{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T17:16:18Z","timestamp":1793812578526,"version":"4.6.1"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Sports Act. Living"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>In professional cycling, the technical characteristics of race stages significantly influence group dynamics and performance variability among competitors. However, stage classifications have traditionally been subjective, lacking a robust empirical foundation. This study aimed to develop an objective, technical classification of professional cycling stages using unsupervised learning (KMeans) and analyze how these categories relate to collective performance variability, measured by the coefficient of variation (CV) of finish times.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Technical data and official results from 439 international race stages conducted between 2017 and 2023 were analyzed. The technical variables included distance, total vertical gain, average relative elevation, and percentages of paved and unpaved surfaces.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Cluster validation via Bootstrap analysis demonstrated high stability (mean silhouette index\u2009=\u20090.62\u2009\u00b1\u20090.03), confirming six clearly distinct technical stage groups. Results indicated that stages characterized by higher relative elevation and greater proportions of unpaved surfaces exhibited higher performance variability (higher CV),whereas less technically demanding stages showed lower variability; relative elevation emerged as the strongest predictor of CV (<jats:italic>\u03b2<\/jats:italic>\u2009=\u20090.42, <jats:italic>p<\/jats:italic>\u2009&amp;lt;\u20090.001), followed by unpaved percentage (<jats:italic>\u03b2<\/jats:italic>\u2009=\u20090.23, <jats:italic>p<\/jats:italic>\u2009&amp;lt;\u20090.01), distance (<jats:italic>\u03b2<\/jats:italic>\u2009=\u20090.18, <jats:italic>p<\/jats:italic>\u2009&amp;lt;\u20090.05), and vertical gain (<jats:italic>\u03b2<\/jats:italic>\u2009=\u20090.11, <jats:italic>p<\/jats:italic>\u2009&amp;lt;\u20090.05). Across 2017\u20132023, a broadly downward pattern in CV was observed, although a pooled linear-trend test with cluster fixed effects did not reach statistical significance (<jats:italic>p<\/jats:italic>\u2009=\u20090.315).<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The lack of physiological data and possible confounding from unmeasured stage and team factors (e.g., weather, stage order, team tactics) limit causal inference. This empirical typology provides a valuable quantitative tool to optimize competitive strategies, plan targeted training based on stage type, and prevent cumulative fatigue and performance-related injuries in high-performance cycling. Future research incorporating direct physiological data is recommended to further explore the relationship between external and internal load in professional cycling.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fspor.2025.1661456","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T05:42:22Z","timestamp":1760506942000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Technical classification of professional cycling stages using unsupervised learning: implications for performance variability"],"prefix":"10.3389","volume":"7","author":[{"given":"Igor","family":"Garcia-Atutxa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ekaitz","family":"Dudagoitia Barrio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisca","family":"Villanueva-Flores","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1080\/17461391.2018.1554706","article-title":"Physical demands and power profile of different stage types within a cycling grand tour","volume":"19","author":"Sanders","year":"2019","journal-title":"Eur J Sport Sci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"325","DOI":"10.2165\/00007256-200131050-00004","article-title":"Physiology of professional road cycling","volume":"31","author":"Luc\u00eda","year":"2001","journal-title":"Sports Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"239","DOI":"10.2165\/00007256-200838030-00004","article-title":"Describing and understanding pacing strategies during athletic competition","volume":"38","author":"Abbiss","year":"2008","journal-title":"Sports Med Auckl NZ"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1903","DOI":"10.1249\/MSS.0000000000002656","article-title":"Maintaining power output with accumulating levels of work done is a key determinant for success in professional cycling","volume":"53","author":"VAN Erp","year":"2021","journal-title":"Med Sci Sports Exerc"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.1080\/02640414.2016.1215504","article-title":"Knowledge is power: issues of measuring training and performance in cycling","volume":"35","author":"Passfield","year":"2017","journal-title":"J Sports Sci"},{"key":"B6","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1097\/00005768-200103000-00013","article-title":"Cardiorespiratory and metabolic characteristics of detraining in humans","volume":"33","author":"Mujika","year":"2001","journal-title":"Med Sci Sports Exerc"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1016\/j.jsams.2022.10.001","article-title":"Road gradient and cycling power: an observational study in male professional cyclists","volume":"25","author":"Valenzuela","year":"2022","journal-title":"J Sci Med Sport"},{"key":"B8","first-page":"5083","article-title":". Experimental modeling of cyclists fatigue and recovery dynamics enabling optimal pacing in a time trial","author":"Ashtiani","year":"2019"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1212573","article-title":"Internal and external load during on-field training drills with an aim of improving the physical performance of players in professional soccer: a retrospective observational study","volume":"14","author":"Ammann","year":"2023","journal-title":"Front Physiol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1186\/s13102-024-00983-6","article-title":"The impact of internal and external loads on player performance in Chinese basketball association","volume":"16","author":"Li","year":"2024","journal-title":"BMC Sports Sci Med Rehabil"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2024.1419097","article-title":"Quarterly fluctuations in external and internal loads among professional basketball players","volume":"15","author":"Yang","year":"2024","journal-title":"Front Physiol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1123\/ijspp.2021-0403","article-title":"The record power profile of male professional cyclists: fatigue matters","volume":"17","author":"Mateo-March","year":"2022","journal-title":"Int J Sports Physiol Perform"},{"key":"B13","doi-asserted-by":"publisher","first-page":"100113","DOI":"10.1016\/j.crphys.2023.100113","article-title":"Physiological and performance effects of live high train low altitude training for elite endurance athletes: a narrative review","volume":"6","author":"Bonato","year":"2023","journal-title":"Curr Res Physiol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2729","DOI":"10.1080\/00423114.2024.2304031","article-title":"Cycling on rough roads: a model for resistance and vibration","volume":"62","author":"Turner","year":"2024","journal-title":"Veh Syst Dyn"},{"key":"B15","doi-asserted-by":"publisher","first-page":"6977","DOI":"10.1007\/s10994-024-06585-0","article-title":"Methodology and evaluation in sports analytics: challenges, approaches, and lessons learned","volume":"113","author":"Davis","year":"2024","journal-title":"Mach Learn"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0267009","article-title":"An unsupervised machine learning approach to evaluate sports facilities condition in primary school","volume":"17","author":"Xia","year":"2022","journal-title":"PLoS One"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/14763141.2024.2372608","article-title":"Clustering analysis across different speeds reveals two distinct running techniques with no differences in running economy","volume":"11","author":"Rivadulla","year":"2024","journal-title":"Sports Biomech"},{"key":"B18","doi-asserted-by":"publisher","first-page":"111136","DOI":"10.1016\/j.jbiomech.2022.111136","article-title":"A hierarchical clustering approach for examining potential risk factors for bone stress injury in runners","volume":"141","author":"Martin","year":"2022","journal-title":"J Biomech"},{"key":"B19","article-title":"Investigating swimming technical skills by a double partition clustering of multivariate functional data allowing for dimension selection [Internet]","author":"Bouvet","year":"2023"},{"key":"B20","doi-asserted-by":"publisher","first-page":"101083","DOI":"10.1016\/j.bjpt.2024.101083","article-title":"Artificial intelligence and machine learning approaches in sports: concepts, applications, challenges, and future perspectives","volume":"28","author":"Reis","year":"2024","journal-title":"Braz J Phys Ther"},{"key":"B21","volume-title":"An Examination of the Factors Determining the Performance of Cyclists in Elite Competitions","author":"Phillips","year":"2020"},{"key":"B22","doi-asserted-by":"publisher","first-page":"955","DOI":"10.3390\/e25060955","article-title":"Shannon entropy and Herfindahl-Hirschman index as team\u2019s performance and competitive balance indicators in cyclist multi-stage races","volume":"25","author":"Ausloos","year":"2023","journal-title":"Entropy"},{"key":"B23","article-title":"Geospatial Road Cycling Race Results Data Set","author":"Janssens","year":"2024"},{"key":"B24","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans Inf Theory"},{"key":"B25","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J Comput Appl Math"},{"key":"B26","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","article-title":"Principal component analysis","volume":"2","author":"Wold","year":"1987","journal-title":"Chemom Intell Lab Syst"},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding Groups in Data: An Introduction to Cluster Analysis [Internet]","author":"Kaufman","year":"1990"},{"key":"B28","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.proeng.2013.07.062","article-title":"On optimization of pacing strategy in road cycling","volume":"60","author":"Sundstr\u00f6m","year":"2013","journal-title":"Procedia Eng"},{"key":"B29","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1007\/s00421-021-04833-y","article-title":"Power profiling and the power-duration relationship in cycling: a narrative review","volume":"122","author":"Leo","year":"2022","journal-title":"Eur J Appl Physiol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"S91","DOI":"10.1080\/02640414.2011.610348","article-title":"Nutrition for endurance sports: marathon, triathlon, and road cycling","volume":"29","author":"Jeukendrup","year":"2011","journal-title":"J Sports Sci"},{"key":"B31","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1123\/ijsnem.2018-0289","article-title":"Toward a common understanding of diet-exercise strategies to manipulate fuel availability for training and competition preparation in endurance sport","volume":"28","author":"Burke","year":"2018","journal-title":"Int J Sport Nutr Exerc Metab"}],"container-title":["Frontiers in Sports and Active Living"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fspor.2025.1661456\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T05:42:24Z","timestamp":1760506944000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fspor.2025.1661456\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":31,"alternative-id":["10.3389\/fspor.2025.1661456"],"URL":"https:\/\/doi.org\/10.3389\/fspor.2025.1661456","relation":{},"ISSN":["2624-9367"],"issn-type":[{"value":"2624-9367","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]},"article-number":"1661456"}}