Background: Accurate and detailed measurement of a dancer's training volume is a key requirement to understanding the relationship between a dancer's pain and training volume. Currently, no system capable of quantifying a dancer's training volume, with respect to specific movement activities, exists. The application of machine learning models to wearable sensor data for human activity recognition in sport has previously been applied to cricket, tennis and rugby. Thus, the purpose of this study was to develop a human activity recognition system using wearable sensor data to accurately identify key ballet movements (jumping and lifting the leg). Our primary objective was to determine if machine learning can accurately identify key ballet movements during dance training. The secondary objective was to determine the influence of the location and number of sensors on accuracy.Results: Convolutional neural networks were applied to develop two models for every combination of six sensors (6, 5, 4, 3, etc.) with and without the inclusion of transition movements. At the first level of classification, including data from all sensors, without transitions, the model performed with 97.8% accuracy. The degree of accuracy reduced at the second (83.0%) and third (75.1%) levels of classification. The degree of accuracy reduced with inclusion of transitions, reduction in the number of sensors and various sensor combinations. Conclusion: The models developed were robust enough to identify jumping and leg lifting tasks in real-world exposures in dancers. The system provides a novel method for measuring dancer training volume through quantification of specific movement tasks. Such a system can be used to further understand the relationship between dancers' pain and training volume and for athlete monitoring systems. Further, this provides a proof of concept which can be easily translated to other lower limb dominant sporting activities Key PointsDeep learning models were shown to have acceptable accuracy when applied to recognised ballet-specific jumping and leg lifting tasks in a population of 23 dancers. A system of multiple sensors (six per dancer) was shown to have the greatest accuracy; however, the optimal single sensor model also performed with acceptable accuracy. The inclusion of all six sensors yielded the highest degree of accuracy: however, fewer sensors still provided an acceptable degree of accuracy. For real-world application, minimal sensors are required to reduce athlete burden. The method demonstrated for model development is highly translatable for future developments in other lower limb dominant sporting activities.

Taping is often used to manage the high rate of knee injuries in ballet dancers; however, little is known about the effect of taping on lower-limb biomechanics during ballet landings in the turnout position. This study investigated the effects of Kinesiotape (KT), Mulligan's tape (MT) and no tape (NT) on knee and hip kinetics during landing in three turnout positions. The effect of taping on the esthetic execution of ballet jumps was also assessed. Eighteen pain-free 12-15-year-old female ballet dancers performed ballet jumps in three turnout positions, under the three knee taping conditions. A Vicon Motion Analysis system (Vicon Oxford, Oxford, UK) and Advanced Mechanical Technology, Inc. (Watertown, Massa chusetts, USA) force plate collected lower-limb mechanics. The results demonstrated that MT significantly reduced peak posterior knee shear forces (P = 0.025) and peak posterior (P = 0.005), medial (P = 0.022) and lateral (P = 0.014) hip shear forces compared with NT when landing in first position. KT had no effect on knee or hip forces. No significant differences existed between taping conditions in all landing positions for the esthetic measures. MT was able to reduce knee and the hip forces without affecting the esthetic performance of ballet jumps, which may have implications for preventing and managing knee injuries in ballet dancers.

This study aimed to develop a wearable sensor system, using machine-learning models, capable of accurately estimating peak ground reaction force (GRF) during ballet jumps in the field. Female dancers (n = 30) performed a series of bilateral and unilateral ballet jumps. Dancers wore six ActiGraph Link wearable sensors (100 Hz). Data were collected simultaneously from two AMTI force platforms and synchronised with the ActiGraph data. Due to sensor hardware malfunctions and synchronisation issues, a multistage approach to model development, using a reduced data set, was taken. Using data from the 14 dancers with complete multi-sensor synchronised data, the best single sensor was determined. Subsequently, the best single sensor model was refined and validated using all available data for that sensor (23 dancers). Root mean square error (RMSE) in body weight (BW) and correlation coefficients (r) were used to assess the GRF profile, and Bland–Altman plots were used to assess model peak GRF accuracy. The model based on sacrum data was the most accurate single sensor model (unilateral landings: RMSE = 0.24 BW, r = 0.95; bilateral landings: RMSE = 0.21 BW, r = 0.98) with the refined model still showing good accuracy (unilateral: RMSE = 0.42 BW, r = 0.80; bilateral: RMSE = 0.39 BW, r = 0.92). Machine-learning models applied to wearable sensor data can provide a field-based system for GRF estimation during ballet jumps.

The high prevalence of lower limb overuse injuries among adolescent ballet dancers may be due in part to repetitive landings. This cross-sectional study compared how adolescent ballet dancers perform a drop-landing task in comparison to non-dancers in order to help understand injury mechanics. Fifteen adolescent female ballet dancers aged 11.9 ± 1.1 years and 17 non-dancers aged 10.9 ± 0.9 years each performed three single limb drop-landings from a 30 cm box. An 18-camera motion capture system (Vicon MX; Oxford Metrics, Oxford, UK; 250 Hz) and a force platform (Advanced Mechanical Technology Inc., Watertown, Massachusetts, USA; 2,000 Hz) were used to collect lower limb joint angles in all three planes of motion and peak vertical ground reaction forces during the landing phase. These variables were compared for the two sets of participants using independent samples t-tests (p < 0.01). While the dancers landed with greater sagittal plane range of motion, this appeared to provide no mechanical advantage with no reduction in ground reaction force. Rather, the increased sagittal range of motion was coupled with increased coronal and frontal plane motion. This may place dancers at increased risk of injury.

OBJECTIVE: Low back pain (LBP) is common in dancers. A biopsychosocial model should be considered in the aetiology of LBP, including a dancer’s general beliefs of the low back and movements of the spine. This study aimed to determine pre-professional dancers’ beliefs about their lower back in general and dance-specific movements of the spine and to explore whether these beliefs were influenced by a history of disabling LBP. METHODS: 52 pre-professional female dancers (mean age 18.3 [1.4] yrs) were recruited and reported whether they had a history of disabling LBP and completed the Back Pain Attitudes Questionnaire (Back-PAQ) and a dance movement beliefs questionnaire. A linear mixed model was applied to determine the effect of a history of disabling LBP on dancers’ beliefs (p<0.05). RESULTS: 20 dancers reported a history of disabling LBP. Regardless of this LBP history, dancers held generally negative beliefs as measured by the Back-PAQ (p=0.130). A history of disabling LBP did not influence dancers’ perceived movement safety of all tasks (p=0.867), and dancers held negative beliefs towards extension activities. These beliefs were linked to the conceptions of perceived risk of damage and the need to protect the lower back. CONCLUSIONS: Dancers hold negative general beliefs around the low back and low back movements, regardless of a history of disabling LBP. Dancers perceive extension activities as more dangerous than flexion activities. These beliefs may reflect a combination of pain experience and beliefs specific to dance.