Race Performance Research Articles

Factor and Correlation Analysis for Predicting Marathon Race Performance Using Machine Learning Algorithms

A marathon race is a long-distance running event typically spanning 26.2 miles or 42.195 kilometers. It is a test of endurance, stamina, and mental fortitude, attracting participants from all walks of life, ranging from elite athletes to recreational runners. The origins of the marathon can be traced back to ancient Greece, where legend has it that a messenger named Pheidippides ran from the battlefield of Marathon to Athens to deliver news of victory before collapsing and dying from exhaustion. Machine learning has increasingly become a valuable tool in optimizing training strategies, performance prediction, and injury prevention for marathon runners. By analyzing vast amounts of data collected from wearable devices, training logs, and race results, machine learning algorithms can identify patterns, trends, and correlations that help runners improve their training regimens and race-day strategies. This paper introduces a novel approach, the Factor Analysis Probabilities Prediction Ranking Machine Learning (FA-PP-R-ML) methodology, for predicting marathon race outcomes. With historical race data, factor analysis, and machine learning techniques, the FA-PP-R-ML methodology aims to accurately estimate marathon finish times and rank predicted outcomes based on their probabilities. Through a comprehensive analysis of marathon race data, including training metrics, environmental conditions, and physiological parameters, the FA-PP-R-ML model identifies latent factors influencing race performance. Through factor analysis, latent factors influencing race performance are identified, with values ranging from 0.5 to 0.9. Machine learning algorithms utilize these factors to predict marathon finish times, resulting in accurate predictions with an average error of ±0.1 hours.

Cardiovascular Fitness and Stride Acceleration in Race-Pace Workouts for the Prediction of Performance in Thoroughbreds.

In-training racehorse physiological data can be leveraged to further explore race-day performance prediction. To date, no large retrospective, observational study has analysed whether in-training speed and heart rate recovery can predict racehorse success. Speed (categorised as 'slow' to 'fast' according to the time taken to cover the last 600 m from a virtual finish line) and heart rate recovery (from gallop to 1 min after exercise) of flat racehorses (n = 485) of varying age, sex and type according to distance (e.g., sprinter, miler and stayer) were obtained using a fitness tracker from a single racing yard in Australia. Race-pace training sessions on turf comprised 'fast gallop' (n = 3418 sessions) or 'jumpout' (n = 1419). A posteriori racing information (n = 3810 races) for all 485 racehorses was extracted and combined with training data. Race performance was categorised as win/not-win or podium or not, each analysed by logistic regression. Colts (p < 0.001), stayers (p < 0.001) and being relatively fast over the last 600 m of a benchmark test in training (p < 0.008) were all predictive of race performance. Heart rate recovery after exercise (p = 0.21) and speed recorded at 600 m of a 1 km benchmark test in training (p = 0.94) were not predictive. In-training physiological data analytics used along with subjective experience may help trainers identify promising horses and improve decision-making.

Stakeholder perceptions of thoroughbred yearling sales endoscopy in Australia: can we do better?

To identify thoroughbred industry stakeholders' views on the yearling sales endoscopy in Australia. Semi-structured qualitative group interviews with equine veterinarians, thoroughbred breeders and yearling purchasers. Twenty-nine experienced thoroughbred industry stakeholders participated in online focus groups: (1) equine veterinarians involved in yearling endoscopy; (2) thoroughbred breeders; and (3) yearling buyers. The focus groups were audio and video recorded and digital whiteboards were available. Data was transcribed, live-coded and analysed thematically. The main themes identified included the uncertainty surrounding the relationship between yearling laryngeal function and future performance, especially the significance of yearlings with grade 3 out of 5 laryngeal function; interobserver variability in the laryngeal function grade assigned by veterinarians to the same endoscopic exam; and the presence of intra-horse variability in laryngeal function over different time points. Stakeholders raised multiple concerns about the current yearling sales endoscopy process in Australia. Recommendations to address these concerns include further investigation into the race performance of yearlings identified with grade 3 laryngeal function; training of veterinarians to reduce inter-observer variability; and the need to determine the most appropriate grading system to use in yearlings. Future research should evaluate the significance of intra-horse variability in a yearling population.

Consistent Race Performance in Racing Pigeons: A Case Report Confirming a Favorable Genetic Profile

A recent multivariate analysis showed that racing pigeons had a better race performance based on DRD4 and F-KER genotypes that were independently statistically significant and those racing pigeons with both DRD4 CCCT and F-KER TT had the lowest race coefficient, i.e. the best race performance. This result indicated that 50% birds with this genotype were consistently in the top 10% in the race results. To date, this is the first multigene genotype reported relating to race performance. In 2023, a consistently performing racing pigeon scored in or around the top 10% in all races of a 5 race series ranging from 100 mile to 350 miles. Retrospectively, this bird was shown to have indeed DRD4 CCCT and F-KER TT. Another bird while distantly family related, showed top performance only in the final long distance race but lacked consistency throughout the race series; this bird not have the consistency genotype profile. We pose the hypothesis that birds with both DRD4 CCCT and F-KER TT are more likely to score consistently in the Top 10% in a race series than birds without. This would need to be confirmed in a larger study in particular including Ace Champion birds with consistent top 10% race performance.

Performance and micro-pacing in sprint cross-country skiing: A comparison of individual time-trial and head-to-head race formats

ABSTRACT This study compared performance strategies and sub-technique selection in cross-country skate skiing sprint races, specifically individual time-trial (ITT) and head-to-head (H2H) formats. Fourteen male cross-country skiers from the Chinese national team participated in the FIS-sanctioned sprint race day. GNSS and heart rate sensors recorded positioning, skiing speeds, heart rate, sub-technique usage, and skiing kinematics. Statistical parametric mapping (SPM) was used to determine the course positions (clusters) where instantaneous skiing speed was significantly associated with section time. One-way analyses of variance were used to examine differences between the ITT and H2H. H2H race speeds were 2.4 ± 0.2% faster than the ITT race (p < 0.05).Variations in sub-technique and skiing kinematics were observed between race formats, indicating different strategies and tactics employed by athletes. SPM identified specific clusters (primarily uphill) where the fastest athlete gained significant time over the slowest. The greatest time gains were associated with higher G3 sub-technique usage and longer G3 cycle length on steep uphill terrain (9–13% gradients). Integrating SPM analyses and sub-technique assessments can help optimise performance and tactics in sprint races. This study enhances our understanding of cross-country skiing dynamics and performance variations among elite competitors.

Are pre‐race serum blood biomarkers associated with the 24‐h ultramarathon race performance?

AbstractThe 24‐h ultramarathon (UM) race is one of the most demanding competitive sports in terms of muscular and physiological exertion. In this context, predictors of UM athletes' physical performance are in high demand; however, data on the predictive capabilities of hematological variables are still sparse. In the present paper, we retrospectively took into consideration the pre‐race blood biomarker levels (including basic blood count, leukocyte subpopulations, markers of inflammation and organ function, metabolic profile, and electrolytes) of 50 UM athletes (M = 33, F = 17) who completed a 24‐h competition in order to identify a combination of analytes capable of predicting the athletic performance in terms of distance covered during the 24‐h run. The multiple regression analysis produced a model that explained a significant portion of the variance in the dependent variable, with an adjusted R‐squared value of 0.783 (F(13, 36) = 14.58, p &lt; 0.001). A greater race distance was correlated with higher pre‐race values of hematocrit, lactate dehydrogenase (LDH), total cholesterol, HDL/LDL ratio, and triglycerides and lower levels of monocytes, eosinophils, alanine aminotransferase (ALT), gamma‐glutamyl transferase (GGT), total proteins, and sodium. This study represents the first of its kind conducted on 24‐h UM athletes that investigated the association between blood markers and endurance performance. Our model, given its promising predictive power, would serve as a starting point that will require refinement and integration with other traditional performance prediction measures, in order to support athletes and coaches in better managing the training loads during the race‐approaching phases.

Staging Haiti in Nineteenth-Century America: Revolution, Race and Popular Performance by Peter P. Reed (review)

Staging Haiti in Nineteenth-Century America: Revolution, Race and Popular Performance by Peter P. Reed (review)

Physiological and muscle histochemical assessment of men and women 10 km runners matched for race performance or training volume.

Women have a disadvantage for performance in long-distance running compared with men. To elaborate on inherent characteristics, 12 subelite women were matched with 12 men for training volume (M-Tm) (56.6 ± 18 vs. 55.7 ± 17 km/wk). The women were also matched to other men for a 10 km staged outdoor time trial (M-Pm) (42:36 min:s) to determine which factors could explain equal running performance. Anthropometry and treadmill tests were done. Fiber type (% Type I and Type IIA) and citrate synthase activities were analyzed in muscle biopsy samples. Consistent sex differences for both comparisons included height, weight, % body fat (P < 0.01), and hematocrit (P < 0.05). Women had lower V̇o2max and peak treadmill speed (PTS) compared with both M-Tm and M-Pm (P < 0.01). Training matched pairs had no sex difference in % PTS at race pace but compared with M-Pm women ran at a higher % PTS (P < 0.05) and %HRmax (P < 0.01) at race pace. On average, the women trained 22.9 km/wk more than M-Pm (+67.5%, P < 0.01). This training was not associated with higher V̇o2max or better running economy. Muscle morphology and oxidative capacity did not differ between groups. Percentage body fat remained significantly higher in women. In conclusion, women matched to men for training volume had slower 10 km performance (-10.5% P < 0.05). Higher training volume, more high-intensity sessions/wk, and time spent training in the 95%-100% HRmax zone may explain the higher % PTS and %HRmax at race pace in women compared with performance-matched men.NEW & NOTEWORTHY When subelite women 10 km runners were matched with male counterparts for 10 km race performance, inherent differences in % body fat, V̇o2max, Hct, and peak treadmill speed were counteracted by significantly higher training volume, more time training at higher %HRmax and consequently, higher %HRmax and %PTS at race pace. Citrate synthase activity and muscle fiber types did not differ. When women and men matched for training, 10 km performance of men was 10.5% faster.

The influence of midsole thickness on running turns

Running race courses typically feature numerous turns, an element of a race typically neglected. If a thick midsole were to decrease frontal plane ankle stability, it could potentially lead to a misalignment of lower limb joints, thereby affecting turn running and overall race performance. Therefore, the purpose of this study was to determine the influence of midsole thickness on turn running performance and peak frontal plane ankle angle. Thirteen recreational athletes participated in this study, which examined the effects of two footwear conditions: one with a 35-mm thick midsole and the other with a 50-mm thick midsole. Participants performed ten running trials around each of three turns of radii 3, 6 and 9 m. No significant differences were found between footwear conditions with respect to time to completion (p = 0.028), centre of mass velocity (p = 0.179) or frontal plane ankle angle (p = 0.935) across any of the three turns. These findings would suggest footwear manufactures need not consider the impact of midsole thickness on turn running performance when designing advanced footwear technology (AFT) and consumers need not avoid a substantial stack height when purchasing running shoes.

Quantitative analysis of the dominant external factors influencing elite speed Skaters' performance using BP neural network.

Speed skating, being a popular winter sport, imposes significant demands on elite skaters, necessitating their effective assessment and adaptation to diverse environmental factors to achieve optimal race performance. The aim of this study was to conduct a thorough analysis of the predominant external factors influencing the performance of elite speed skaters. A total of 403 races, encompassing various race distances and spanning from the 2013 to the 2022 seasons, were examined for eight high-caliber speed skaters from the Chinese national team. We developed a comprehensive analytical framework utilizing an advanced back-propagation (BP) neural neural network model to assess three key factors on race performance: ice rink altitude, ice surface temperature, and race frequency. Our research indicated that the performance of all skaters improves with higher rink altitudes, particularly in races of 1,000 m and beyond. The ice surface temperature can either enhance or impaire performance and varies in its influences based on skaters' technical characteristics, which had a perceptible or even important influence on races of 1,500 m and beyond, and a negligible influence in the 500 m and 1,000 m races. An increase in race frequency generally contributed to better performance. The influence was relatively minor in the 500 m race, important in the 3,000 m race, and varied among individuals in the 1,000 m and 1,500 m races. The study results offer crucial guidelines for speed skaters and coaches, aiding in the optimization of their training and competition strategies, ultimately leading to improved competitive performance levels.

Cycling is the most important predictive split discipline in professional Ironman® 70.3 triathletes.

Our study examined 16,611 records of professional triathletes from 163 Ironman® 70.3 races across 97 countries (2004-2020). The aim was to identify the most predictive discipline-swim, bike, or run-for overall race time. We used correlation matrices to compare the dependent variable "finish time" with independent variables "swim time," "bike time," and "run time." This analysis was conducted separately for male and female athletes. Additionally, univariate and multiple linear regression models assessed the strength of these associations. The results indicated that "bike time" had the strongest correlation with finish time (0.85), followed by "run time" (0.75 for females, 0.82 for males) and "swim time" (0.46 for females, 0.63 for males). Regression models confirmed "bike time" as the strongest predictor of overall race time (R² = 0.8), with "run time" and "swim time" being less predictive. The study concludes that in Ironman 70.3 races, "bike time" is the most significant predictor of overall race performance for both sexes, suggesting a focus on cycling in training and competition strategies. It also highlights a smaller performance gap between genders in swimming than in cycling or running.

The relationships between age and race performance in women’s road cycling

ABSTRACT We investigate the relationships between age and race performance in women’s road cycling. Therefore, we consider public data from ProCyclingStats (PCS) on race results of 558 female riders present in the top 500 of one of the yearly rankings between 1993 and 2021. We apply a data-driven approach consisting of three subsequent steps. First, we train decision tree classifiers to distinguish between race profiles. Second, we cluster the riders based on the fraction of PCS points obtained in different race types and uniquely identified the speciality of a rider as Sprinter, All Rounder or One Day. Third, we use polynomial regression to determine relationships between age and a rider’s yearly race performance, defined as the average number of points per race entered in a single year, for each cluster. We obtain that the yearly performance is independent of age for one-day specialists. For sprinters and all-rounders, we found that the race performance increases until it reaches a maximum at 28.7 (sprinters) and 27.0 (all-rounders) years and then decreases again. Our findings can be used as a benchmarking tool for monitoring the development of women’s road cyclists, talent identification or constructing long-term training programmes.

QUICKeR: Quicker Updates Involving Continuous Key Rotation

Since the advent of cloud computing, storing large quantities of sensitive data on remote services have demanded secure encryption practices to maintain data privacy. Merely encrypting data at-rest leaves ciphertexts vulnerable to inevitable key leakage from mismanaged keys, side-channel attacks, and security bugs. To combat this, we propose QUICKeR, a system to facilitate continuous key rotation and ciphertext updates. Unfortunately, continuous ciphertext updates from key rotation interferes with routine access operations by introducing race conditions and performance bottlenecks that preclude prior works from practical use. QUICKeR addresses these concerns through protocols that eliminate race conditions and even achieve the stronger linearizability correctness criterion. In addition, QUICKeR proposes three approaches to implement frequent ciphertext updates. We show how these different update schemes perform under different database bottlenecks. Finally, we demonstrate that QUICKeR is practical through end-to-end experiments showing that routine access operations are not significantly impacted by ciphertext update operations.

Barriers and facilitators to physical activity: A comparative analysis of transplant athletes competing in high intensity sporting events with other transplant recipients.

There is widespread recognition that many transplant recipients struggle to become and remain physically active. However, some transplant recipients do undertake strenuous training and significant physical activity (PA) and participate in intensive sports. This study sought to understand facilitators and barriers to be physically active for Transplant Athletes (TXA) compared to a group of Dutch transplantees. This explorative mixed methods study analysed race performance and interview data from TxA who participated in cycling and/or the sprint triathlon at the World Transplant Games 2023, and compared their lived experiences in terms of barriers and facilitators of PA with those of 16 transplantees in a study from the Netherlands previously published in this journal. Using Patient and Public Involvement and engagement (PPI), race data from World Transplant Games 2023 and subsequent in-depth interviews were used from 27 TxA. A visual artefact of barriers and facilitators from the previous Dutch study was used to prompt identification and discussion of barriers and facilitators of PA. Interview data were coded by three coders. Many of the barriers to PA previously reported by Dutch transplant recipients were not shared by the majority of TxA in this study. The TxA in this study reported significantly lower physical limitations, lower fear to undertake exercise, and no comorbidity issues for TxA. Furthermore, TxA perceived they received substantial social support, had the strength to do PA, and were in control of their weight. Several TxA reported a lack of understanding from medical and other professionals about the appropriate intensity of PA. An evidence-based framework of PA for transplant recipients and transplant athletes is needed for safe and appropriate PA.

What Determines the Number of Social Media Followers of Professional Cyclists: A Statistical Analysis

This paper examines which factors influence the change in the number of followers of professional cyclists on social media using a fixed-effects model on 33 days of panel data regarding the performance, activity, and content of Twitter messages of 795 cyclists. The analysis shows that a better race performance leads to more new followers. Posting social tweets has no effect, but posting social retweets does increase the number of new followers for riders with a low or medium number of followers. For parasocial tweets, the reverse is true: Parasocial retweets have no effect, while parasocial noninteractive tweets have a positive significant effect for riders with a low or high number of followers. Finally, for riders with a high number of followers, posting a general question to followers has a positive impact on the number of new followers. Cyclists and teams can use the results of this study to identify over- and underperformers in terms of social media success and to attract more followers with all the associated benefits.

COGNITIVE CHARACTERISTICS AND SOME FACTORS AFFECTING THE SPRINT AND MEMORY COURSE PERFORMANCE OF ORIENTEERS

It is known that physical, psychological, and cognitive characteristics are important in orienteering. However, no studies have investigated the effects of cognitive characteristics on performance in practice. This study aimed to determine the effect levels of the different variables of elite male orienteers (i.e., success rate, year of sports experience, short-term memory, visual memory, attention, and concentration) on their performance in two orienteering courses (sprint and memory courses). A total of 36 voluntary elite male athletes who had been orienteering for at least two years, over 18, with a mean age of 24.58±4.85 years and sports experience of 7.83±3.56 years participated in the study. The Cognitrone, VISGED visual memory, d2 attention, and serial digit learning tests were applied to all participants, respectively. All participants ran the memory and sprint orienteering courses at 72-hour intervals in a randomized manner. Afterward, the effects of the athletes’ cognitive performance and some characteristics on the course completion time were examined. According to the results of the linear regression analysis, the model’s independent variables that affected the winning time of the sprint course were the success rate, short-term memory score, and concentration (R= .505, R2= .255, F=3.193, p=.003, p&lt;.01). Among these variables, the variable that predicted the winning time of the sprint course the most was the success rate (B=-244.25, Beta=-0.473, P=.015, p&lt;.05). Year of sports experience, success rate, short-term memory score, concentration, and cog-correct response time were the independent variables affecting the winning time of the memory course (R=.620, R2=.385, F= 3.374, p=.000, p&lt;.001). Year of sports experience was the independent variable with the highest effect on the winning time of the memory course (B=-6.718, Beta=-0.369, p=.029, p&lt;.05). The factors affecting the sprint and memory courses' winning time were examined, and it was concluded that the orienteers' years of sports experience and successes affected the course winning time. These findings suggest that orienteering race performance is more related to the experience of transferring them to orienteering and creating tactical processes rather than the cognitive characteristics of orienteers.

Hurdling on home straight in the women 3000m steeplechase

The 3000m steeplechase is an event in which athletes must clear 28 hurdles and 7 water jumps while competing for the fastest time. In this race, women must clear hurdles set at a height of 0.762 meters, whereas men face hurdles set at a height of 0.914 meters. There is a paucity of research on the 3000m steeplechase compared to other long-distance events. This study aimed to clarify the characteristics of hurdle clearance for the 3000m steeplechase. Investigating how to clear the hurdles on the home straight could significantly enhance race strategies and performance. Data were collected from the women’s 3000m steeplechase races at Kanto intercollegiate race. 15 women’s performances were analyzed. The 3000m steeplechase races were recorded by video camera. All jumps from participants were digitized using Kinovea (version 0.9.3). I focused on variables of three steps related to the three steps around hurdles, and comparisons were made among each lap. In terms of total clearance speed, we observed that lap 4 had a lower speed than lap 3, and lap 7 had a higher speed than lap 4. Before the increase in speed at the hurdle, there was an increase in the length of three steps in lap 7. Athletes in the final lap took off from a longer distance and achieved a faster clearance speed. The step frequency before hurdle clearance was higher in lap1 and lap2 than in lap4, lap5, lap6, and lap7. In addition, step frequency after hurdle clearance did not differ among laps and was lower than before hurdle clearance. Fatigue might be a contributing factor to this decline in step frequency before hurdle clearance. It would be advantageous for athletes to consciously increase their step frequency when approaching the next hurdle. The present study provided practical evidence for hurdle clearance of 3000m steeplechase.

Biomechanical changes identified during a marathon race among high-school aged runners

BackgroundDespite the increasing popularity of endurance running competitions among adolescent runners, there is currently limited information regarding expected biomechanical changes across the duration of a long-distance running event, and the relationship between young runners’ biomechanics and running performance. Wearable technology offers an ecological means to continuously assess runners’ biomechanical data during outdoor running competitions. Research questionDo adolescent athletes adopt changes in sensor-derived biomechanics throughout a marathon race, and are there relationships between race performance and biomechanical features among young marathoners? MethodsFourteen high-school aged runners (9 M, 5 F; age: 16 ± 1 years, height: 170.8 ± 7.5 cm; mass: 63.6 ± 9.4 kg) wore lace-mounted sensors to record step-by-step biomechanics during a marathon race. Official race segment completion times were extracted across 5 race segments (5-K, 15-K, Half Marathon [21.1-K], 35-K, Marathon [42.2-K]). Within-participant repeated measures of covariance (pace) were conducted to assess changes in biomechanics across the race, with Bonferroni post-hoc comparisons. Pearson’s r correlations were performed to assess the relationship between race finish times and biomechanics. ResultsPace was significantly slower (p-range: 0.002–0.005), contact times significantly longer, and stride lengths significantly shorter in the final segment compared to middle segments (p-range: 0.003–0.004). The rate of shock accumulation was significantly higher in the final race segment compared to the first three segments (p-range: 0.001–0.002). Moderate relationships existed between finish times and pace (r = −0.63), stride length (r = −0.62), and contact time (r = 0.51). SignificanceAdolescent runners altered their gait patterns in the final marathon segment compared to earlier segments. Spatiotemporal measures were moderately correlated with race finish times, suggesting a link between faster run pace, increased stride lengths, and reduced contact time for improved running performance during an endurance race.

Abstract 14060: Health Disparities in Exercise Performance in Tetralogy of Fallot

Introduction: Patients with tetralogy of Fallot (TOF) from disadvantaged racial and ethnic groups are reported to have worse outcomes, including worse exercise performance. The underlying mechanisms are not fully understood. Hypothesis: We hypothesize that the association of exercise performance with race is mediated by socioeconomic factors. Methods: We conducted a single center retrospective cohort study of TOF patients aged 8 - 30 years who underwent maximal exercise stress testing (EST) from 2007 - 2020. The primary outcome was percent-predicted maximum oxygen consumption (VO2). Addresses were geocoded. The Childhood Opportunity Index (COI) and its three domains represented neighborhood socioeconomic status. Generalized linear models and mediation analysis were used (Figure). Results: We included 154 subjects who underwent 273 ESTs (Table). Correcting for age at EST, sex, outflow tract repair type, and body mass index, those of non-Hispanic Black race had an 8.6% lower percent-predicted VO2 (95% CI -15.0, -2.2) than those of non-Hispanic white race. Mediation analysis showed that the COI mediates 90% of this relationship. By domain, Education is the strongest mediator and alone can account for 75% of this relationship. Conclusions: Disparities exist in exercise performance after TOF repair. Neighborhood-level factors, in particular related to Education, are significant mediators of the relationship between race and exercise performance in TOF. A detailed understanding of the driving mechanisms underlying health disparities, particularly those that are modifiable, is critical to eliminating those disparities at both the patient and societal levels.

The improvements to the minimum curvature race line optimization

Motorsports is gaining increasingly large and broad attention and simulations using modern information technology on race performance are in demand. This paper focuses on the improvements of the minimum curvature method on optimal racing lines for a race car. The key contribution of the improvements is to generate a more realistic optimal racing line, therefore getting a better description of the car and driver performance. The improvements contain the introduction of the kerb of the track and the late apex technique applied by drivers during the race. The effect of two improvements is verified in the simulation racing software Assetto Corsa and the result shows that the introduction of the kerb raises the lap time accuracy by 90% and the late apex trajectory is matched with the actual path.