The role of the biomechanics analyst in swimming training and competition analysis

Agreement between an automated video-based system and tethered system to measure instantaneous swimming velocity

Successful performance in competitive swimming requires a swimmer to maximise propulsion and minimise drag, which can be assessed using instantaneous swimming velocity. Many systems exist to quantify velocity, and therefore, it is important to understand the agreement between systems. This study examined the agreement between an automated video-based system and a tethered system to measure instantaneous velocity. Twenty-two competitive swimmers (state level or higher) completed 25 m of each stroke at maximal intensity. The tethered speedometer was attached to the swimmer's waist, while videos of each trial were recorded. The swimmer's head was then automatically tracked using proprietary software, and instantaneous velocity was determined from each system. Bland-Altman plots showed good agreement between the two systems in backstroke (95% Limits of Agreement (LOA): -0.24-0.26 m.s-1) and freestyle (95% LOA: -0.36-0.38 m.s-1) but poorer agreement in butterfly (95% LOA: -0.51-0.53 m.s-1) and breaststroke (95% LOA: -0.88-0.92 m.s-1). The root mean square error was higher in butterfly (0.27 m.s-1) and breaststroke (0.46 m.s-1) compared to backstroke (0.13 m.s-1) and freestyle (0.19 m.s-1). Results demonstrated that the two systems are comparable for measuring instantaneous swimming velocity; however, larger discrepancies are evident for butterfly and breaststroke.

Race analysis in swimming: understanding the evolution of publications, citations and networks through a bibliometric review

The aim of this study was to conduct a scoping and bibliometric review of swimming articles related to race analysis. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were used to identify relevant studies. Articles on race analysis in swimming published between 1984 and December 31, 2023 were retrieved from the Web of Science database. 366 records were screened and a total of 74 articles were retained for analysis. Until 2012, there were some time intervals with no or few publications. From 2012, there was a clear upward trend in publications and citations. This theme was led by the United States of America, Australia, and Spain. Australia and Spain maintain their status as the countries with the most publications. The analysis of author collaborations revealed two clusters with Spanish authors, and the remaining clusters are composed of Portuguese, Swiss, and Australian authors. With this bibliometric review, it has been possible to understand the evolution of the articles published on race analysis in swimming, the countries and the authors that have contributed most to this topic over the years. The prediction model shows that the number of articles and citations on this topic will continue to increase over the next 10 years (until 2034).

Effects of anthropometrics, thrust, and drag on stroke kinematics and 100 m performance of young swimmers using path-analysis modeling

The aim of this study was to understand the interactions between anthropometric, kinetic, and kinematic variables and how they determine the 100 m freestyle performance in young swimmers. Twenty-five adolescent swimmers (15 male and 10 female, aged 15.75 ± 1.01 years) who regularly participated in regional and national competitions were recruited. The 100 m freestyle performance was chosen as the variable to be predicted. A series of anthropometric (hand surface area-HSA), kinetic (thrust and active drag coefficient (CDA )), and kinematic (stroke length (SL); stroke frequency (SF), and swimming speed) variables were measured. Structural equation modeling (via path analysis) was used to develop and test the model. The initial model predicted performance with 90.1% accuracy. All paths were significant (p < 0.05) except the thrust-SL. After deleting this non-significant path (thrust-SL) and recalculating, the model goodness-of-fit improved and all paths were significant (p < 0.05). The predicted performance was 90.2%. Anthropometrics had significant effects on kinetics, which had significant effects on kinematics, and consequently on the 100 m freestyle performance. The cascade of interactions based on this path-flow model allowed for a meaningful prediction of the 100 m freestyle performance. Based on these results, coaches and swimmers should be aware that the swimming predictors can first meaningfully interact with each other to ultimately predict the 100 m freestyle performance.

Associations between load-velocity profiling and race parameters of elite swimmers in the 100 and 200m freestyle events

Introduction

Improving swimming performance involves assessments of biomechanical variables of the stroke, and it can be achieved using semi-tethered swimming tests. The aim of this study was thus to investigate the associations between load-velocity (L-V) profiles, from a semi-tethered swimming protocol and race variables in the 100 m and 200 m freestyle events.

Methods

Eight swimmers completed a L-V profiling protocol consisting of four sprints (25 m, 25 m, 20 m, 15 m) against increasing loads (0.1, 2.0, 4.0, 6.0 kg respectively) with complete recovery between repetitions (>5 min). The L-V linear regression was used to estimate maximal velocity (V0) and body mass normalized load (rL0). Race variables such as clean swimming speed (V), stroke rate (SR), distance per cycle (SL) and stroke index (SI) were assessed from video analysis of 100 m and 200 m freestyle events taking place 3-4 days after the L-V protocol.

Results

L-V results showed high levels of speed (mean ± SD: 1.87 ± 0.04 m/s) and heavy maximal relative loads (mean ± SD: 38.5 ± 6.51 as % of body mass). Swimmers also achieved high-level performances in the 100 m (mean ± SD time: 51.95 ± 0.75 s) and the 200 m (mean ± SD time: 113.85 ± 2.67 s). For the 100 m events, the maximal relative load showed strong correlation with performance (r = 0.63) whereas trivial correlation was observed for the 200 m events (r = 0.12). SR on the 100 m and the 200 m also showed very strong association with rL0 (r = 0.83) and a strong association with V0 (r = 0.68) respectively.

Conclusion

The relationships between L-V variables and race variables depend on the distance of the event. However, L-V variables seem to be less related to SR and SL evolutions for the 100 m than in the 200 m event. Moreover, L-V profiles tend to be more related to the 100 m than 200 m freestyle performance. L-V profile should be interpreted taking into consideration the specific physiological and biomechanical constraints of the main events of the swimmer.

Next-Generation Models for Predicting Winning Times in Elite Swimming Events: Updated Predictions for the Paris 2024 Olympic Games

PURPOSE

To evaluate statistical models developed for predicting medal-winning performances for international swimming events and generate updated performance predictions for the Paris 2024 Olympic Games.

METHODS

The performance of 2 statistical models developed for predicting international swimming performances was evaluated. The first model employed linear regression and forecasting to examine performance trends among medal winners, finalists, and semifinalists over an 8-year period. A machine-learning algorithm was used to generate time predictions for each individual event for the Paris 2024 Olympic Games. The second model was a Bayesian framework and comprised an autoregressive term (the previous winning time), moving average (past 3 events), and covariates for stroke, gender, distance, and type of event (World Championships vs Olympic Games). To examine the accuracy of the predictions from both models, the mean absolute error was determined between the predicted times for the Budapest 2022 World Championships and the actual results from said championships.

RESULTS

The mean absolute error for prediction of swimming performances was 0.80% for the linear-regression machine-learning model and 0.85% for the Bayesian model. The predicted times and actual times from the Budapest 2022 World Championships were highly correlated (r = .99 for both approaches).

CONCLUSIONS

These models, and associated predictions for swimming events at the Paris 2024 Olympic Games, provide an evidence-based performance framework for coaches, sport-science support staff, and athletes to develop and evaluate training plans, strategies, and tactics, as well as informing resource allocation to athletes, based on their potential for the Paris 2024 Olympic Games.

A comparison of load cell and pressure sensors to measure in-water force in young competitive swimmers

The purpose of this study was to compare the in-water force of young competitive swimmers using tethered swimming and differential pressure sensors. Thirty-one swimmers (16 girls and 15 boys) were randomly assigned to perform two in-water tests. Swimmers completed two maximum bouts of 25 m front crawl with a differential pressure system and a 30 s maximum bout with an attached load cell (tethered-swimming). The peak force (FPEAK, in N) of dominant and non-dominant upper limbs was retrieved for further analysis. Comparison between methods revealed significant differences in all force variables (p ≤ 0.05) and the biases (mean differences) were large in girls (FPEAK dominant, 45.89 N; FPEAK non-dominant, 43.79 N) and boys (FPEAK dominant, 67.26 N; FPEAK non-dominant, 61.78 N). Despite that, simple linear regression models between the two methods showed significant relationships with a moderate effect in all variables for girls, whereas in boys a high and moderate effect was verified for FPEAK of dominant and non-dominant limbs (respectively). It seems that using pressure sensors and tethered swimming leads to different FPEAK values in young competitive, where correction factors are needed to compare data between both methods.

The metronome-based methodology to monitor the stroke length changes in trained swimmers

The aim of our study was to develop a methodology that uses the metronome to constrain the swimmers' stroke rate with the aim to monitor changes in stroke length (SL) during two different periods of the season. Thirteen young trained swimmers (15.7 ± 1.7 y) performed three 50 m front crawl time trials during pre-season (PRE) and after 2 months, during the in-season period (IN). They were asked: (I) to swim at their maximum intensity (NO-MET condition); (II) to synchronize their stroke with a metronome beat set to their preferred intra-stroke-interval (ISI) (100% condition, corresponding to 48 ± 0.7 cycles/min); (III) to synchronize their stroke with a metronome beat set at 5% higher than their preferred ISI (95% condition, corresponding to 51 ± 0.8 cycles/min). The outcome parameters used to evaluate the performance were ISI, SL and total time of 50 m (TT). In NO-MET condition, results showed that TT in IN improved with respect to PRE, but no changes in ISI and SL. In 100% condition, no differences were obtained between the imposed and the performed ISI, whilst in 95% condition, the performed ISI was lower than the metronome ISI, and lower than that in 100% condition. At last, when using the metronome, SL was higher during IN compared to PRE and SL was lower in the 95% condition compared to the 100% condition. Results indicate that the use of the metronome successfully allowed monitoring changes in SL during different periods of the season. This methodology provides valuable information to coaches and athletes to enhance their performance throughout the season.

From Entry to Finals: Progression and Variability of Swimming Performance at the 2022 FINA World Championships

The aim of the present study was two-fold: (i) to analyze the progression and variability of swimming performance (from entry times to best performances) in the 50, 100, and 200 m at the most recent FINA World Championships and (ii) to compare the performance of the Top16, semifinalists, and finalists between all rounds. Swimmers who qualified with the FINA A and B standards for the Budapest 2022 World Championships were considered. A total of 1102 individual performances swimmers were analyzed in freestyle, backstroke, breaststroke, and butterfly events. The data was retrieved from the official open-access websites of OMEGA and FINA. Wilcoxon test was used to compare swimmers' entry times and best performances. Repeated measures ANOVA followed by the Bonferroni post-hoc test were performed to analyze the round-to-round progression. The percentage of improvement and variation in the swimmers' performance was computed between rounds. A negative progression (entry times better than best performance) and a high variability (> 0.69%) were found for most events. The finalists showed a positive progression with a greater improvement (~1%) from the heats to the semifinals. However, the performance progression remained unchanged between the semifinals and finals. The variability tended to decrease between rounds making each round more homogeneous. Coaches and swimmers can use these indicators to prepare a race strategy between rounds.

Profiles of stroke regulations discriminate between finishing positions during international open water races

This study aims to identify stroke regulation profiles and tipping-points in stroke regulation timing during international open water races according to performance level. Twelve elite or world-class swimmers were analysed during 18 international races. Stroke rate and jerk cost were computed cycle-to-cycle using an Inertial Measurement Unit and regulations profiles fitted using polynomials. We performed two-ways mixed-ANOVA to compare stroke kinematics among race segments and performance groups (G1 -fastest- to G3 -slowest-). Swimmers displayed specific regulation profiles (i.e., J-shape with end-spurt, J-shape without end-spurt and reverse L-shape for stroke rate and U-shape, reverse J-shape and reverse L-shape for jerk cost, for respectively G1, G2 and G3) with significant effect of race segment on stroke kinematics for G1 and G2. We highlighted tipping-points in stroke regulations profiles (TP1 and TP2) at respectively 30% and 75% of the race with greater magnitude in G1 than G2. TP1 reflects the end of a stroke economy period (0-30%) and TP2 the end of a progressive increase in stroke kinematics (30-75%) towards end-spurt (75-100%). Open water races follow a high-grading dynamics requiring biomechanical regulations along the race. Targeting stroke rate reserve and management of stroke smoothness should be considered during training of open water swimmers.

Association between elite swimmers' force production and 100 m front crawl inter-lap pacing and kinematics

The present study aimed to analyse the associations between force production and 100 m front crawl inter-lap pacing and kinematics. Eleven elite male swimmers performed a 100 m front crawl maximal effort to collect 50 m lap time (T₅₀, s) and velocity (v, m·s^-1) for pacing, stroke rate (SR), stroke length (SL) and stroke index (SI) as kinematic variables. A 30 s tethered effort allowed to determine the peak (F_peak) and mean force (F_mean) as force production variables. The relative change (Δ) between 50 m laps was also calculated for all measures. A paired sample t-test was used to check differences between laps and Pearson correlation coefficients allowed to quantify the associations between force and remaining variables. The T₅₀ increased from the first to the second lap (ΔT₅₀ = 10.61%, p < 0.01, d = 2.68), while v (Δv = -5.92%, p < 0.01, d = 1.53), SR (ΔSR = -6.61%, p < 0.01, d = 0.45) and SI (ΔSI = -4.92%, p = 0.02, d = 0.45) decreased. SL remained unchanged between laps (ΔSL = 1.07%, p = 0.66, d = 0.08). No associations were found between force production and most of Δ, with the only exception being the reasonable good association between F_peak and Δv (r = 0.62, p = 0.04). Although both pacing and kinematics fall from the first to the second sections of a 100 m front-crawl effort, the swimmers who exhibit higher F_peak show a more stable front crawl v between both 50 m laps.

Race Analysis and Determination of Stroke Frequency - Stroke Length Combinations during the 50-M Freestyle Event

The aims of this study were to: (1) analyze and compare the stroke kinematics between junior and senior elite male swimmers in every section of the race during the 50-m freestyle event, and; (2) identify stroke frequency (SF)-stroke length (SL) combinations on swim speed independently for junior and senior swimmers in each section of the 50-m freestyle event. Eighty-six junior swimmers (2019) and 95 seniors (2021) competing in the 50-m long course meter LEN Championships were analyzed. The t-test independent samples (p ≤ 0.05) were used to compare juniors and seniors. The SF and SL combinations on swim speed were explored using three-way ANOVAs. Senior swimmers were significantly faster in the 50-m race than juniors (p < 0.001). Speed presented the largest significant difference (p < 0.001) in section S0-15 m (start until the 15^th meter mark) being seniors fastest. Both junior and senior swimmers revealed a significant categorization (p < 0.001) by stroke length and stroke frequency in each race section. It was possible to model several SF-SL combinations for seniors and juniors in each section. The fastest swim speed in each section, for seniors and juniors independently, was achieved by a SF-SL combination that may not be the fastest SF or the longest SL. Coaches and swimmers must be aware that despite the 50-m event being an all-out bout, several SF-SL combinations were observed (independently for juniors and seniors), and they differ between race sections.

The Mechanical and Efficiency Constraints when Swimming Front Crawl with the Aquanex System

The aim of this study was to compare the mechanical and efficiency constraints between free swim and swimming with differential pressure sensors (Aquanex System). These conditions were also analysed to understand the differences between sexes. Thirty young swimmers, 14 boys and 16 girls (12.31 ± 0.67 years) performed three 25-m front crawl maximal bouts under each condition: free swim and swimming with sensors. Under the condition with sensors, swimmers carried the Aquanex System composed of two hand pressure sensors (v.4.1, Model DU2, Type A, Swimming Technology Research, Richmond, VA, USA). The 25-m time (T25) was assessed as a swimming performance variable. The swimming velocity (v), stroke rate (SR), and stroke length (SL) were assessed and calculated as stroke mechanics variables. Thereafter, the stroke index (SI) and arm stroke efficiency (η F) were estimated for swimming efficiency. Statistical significance was set at p ≤ 0.05. Swimming performance was impaired when swimmers swam with sensors (overall: p = 0.03, d = 0.14; Δ = 1.30%) and a significant decrease in v was found for overall (p = 0.04, d = 0.14; Δ = 1.42%) and the girls’ group (p < 0.01, d = 0.39; Δ = -1.99%). The remaining stroke mechanics variables showed no differences between conditions, as well as for swimming efficiency. Furthermore, there were no differences between girls and boys in free swim and with sensors for all variables. Swimming with the Aquanex System seems not to impose constraints in the mechanics and efficiency of young swimmers, despite differences in swimming performance and v.

Race analysis of the men's 50 m events at the 2021 LEN European Championships

The aim of this study was to: (i) characterise the stroke kinematics' stability of the male swimmers competing in the four 50 m events at the 2021 European Championships, and; (ii) understand the speed-time relationship in the four race events. All male swimmers who participated in the 50 m events (backstroke: 78 swimmers; breaststroke: 79 swimmers; butterfly: 89 swimmers; freestyle: 95 swimmers) were evaluated. In each swimming stroke swimmers were split in two groups (better and poorer performances). Significant variances (p < 0.05) were observed in both groups in all variables and for all swimming strokes. Swimming speed was the variable with the highest variance in both groups and strokes. Overall, better swimmers presented a low to high normative stability, and poorer swimmers a moderate-to-high. Speed-time curve fitting for all swimming strokes and groups suggested a cubic relationship. It can be considered that elite male swimmers racing 50 m sprint events at major competitions present an all-out trend. The present data provide coaches with substantial information about the main trend in the 50 m sprint events, specifically in each section of the race.

Performance Development of European Swimmers Across the Olympic Cycle

The aims of the study were to (1) quantify the performance development of race times and key performance indicators of European swimmers across the last Olympic cycle (from 2016 to 2021) and (2) provide reference values for long-course swimming pool events for both sexes from 50 m to 1,500 m including butterfly, backstroke, breaststroke, freestyle, and individual medley. Individual events from the 2016 and 2021 European swimming championships were included. Specifically, 246 men (age: 24.2 ± 3.4 years, FINA points: 890 ± 40) and 256 women races (age: 24.2 ± 4, FINA points: 879 ± 38) of the finalists were recorded and key performance indicators and split times analyzed. Performance differences in finalists of the 2016 and 2021 European championships were determined by an independent t-test and Cohen's d effect size. Reference values were retrieved from 2021 European championship finalists and are provided for all key performance indicators. Race times improved significantly (P < 0.05) or showed moderate (d = 0.5–1) to large effect sizes (d > 1) in 14 (men) and 6 (women) out of 16 events. Improvements were primarily evident in 100 m and 200 m events for males, as well as BR and sprint events for female swimmers. While start times improved in 15 (men) and 14 (women) events, turn times remained inconclusive in both sexes. Generally, breakout distances increased. Clean swimming velocities were faster in 12 (men) and 5 (women) events. In particular, for alternating swimming strokes, i.e., backstroke and freestyle, effect sizes indicated improved swimming efficiency with an inverse relationship between reduced stroke rate and increased distance per stroke. Coaches and performance analysts may use the present reference values as comparative data for race analyses and to specifically prepare swimmers for the various race sections. Data on the performance development should be used to analyze swimmers' potential and set goals for the various events and the next Olympic cycle.

Multi-Output Sequential Deep Learning Model for Athlete Force Prediction on a Treadmill Using 3D Markers

Reliable and innovative methods for estimating forces are critical aspects of biomechanical sports research. Using them, athletes can improve their performance and technique and reduce the possibility of fractures and other injuries. For this purpose, throughout this project, we proceeded to research the use of video in biomechanics. To refine this method, we propose an RNN trained on a biomechanical dataset of regular runners that measures both kinematics and kinetics. The model will allow analyzing, extracting, and drawing conclusions about continuous variable predictions through the body. It marks different anatomical and reflective points (96 in total, 32 per dimension) that will allow the prediction of forces (N) in three dimensions (Fx, Fy, Fz), measured on a treadmill with a force plate at different velocities (2.5 m/s, 3.5 m/s, 4.5 m/s). In order to obtain the best model, a grid search of different parameters that combined various types of layers (Simple, GRU, LSTM), loss functions (MAE, MSE, MSLE), and sampling techniques (down-sampling, up-sampling) helped obtain the best performing model (LSTM, MSE, down-sampling) achieved an average coefficient of determination of 0.68, although when excluding Fz it reached 0.92.

Turn Performance Variation in European Elite Short-Course Swimmers

Turn performances are important success factors for short-course races, and more consistent turn times may distinguish between higher and lower-ranked swimmers. Therefore, this study aimed to determine coefficients of variation (CV) and performance progressions (∆%) of turn performances. The eight finalists and eight fastest swimmers from the heats that did not qualify for the semi-finals, i.e., from 17th to 24th place, of the 100, 200, 400, and 800 (females only)/1500 m (males only) freestyle events at the 2019 European Short Course Championships were included, resulting in a total of 64 male (finalists: age: 22.3 ± 2.6, FINA points: 914 ± 31 vs. heats: age: 21.5 ± 3.1, FINA points: 838 ± 74.9) and 64 female swimmers (finalists: age: 22.9 ± 4.8, FINA points: 904 ± 24.5 vs. heats: age: 20.1 ± 3.6, FINA points: 800 ± 48). A linear mixed model was used to compare inter- and intra-individual performance variation. Interactions between CVs, ∆%, and mean values were analyzed using a two-way analysis of variance (ANOVA). The results showed impaired turn performances as the races progressed. Finalists showed faster turn section times than the eight fastest non-qualified swimmers from the heats (p < 0.001). Additionally, turn section times were faster for short-, i.e., 100 and 200 m, than middle- and long-distance races, i.e., 400 to 1500 m races (p < 0.001). Regarding variation in turn performance, finalists showed lower CVs and ∆% for all turn section times (0.74% and 1.49%) compared to non-qualified swimmers (0.91% and 1.90%, respectively). Similarly, long-distance events, i.e., 800/1500 m, showed lower mean CVs and higher mean ∆% (0.69% and 1.93%) than short-distance, i.e., 100 m events (0.93% and 1.39%, respectively). Regarding turn sections, the largest CV and ∆% were found 5 m before wall contact (0.70% and 1.45%) with lower CV and more consistent turn section times 5 m after wall contact (0.42% and 0.54%). Non-qualified swimmers should aim to match the superior turn performances and faster times of finalists in all turn sections. Both finalists and non-qualified swimmers should pay particular attention to maintaining high velocities when approaching the wall as the race progresses.

Survey on Video-Based Biomechanics and Biometry Tools for Fracture and Injury Assessment in Sports

This work presents a survey literature review on biomechanics, specifically aimed at the study of existent biomechanical tools through video analysis, in order to identify opportunities for researchers in the field, and discuss future proposals and perspectives. Scientific literature (journal papers and conference proceedings) in the field of video-based biomechanics published after 2010 were selected and discussed. The most common application of the study of biomechanics using this technique is sports, where the most reported applications are american football, soccer, basketball, baseball, jumping, among others. These techniques have also been studied in a less proportion, in ergonomy, and injury prevention. From the revised literature, it is clear that biomechanics studies mainly focus on the analysis of angles, speed or acceleration, however, not many studies explore the dynamical forces in the joints. The development of video-based biomechanic tools for force analysis could provide methods for assessment and prediction of biomechanical force associated risks such as injuries and fractures. Therefore, it is convenient to start exploring this field. A few case studies are reported, where force estimation is performed via manual tracking in different scenarios. This demonstration is carried out using conventional manual tracking, however, the inclusion of similar methods in an automated manner could help in the development of intelligent healthcare, force prediction tools for athletes and/or elderly population. Future trends and challenges in this field are also discussed, where data availability and artificial intelligence models will be key to proposing new and more reliable methods for biomechanical analysis.