• Analysis of the 50-mile ultram...

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

Title:
Analysis of the 50-mile ultramarathon distance using a predictive XGBoost model.
Authors:
Turnwald J; Centre for Rehabilitation and Sports Medicine, University Hospital Bern, Inselspital Bern, University of Bern, Bern, Switzerland., Valero D; Ultra Sports Science Foundation, Pierre-Benite, France., Forte P; Higher Institute of Educational Sciences of the Douro, Penafiel, Portugal., Weiss K; Institute of Primary Care, University of Zurich, Zurich, Switzerland., Villiger E; Institute of Primary Care, University of Zurich, Zurich, Switzerland., Thuany M; Faculty of Sports, University of Porto, Porto, Portugal., Scheer V; Ultra Sports Science Foundation, Pierre-Benite, France., Wilhelm M; Centre for Rehabilitation and Sports Medicine, University Hospital Bern, Inselspital Bern, University of Bern, Bern, Switzerland., Andrade M; Physiology Department, Federal University of Sao Paulo, Sao Paulo, Brazil., Cuk I; Faculty of Sport and Physical Education, University of Belgrade, Belgrade, Serbia., Nikolaidis PT; School of Health and Caring Sciences, University of West Attica, Athens, Greece., Knechtle B; Institute of Primary Care, University of Zurich, Zurich, Switzerland. beat.knechtle@hispeed.ch.; Medbase St. Gallen Am Vadianplatz, Vadianstrasse 26, 9001, St. Gallen, Switzerland. beat.knechtle@hispeed.ch.
Source:
Scientific reports [Sci Rep] 2025 Mar 15; Vol. 15 (1), pp. 9016. Date of Electronic Publication: 2025 Mar 15.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
Imprint Name(s):
Original Publication: London : Nature Publishing Group, copyright 2011-
MeSH Terms:
Athletic Performance*/physiology , Boosting Machine Learning Algorithms* , Marathon Running*/physiology, Adult ; Female ; Humans ; Male ; Middle Aged ; Young Adult ; Age Factors ; Algorithms ; Athletes ; Machine Learning ; Running
References:
J Physiol. 2017 May 1;595(9):2949-2954. (PMID: 28028816)
Int J Sport Nutr Exerc Metab. 2019 Mar 1;29(2):130-140. (PMID: 30943823)
Int J Environ Res Public Health. 2020 Apr 08;17(7):. (PMID: 32276349)
Basic Res Cardiol. 2006 Sep;101(5):408-17. (PMID: 16915533)
Int J Environ Res Public Health. 2019 Jul 04;16(13):. (PMID: 31277399)
J Sport Health Sci. 2016 Sep;5(3):349-354. (PMID: 30356518)
Front Physiol. 2018 Jun 01;9:634. (PMID: 29910741)
Front Physiol. 2021 Sep 24;12:738665. (PMID: 34630159)
Age (Dordr). 2014;36(5):9715. (PMID: 25280550)
J Strength Cond Res. 2011 Oct;25(10):2835-42. (PMID: 21946910)
Sci Rep. 2023 Jan 25;13(1):1415. (PMID: 36697457)
Int J Sports Physiol Perform. 2016 Jul;11(7):635-42. (PMID: 26561864)
Scand J Pain. 2021 Jan 06;21(2):364-371. (PMID: 34387950)
Med Sci Sports Exerc. 2023 Dec 1;55(12):2328-2360. (PMID: 37772882)
Int J Environ Res Public Health. 2019 Mar 13;16(6):. (PMID: 30871153)
Int J Sports Physiol Perform. 2014 Nov;9(6):913-24. (PMID: 24584647)
Scand J Pain. 2018 Oct 25;18(4):703-709. (PMID: 30001216)
Springerplus. 2016 Feb 29;5:223. (PMID: 27026917)
J Sports Sci. 2006 Apr;24(4):415-22. (PMID: 16492605)
Percept Mot Skills. 2010 Dec;111(3):681-93. (PMID: 21319608)
Phys Sportsmed. 1982 May;10(5):61-65. (PMID: 29278194)
Clinics (Sao Paulo). 2013 May;68(5):605-11. (PMID: 23778421)
Front Physiol. 2019 Jul 24;10:973. (PMID: 31396109)
Springerplus. 2014 Nov 25;3:693. (PMID: 25520912)
PLoS One. 2021 Sep 16;16(9):e0256888. (PMID: 34529656)
Int J Environ Res Public Health. 2019 Jun 29;16(13):. (PMID: 31261850)
Sci Rep. 2023 Jun 8;13(1):9303. (PMID: 37291186)
Front Physiol. 2022 Jan 04;12:804149. (PMID: 35058806)
Open Access J Sports Med. 2018 Mar 01;9:37-45. (PMID: 29535560)
Age (Dordr). 2014 Apr;36(2):1003-8. (PMID: 24407890)
J Strength Cond Res. 2020 May;34(5):1409-1415. (PMID: 32324710)
Res Sports Med. 2020 Oct-Dec;28(4):507-517. (PMID: 32573266)
Sports Med. 2021 May;51(5):895-915. (PMID: 33502701)
PLoS One. 2017 Feb 10;12(2):e0172121. (PMID: 28187185)
Emerg Med J. 2017 Oct;34(10):637-642. (PMID: 28679502)
J Strength Cond Res. 2017 Aug;31(8):2189-2207. (PMID: 28731980)
Open Access J Sports Med. 2015 Jan 22;6:7-21. (PMID: 25653567)
Springerplus. 2016 May 20;5(1):672. (PMID: 27350909)
Int J Sports Physiol Perform. 2015 Apr;10(3):285-91. (PMID: 25115138)
Clinics (Sao Paulo). 2014 Mar;69(3):203-11. (PMID: 24626948)
Res Sports Med. 2020 Jan-Mar;28(1):121-137. (PMID: 30889965)
Sports Med Open. 2023 Jan 25;9(1):6. (PMID: 36695958)
Age (Dordr). 2014 Feb;36(1):407-16. (PMID: 23591938)
Sports Med. 2015 Oct;45(10):1431-41. (PMID: 26088954)
PLoS One. 2018 Jul 11;13(7):e0199701. (PMID: 29995926)
Sports Med. 2003;33(12):877-88. (PMID: 12974656)
Life Sci. 1996;58(25):2337-43. (PMID: 8649223)
Entry Date(s):
Date Created: 20250316 Date Completed: 20250513 Latest Revision: 20250514
Update Code:
20250515
PubMed Central ID:
PMC11910544
DOI:
10.1038/s41598-025-92581-w
PMID:
40089510
Database:
MEDLINE

Weitere Informationen

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.
(© 2025. The Author(s).)

Declarations. Competing interests: The authors declare no competing interests.