Eating behaviours, menstrual history and the athletic career: a retrospective survey from adolescence to adulthood in female endurance athletes.

Aim: To evaluate differences in menstrual and pubertal history and trends in eating behaviours among women with and without a competitive sports background. Additionally, we investigated if menstrual history and eating behaviours are associated with sports career-related factors. Methods: This retrospective study was conducted on 100 women with a competitive endurance sports background and their age-matched, gender-matched and municipality-matched controls (n=98). Data were collected using a questionnaire using previously validated instruments. Generalised estimating equations were used to calculate associations of menstrual history and eating behaviours with outcome variables (career length, participation level, injury-related harms and career termination due to injury). Results: Athletes reported higher rates of delayed puberty and menstrual dysfunction than controls. No differences between the groups were observed in the Eating Disorder Examination Questionnaire short form (EDE-QS) scores at any age. Previous disordered eating (DE) was associated with current DE in both groups. Among athletes, higher EDE-QS scores during the sports career were associated with a shorter career (B=-0.15, 95% CI -0.26 to -0.05). Secondary amenorrhoea was associated with lower participation level (OR 0.51, 95% CI 0.27 to 0.95), injury-related harms during the career (OR 4.00, 95% CI 1.88 to 8.48) and career termination due to injury (OR 1.89, 95% CI 1.02 to 3.51). Conclusion: The findings indicate that DE behaviours and menstrual dysfunction, specifically secondary amenorrhoea, have a disadvantageous relationship with a sports career in women competing in endurance sports. DE during the sports career is associated with DE after the career.

Markerless 2D kinematic analysis of underwater running: A deep learning approach.

Kinematic analysis is often performed with a camera system combined with reflective markers placed over bony landmarks. This method is restrictive (and often expensive), and limits the ability to perform analyses outside of the lab. In the present study, we used a markerless deep learning-based method to perform 2D kinematic analysis of deep water running, a task that poses several challenges to image processing methods. A single GoPro camera recorded sagittal plane lower limb motion. A deep neural network was trained using data from 17 individuals, and then used to predict the locations of markers that approximated joint centres. We found that 300-400 labelled images were sufficient to train the network to be able to position joint markers with an accuracy similar to that of a human labeler (mean difference < 3 pixels, around 1 cm). This level of accuracy is sufficient for many 2D applications, such as sports biomechanics, coaching/training, and rehabilitation. The method was sensitive enough to differentiate between closely-spaced running cadences (45-85 strides per minute in increments of 5). We also found high test-retest reliability of mean stride data, with between-session correlation coefficients of 0.90-0.97. Our approach represents a low-cost, adaptable solution for kinematic analysis, and could easily be modified for use in other movements and settings. Using additional cameras, this approach could also be used to perform 3D analyses. The method presented here may have broad applications in different fields, for example by enabling markerless motion analysis to be performed during rehabilitation, training or even competition environments.