Adding confidence to our injury burden estimates: is bootstrapping the solution?

Williams, Sean; Shaw, Joseph W; Emery, Carolyn; Stokes, Keith A

doi:10.1136/bjsports-2023-107496

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 1 Incidence is reported as number of non-contact muscle injuries/1000 player hours of exposure (95% CI) 2 Data are reported as mean (± SD) 3 Injury burden = number of days lost/1000 hours of exposure (95% CI) [ 24 ] …”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Epidemiology of Non-Contact Muscle Injuries in the Italian Male Elite Under-19 Football (Soccer) Championship

Magistrali,

Stefanini,

Abate

et al. 2024

Sports Med - Open

View full text Add to dashboard Cite

Background While extensive research exists on muscle injuries among adult football players, a notable gap persists in studies concerning younger footballers. The aim of the current study is to provide epidemiological data on the characteristics of time-loss muscle injuries in young football players participating in the Italian Under-19 male elite Championship (“Primavera 1”). Results Conducted as a multicentre, prospective, observational cohort study, this research gathered injury data from the 2022-23 season across 14 of the 18 Clubs in the first Italian Under-19 championship. The cohort comprised 391 players with a mean age (± standard deviation) of 18.0 ± 0.4 years. A total of 479 injuries were reported, resulting in 14,231 days of activity lost. Of these, muscle injuries were 209 (44%), accounting for 4,519 (32%) days lost. Overall muscle injuries incidence was 1.82/1000 hours, with a mean injury burden of 39.4 days lost/1000 hours. Almost all muscle injuries (206 out of 209: 98.5%) occurred in hamstrings, quadriceps, adductors, calf and iliopsoas. Hamstrings injuries were the most burdensome (18.8 days lost/1000 hours) accounting for nearly half of all days lost due to muscle injuries. Incidence and burden of adductors injuries (0.25 injuries and 4.1 days lost/1000 hours, respectively) were found to be comparable to calf injuries (0.24 injuries and 4.7 days lost/1000 hours, respectively). Iliopsoas injuries accounted for a noteworthy portion of the total, with an injury incidence of 0.16/1000 hours and a burden of 3.3 days lost/1000 hours. Injuries with myo-tendinous or myo-aponeurotic involvement demonstrated delayed return-to-football compared to those without such involvement (35.6 vs. 18.5 days, p < 0.0001). Conclusions The study highlighted a peculiar distribution of non-contact muscle injuries among elite young football players. While hamstring injuries were confirmed as the most burdensome, incidence and burden of adductors and calf injuries were found to be similar. A significant incidence and burden of iliopsoas injuries were observed. These findings suggest potential implementations for targeted injury prevention strategies in the Italian male elite Under-19 football Championship.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Data were reported as means and standard deviation (SD) or 95% confidence interval (CI), as indicated [ 9 ]. The 95% CI for injury burden was computed via bootstrapping [ 24 ], with results based on 1000 bootstrap samples. The independent sample t-test was adopted for comparisons between different subgroups.…”

Section: Methodsmentioning

confidence: 99%

Epidemiology of Non-Contact Muscle Injuries in the Italian Male Elite Under-19 Football (Soccer) Championship

Magistrali,

Stefanini,

Abate

et al. 2024

Sports Med - Open

View full text Add to dashboard Cite

show abstract

Identifying stigmatizing and positive/preferred language in obstetric clinical notes using natural language processing

Scroggins,

Hulchafo,

Harkins

et al. 2024

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

Objective To identify stigmatizing language in obstetric clinical notes using natural language processing (NLP). Materials and Methods We analyzed electronic health records from birth admissions in the Northeast United States in 2017. We annotated 1771 clinical notes to generate the initial gold standard dataset. Annotators labeled for exemplars of 5 stigmatizing and 1 positive/preferred language categories. We used a semantic similarity-based search approach to expand the initial dataset by adding additional exemplars, composing an enhanced dataset. We employed traditional classifiers (Support Vector Machine, Decision Trees, and Random Forest) and a transformer-based model, ClinicalBERT (Bidirectional Encoder Representations from Transformers) and BERT base. Models were trained and validated on initial and enhanced datasets and were tested on enhanced testing dataset. Results In the initial dataset, we annotated 963 exemplars as stigmatizing or positive/preferred. The most frequently identified category was marginalized language/identities (n = 397, 41%), and the least frequent was questioning patient credibility (n = 51, 5%). After employing a semantic similarity-based search approach, 502 additional exemplars were added, increasing the number of low-frequency categories. All NLP models also showed improved performance, with Decision Trees demonstrating the greatest improvement (21%). ClinicalBERT outperformed other models, with the highest average F1-score of 0.78. Discussion Clinical BERT seems to most effectively capture the nuanced and context-dependent stigmatizing language found in obstetric clinical notes, demonstrating its potential clinical applications for real-time monitoring and alerts to prevent usages of stigmatizing language use and reduce healthcare bias. Future research should explore stigmatizing language in diverse geographic locations and clinical settings to further contribute to high-quality and equitable perinatal care. Conclusion ClinicalBERT effectively captures the nuanced stigmatizing language in obstetric clinical notes. Our semantic similarity-based search approach to rapidly extract additional exemplars enhanced the performances while reducing the need for labor-intensive annotation.

show abstract

Injury incidence and prevalence in elite short-course triathletes: a 4-year prospective study

Crunkhorn,

Toohey,

Charlton

et al. 2024

Br J Sports Med

View full text Add to dashboard Cite

ObjectiveTo characterise the prevalence, incidence rate (IR) and burden of injuries in elite short-course triathletes over a 4-year training and competition period.MethodsFifty elite Australian triathletes were prospectively monitored for injury during four consecutive seasons (2018–2021). Injuries requiring medical attention were prospectively recorded and further subcategorised according to time loss. The IR and burden (injury IR×mean injury severity) were calculated per 365 athlete days, with sex differences in IR compared using IR ratios (IRR) from negative binomial regression models.ResultsTwo hundred and sixty-six injuries were reported in 46 (92.0%) athletes, of which 67.3% resulted in time loss. The injury IR was 1.87 injuries per 365 athlete days (95% CI 1.70 to 2.80), and comparable between sexes (IRR 0.82, 95% CI 0.64 to 1.04, p=0.109). Most injuries (70.7%) were training related. The most frequently injured body sites were the ankle (15.8%), foot (12.4%) and lower leg (12.0%). Bone stress injuries (BSIs) were the most burdensome injury type with 31.38 days of time loss per 365 days (95% CI 24.42 to 38.34). Twenty athletes (40.0%) reported at least one bone stress injury (BSI) (range 0–3). The rate of BSIs in female athletes was three times greater compared with male athletes (IRR 2.99, 95% CI 1.26 to 7.07, p=0.013).ConclusionTwo-thirds of injuries reported in elite short-course triathletes resulted in time loss, with the majority occurring during training activities. Foot, ankle and other lower leg injuries had the highest incidence, with BSIs carrying the highest injury burden. The considerably higher rate of BSI observed in female athletes warrants consideration for future prevention strategies in female triathletes.

show abstract

Adding confidence to our injury burden estimates: is bootstrapping the solution?

Cited by 6 publications

References 10 publications

Epidemiology of Non-Contact Muscle Injuries in the Italian Male Elite Under-19 Football (Soccer) Championship

Epidemiology of Non-Contact Muscle Injuries in the Italian Male Elite Under-19 Football (Soccer) Championship

Identifying stigmatizing and positive/preferred language in obstetric clinical notes using natural language processing

Injury incidence and prevalence in elite short-course triathletes: a 4-year prospective study

Contact Info

Product

Resources

About