally assessed, resulting in the removal of three (3.5%) players from the match. Six (6.9%) PCEs showed one sign of concussion, 60 (69.0%) showed two signs, 20 (23.0%) showed three signs and 1 (1.2%) showed four or more signs. The mean time stopped for assessment was 63.3 s. No significant change in the percentage of professional assessments (mean=33.4%, 95% CI 20.7% to 46.1%) were identified across tournaments (p=0.42). INTERPRETATION: These findings demonstrate a need for adherence to concussion protocols in order to improve the brain-health of athletes. Proper enforcement of the ICCS protocols during these tournaments and promoting player health and safety can influence the officiating, coaching and playing of football worldwide by promoting player safety.

Characteristics of potential concussive events in three elite football tournaments.

OBJECTIVE: Identify patterns in the nature and characteristics of potential concussive events (PCEs) in football. METHODS: This study analysed the incidence and characteristics of PCEs that occurred during the 2014 and 2018 Fédération Internationale de Football Association World Cups, and the 2016 UEFA Euro Cup. PCEs were defined as direct head collision incidents resulting in the athlete being unable to immediately resume play for at least 5 sec following impact. RESULTS: A total of 218 incidents were identified in 179 matches (1.22 per match, 36.91 per 1000 hours of exposure). The most common mechanism of PCE was elbow-to-head (28.7%, n=68). The frontal region was the most frequently affected location of impact with 22.8% (n=54). CONCLUSION: Our study defined the identification, prevalence and nature of PCEs in professional international soccer tournaments. Our findings indicate the different contexts and mechanisms of head contact and contact to different regions of the head can be associated with varying signs of concussion. The results highlight targets for future injury prevention strategies.

Medical assessment of potential concussion in elite football: video analysis of the 2016 UEFA European championship.

OBJECTIVE: The objective is to determine if suspected concussions in elite football are medically assessed according to the International Conferences on Concussion in Sport consensus statement recommendations. SETTING: Men's Union of European Football Association (UEFA) Football Championship. PARTICIPANTS: All professional football players in the UEFA 2016 Championship Tournament. DESIGN: Observational study. OUTCOME MEASURES: Potential concussive events (PCEs) were defined as direct head collision incidents resulting in the athlete being unable to immediately resume play following impact. PCEs identified and description of PCE assessment and outcome were accomplished through direct standardised observation of video footage by trained observers in 51 games played in the Men's UEFA European Championship (10 June-10 July 2016). RESULTS: Sixty-nine total PCEs (1.35 per match) were identified in 51 games played during the 2016 Men's UEFA European Championship. Forty-eight PCEs (69.6%) resulted in two observable signs of concussion, 13 (18.8%) resulted in three signs and 1 (1.4%) resulted in four signs in the injured athletes. Nineteen (27.5%) PCEs were medically assessed by sideline healthcare personnel while 50 (72.5%) were not. Of the 50 PCEs that were not medically assessed, 44 (88%) PCEs resulted in two or more signs of concussion among injured athletes. Of the 19 medically assessed PCEs, 8 resulted in 3 signs of concussion, and 1 resulted in 4 signs; all assessments concluded in the same-game return for the injured athletes. CONCLUSIONS: PCEs were frequent events in the 2016 UEFA Euro championship, but were rarely assessed concordant with the International Conferences on Concussion in Sport consensus statement recommendations. There is an imperative need to improve the assessment and management of players suspected of concussion in elite football.