Analysis of the 50-mile ultramarathon distance using a predictive XGBoost model

Although the 50-mile ultramarathon is one of the most common race distances, it has received little scientific attention. The objective of this study was to assess how an athlete's age group, sex, nationality, and the race location, affect race speed. Utilizing a dataset with ultramarathon races from 1863 to 2022, a machine learning model based on the XGBoost algorithm was developed to predict the race speed based on the aforementioned variables. Model explainability tools, including model features relative importances and prediction distribution plots were then used to investigate how each feature affects the predicted race speed. The most important features, with respect to the predictive power of the XGBoost model, were the location of the race and the athlete's gender. The top 3 countries with the fastest predicted median race speeds were Slovenia, New Zealand, and Bulgaria for nationality and New Zealand, Croatia, and Serbia for the race location. The fastest median race speed was predicted for the age group 20-24 years, but a marked age-related performance decline only became apparent from the age group 40-44 years onward. Model predictions for male athletes were faster than for female athletes. This study offers insights into factors influencing race speed in 50-mile ultramarathons, which may be beneficial for athletes, coaches, and race organizers. The identification of nationalities and event countries with fast race speeds provides a foundation for further exploration in the field of ultramarathon events.

The influence of origin and race location on performance in IRONMAN® age group triathletes

BACKGROUND

The IRONMAN® (IM) triathlon is a popular multi-sport, where age group athletes often strive to qualify for the IM World Championship in Hawaii. The aim of the present study was to investigate the location of the fastest IM racecourses for age group IM triathletes. This knowledge will help IM age group triathletes find the best racecourse, considering their strengths and weaknesses, to qualify.

OBJECTIVE

To determine the fastest IM racecourse for age group IM triathletes using descriptive and predictive statistical methods.

METHODS

We collected and analyzed 677,702 age group IM finishers' records from 228 countries participating in 444 IM competitions held between 2002 and 2022 across 66 event locations. Locations were ranked by average race speed (performance), and countries were sorted by number of records in the sample (participation). A predictive model was built with race finish time as the predicted variable and the triathlete's gender, age group, country of origin, event location, average air, and water temperatures in each location as predictors. The model was trained with 75% of the available data and was validated against the remaining 25%. Several model interpretability tools were used to explore how each predictor contributed to the model's predictive power, from which we intended to infer whether one or more predictors were more important than the others.

RESULTS

The average race speed ranking showed IM Vitoria-Gasteiz (1 race only), IM Copenhagen (8 races), IM Hawaii (18 races), IM Tallinn (4 races) and IM Regensburg (2 races) in the first five positions. The XG Boost Regressor model analysis indicated that the IM Hawaii course was the fastest race course and that male athletes aged 35 years and younger were the fastest. Most of the finishers were competing in IM triathlons held in the US, such as IM Wisconsin, IM Florida, IM Lake Placid, IM Arizona, and IM Hawaii, where the IM World Championship took place. However, the fastest average times were achieved in IM Vitoria-Gasteiz, IM Copenhagen, IM Hawaii, IM Tallin, IM Regensburg, IM Brazil Florianopolis, IM Barcelona, or IM Austria with the absolutely fastest race time in IM Hawaii. Most of the successful IM finishers originated from the US, followed by athletes from the UK, Canada, Australia, Germany, and France. The best mean IM race times were achieved by athletes from Austria, Germany, Belgium, Switzerland, Finland, and Denmark. Regarding environmental conditions, the best IM race times were achieved at an air temperature of ∼27°C and a water temperature of ∼24°C.

CONCLUSIONS

IM age group athletes who intend to qualify for IM World Championship in IM Hawaii are encouraged to participate in IM Austria, IM Copenhagen, IM Brazil Florianopolis, and/or IM Barcelona in order to achieve a fast race time to qualify for the IM World Championship in IM Hawaii where the top race times were achieved. Most likely these races offer the best ambient temperatures for a fast race time.

The fastest 24-hour ultramarathoners are from Eastern Europe

Ultramarathon running is of increasing popularity, where the time-limited 24-hour run is one of the most popular events. Although we have a high scientific knowledge about different topics for this specific race format, we do not know where the best 24-hour runners originate from and where the fastest races are held. The purpose of the present study was to investigate the origin of these runners and the fastest race locations. A machine learning model based on the XG Boost algorithm was built to predict running speed based on the athlete´s age, gender, country of origin and the country where the race takes place. Model explainability tools were used to investigate how each independent variable would influence the predicted running speed. A sample of 171,358 race records from 63,514 unique runners from 73 countries participating in 24-hour races held in 57 countries between 1807 and 2022 was analyzed. Most of the athletes originated from the USA, France, Germany, Great Britain, Italy, Japan, Russia, Australia, Austria, and Canada. Tunisian athletes achieved the fastest average running speed, followed by runners from Russia, Latvia, Lithuania, Island, Croatia, Slovenia, and Israel. Regarding the country of the event, the ranking looks quite similar to the participation by the athlete, suggesting a high correlation between the country of origin and the country of the event. The fastest 24-hour races are recorded in Israel, Romania, Korea, the Netherlands, Russia, and Taiwan. On average, men were 0.4 km/h faster than women, and the fastest runners belonged to age groups 35-39, 40-44, and 45-49 years. In summary, the 24-hour race format is spread over the world, and the fastest athletes mainly originate from Eastern Europe, while the fastest races were organized in European and Asian countries.

Analysis of over 1 million race records shows runners from East African countries as the fastest in 50-km ultra-marathons

The 50-km ultra-marathon is a popular race distance, slightly longer than the classic marathon distance. However, little is known about the country of affiliation and age of the fastest 50-km ultra-marathon runners and where the fastest races are typically held. Therefore, this study aimed to investigate a large dataset of race records for the 50-km distance race to identify the country of affiliation and the age of the fastest runners as well as the locations of the fastest races. A total of 1,398,845 50-km race records (men, n = 1,026,546; women, n = 372,299) were analyzed using both descriptive statistics and advanced regression techniques. This study revealed significant trends in the performance of 50-km ultra-marathoners. The fastest 50-km runners came from African countries, while the fastest races were found to occur in Europe and the Middle East. Runners from Ethiopia, Lesotho, Malawi, and Kenya were the fastest in this race distance. The fastest 50-km racecourses, providing ideal conditions for faster race times, are in Europe (Luxembourg, Belarus, and Lithuania) and the Middle East (Qatar and Jordan). Surprisingly, the fastest ultra-marathoners in the 50-km distance were found to fall into the age group of 20-24 years, challenging the conventional belief that peak ultra-marathon performance comes in older age groups. These findings contribute to a better understanding of the performance models in 50-km ultra-marathons and can serve as valuable insights for runners, coaches, and race organizers in optimizing training strategies and racecourse selection.

The Role of Nationality in Ultra-Endurance Sports: The Paradigm of Cross-Country Skiing and Long-Distance Running

Although the variation of performance by nationality in endurance sports such as marathon has been well studied, little information exists so far on the role of nationality on performance in ultra-endurance sports. The aim of the present study was to review the role of nationality on cross-country skiing and ultra-endurance running. Scopus and PubMed were searched using the syntax "nationality AND (ultra-endurance OR ultra-marathon OR cross-country skiing) in 1/4/2020. This search identified 17 articles, whose references were further examined for relevant literature. It was observed that Russian athletes dominated ultra-endurance running and cross-country skiing races. It was shown that these races were in other countries, where it was assumed that only the best Russians competed. Potential explanations could be misuse of performance enhancing substances, historical, climate-geographical and psychophysiological (e.g., combination of genetic and social factors). In summary, recent studies found a dominance of Russian athletes in specific races (i.e., 'Comrades Marathon', 'Vasaloppet', and 'Engadin Ski Marathon') and disciplines (i.e., ultra-marathon running, cross-country skiing) over a period of several decades. Future studies are need to investigate other events and other sport disciplines to confirm this Russian dominance.

Different Predictor Variables for Women and Men in Ultra-Marathon Running-The Wellington Urban Ultramarathon 2018

Ultra-marathon races are increasing in popularity. Women are now 20% of all finishers, and this number is growing. Predictors of performance have been examined rarely for women in ultra-marathon running. This study aimed to examine the predictors of performance for women and men in the 62 km Wellington Urban Ultramarathon 2018 (WUU2K) and create an equation to predict ultra-marathon race time. For women, volume of running during training per week (km) and personal best time (PBT) in 5 km, 10 km, and half-marathon (min) were all associated with race time. For men, age, body mass index (BMI), years running, running speed during training (min/km), marathon PBT, and 5 km PBT (min) were all associated with race time. For men, ultra-marathon race time might be predicted by the following equation: (r² = 0.44, adjusted r² = 0.35, SE = 78.15, degrees of freedom (df) = 18) ultra-marathon race time (min) = −30.85 ± 0.2352 × marathon PBT + 25.37 × 5 km PBT + 17.20 × running speed of training (min/km). For women, ultra-marathon race time might be predicted by the following equation: (r² = 0.83, adjusted r² = 0.75, SE = 42.53, df = 6) ultra-marathon race time (min) = −148.83 + 3.824 × (half-marathon PBT) + 9.76 × (10 km PBT) − 6.899 × (5 km PBT). This study should help women in their preparation for performance in ultra-marathon and adds to the bulk of knowledge for ultra-marathon preparation available to men.

Physiology and Pathophysiology in Ultra-Marathon Running

In this overview, we summarize the findings of the literature with regards to physiology and pathophysiology of ultra-marathon running. The number of ultra-marathon races and the number of official finishers considerably increased in the last decades especially due to the increased number of female and age-group runners. A typical ultra-marathoner is male, married, well-educated, and ~45 years old. Female ultra-marathoners account for ~20% of the total number of finishers. Ultra-marathoners are older and have a larger weekly training volume, but run more slowly during training compared to marathoners. Previous experience (e.g., number of finishes in ultra-marathon races and personal best marathon time) is the most important predictor variable for a successful ultra-marathon performance followed by specific anthropometric (e.g., low body mass index, BMI, and low body fat) and training (e.g., high volume and running speed during training) characteristics. Women are slower than men, but the sex difference in performance decreased in recent years to ~10–20% depending upon the length of the ultra-marathon. The fastest ultra-marathon race times are generally achieved at the age of 35–45 years or older for both women and men, and the age of peak performance increases with increasing race distance or duration. An ultra-marathon leads to an energy deficit resulting in a reduction of both body fat and skeletal muscle mass. An ultra-marathon in combination with other risk factors, such as extreme weather conditions (either heat or cold) or the country where the race is held, can lead to exercise-associated hyponatremia. An ultra-marathon can also lead to changes in biomarkers indicating a pathological process in specific organs or organ systems such as skeletal muscles, heart, liver, kidney, immune and endocrine system. These changes are usually temporary, depending on intensity and duration of the performance, and usually normalize after the race. In longer ultra-marathons, ~50–60% of the participants experience musculoskeletal problems. The most common injuries in ultra-marathoners involve the lower limb, such as the ankle and the knee. An ultra-marathon can lead to an increase in creatine-kinase to values of 100,000–200,000 U/l depending upon the fitness level of the athlete and the length of the race. Furthermore, an ultra-marathon can lead to changes in the heart as shown by changes in cardiac biomarkers, electro- and echocardiography. Ultra-marathoners often suffer from digestive problems and gastrointestinal bleeding after an ultra-marathon is not uncommon. Liver enzymes can also considerably increase during an ultra-marathon. An ultra-marathon often leads to a temporary reduction in renal function. Ultra-marathoners often suffer from upper respiratory infections after an ultra-marathon. Considering the increased number of participants in ultra-marathons, the findings of the present review would have practical applications for a large number of sports scientists and sports medicine practitioners working in this field.

The Russians Are the Fastest in Marathon Cross-Country Skiing: The "Engadin Ski Marathon"

It is well known that athletes from a specific region or country are dominating certain sports disciplines such as marathon running or Ironman triathlon; however, little relevant information exists on cross-country skiing. Therefore, the aim of the present study was to investigate the aspect of region and nationality in one of the largest cross-country skiing marathons in Europe, the “Engadin Ski Marathon.” All athletes (n = 197,125) who finished the “Engadin Ski Marathon” between 1998 and 2016 were considered. More than two-thirds of the finishers (72.5% in women and 69.6% in men) were Swiss skiers, followed by German, Italian, and French athletes in both sexes. Most of the Swiss finishers were from Canton of Zurich (20.5%), Grisons (19.2%), and Berne (10.3%). Regarding performance, the Russians were the fastest and the British the slowest. Considering local athletes, finishers from Canton of Uri and Glarus were the fastest and those from Canton of Geneva and Basel the slowest. Based on the findings of the present study, it was concluded that local athletes were not the fastest in the “Engadin Ski Marathon.” Future studies need to investigate other cross-country skiing races in order to find the nationalities and regions of the fastest cross-country skiers.