{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:08:01Z","timestamp":1792022881706,"version":"4.4.0"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Marathon running has evolved into a global phenomenon, with rising participation across age and experience groups. Training for a marathon requires adherence to well-established principles involving pacing, training volume, and periodization. With the increasing integration of artificial intelligence (AI) into healthcare and fitness, it remains unclear whether AI can reliably prescribe evidence-based training programs for such demanding endurance events.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Sources of data<\/jats:title>\n                    <jats:p>We conducted a descriptive study using outputs from leading AI models: Claude 3.5 Sonnet, Claude 3.5 Haiku (Free), ChatGPT 4.0 (o-model), ChatGPT 0.1, ChatGPT 4 (free), Gemini 2.0 Flash, Gemini 2.0 Flash Thinking, and DeepSeek R1. Each was prompted to generate a 6-month marathon training plan tailored to three athlete levels: Beginner, Intermediate, and Advanced. Outputs were compared with peer-reviewed literature on the determinants of marathon training.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Areas of agreement<\/jats:title>\n                    <jats:p>Most AI systems identified key training components: weekly mileage progression, tapering, and intensity distribution (&amp;gt;80% at low intensity), which aligns with current endurance training theory.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Areas of controversy<\/jats:title>\n                    <jats:p>AI responses varied in accuracy and completeness. Some engines omitted key details (e.g. weekly mileage), failed to differentiate clearly between athlete levels (intermediate and advanced have been merged as if they were the same level), or offered inconsistent pacing data, especially for advanced runners. This descriptive analysis evaluated qualitative adherence to evidence-based training principles rather than quantitative outcomes requiring statistical inference.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Growing points<\/jats:title>\n                    <jats:p>AI demonstrates strong potential in accessible, structured training content. When properly prompted, outputs often align with contemporary training principles, though significant limitations regarding personalization and professional oversight necessitate further validation before clinical implementation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Areas timely for developing research<\/jats:title>\n                    <jats:p>Future studies should evaluate the real-world outcomes of AI-generated programs in randomized trials including the integration of personal physiological data. Inizio moduloFine modulo.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bmb\/ldag010","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T12:21:54Z","timestamp":1770034914000},"source":"Crossref","is-referenced-by-count":2,"title":["Artificial intelligence\u2013generated marathon training programs: reliable tools in exercise prescription for athletic performance?"],"prefix":"10.1093","volume":"157","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4294-4911","authenticated-orcid":false,"given":"Gianluca","family":"Montaruli","sequence":"first","affiliation":[{"name":"Le Club Gym , 29121 Piacenza ,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8030-7122","authenticated-orcid":false,"given":"Pantelis Theodoros","family":"Nikolaidis","sequence":"additional","affiliation":[{"name":"School of Health and Caring Sciences, University of West Attica , 12243 Athens ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5171-7026","authenticated-orcid":false,"given":"Ghazi","family":"Racil","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Higher Institute of Sport and Physical Education of Gafsa , 2112 Gafsa ,","place":["Tunisia"]},{"name":"Research Unit (LR 23JS01) \u201cSport Performance, Health & Society\u201d Higher Institute of Sport and Physical Education of Ksar Said , 1000 Tunis ,","place":["Tunisia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-3702","authenticated-orcid":false,"given":"Nicola","family":"Maffulli","sequence":"additional","affiliation":[{"name":"Department of Trauma and Orthopaedic Surgery, Faculty of Medicine and Psychology, Sapienza University of Rome , 00166 Rome ,","place":["Italy"]},{"name":"Institute of Science and Technology in Medicine, Guy Hilton Research Centre, School of Medicine, Keele University , ST5 5BG Stoke-On-Trent ,","place":["United Kingdom"]},{"name":"Centre for Sports and Exercise Medicine, Barts and the London School of Medicine and Surgery, Queen Mary University of London , E1 4NS London ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7144-7403","authenticated-orcid":false,"given":"Gian Mario","family":"Migliaccio","sequence":"additional","affiliation":[{"name":"Department of Human Sciences and Promotion of the Quality of Life, San Raffaele Rome Open University , Rome 00166 ,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4254-3105","authenticated-orcid":false,"given":"Johnny","family":"Padulo","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences for Health, Universit\u00e0 degli Studi di Milano , 20133 Milan ,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"2026022113594602100_ref1","doi-asserted-by":"crossref","first-page":"631237","DOI":"10.3389\/fphys.2021.631237","article-title":"Increased participation and decreased performance in recreational master athletes in \u201cBerlin Marathon\u201d 1974\u20132019","volume":"12","author":"Reusser","year":"2021","journal-title":"Front Physiol"},{"key":"2026022113594602100_ref2","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1186\/s40064-015-1254-6","article-title":"Participation and performance trends in elderly marathoners in four of the world\u2019s largest marathons during 2004\u20132011","volume":"4","author":"Ahmadyar","year":"2015","journal-title":"Springerplus."},{"key":"2026022113594602100_ref3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fphys.2024.1388565","article-title":"Themes and trends in marathon performance research: a comprehensive bibliometric analysis from 2009 to 2023","volume":"15","author":"Yan","year":"2024","journal-title":"Front Physiol"},{"key":"2026022113594602100_ref4","first-page":"172","article-title":"Classifying running related injuries based upon etiology, with emphasis on volume and pace","volume":"8","author":"Oestergaard","year":"2013","journal-title":"Int J Sports Phys Ther"},{"key":"2026022113594602100_ref5","doi-asserted-by":"publisher","first-page":"e0114937","DOI":"10.1371\/journal.pone.0114937","article-title":"Injuries in runners; a systematic review on risk factors and sex differences","volume":"10","author":"Van Der Worp","year":"2015","journal-title":"PloS One"},{"key":"2026022113594602100_ref6","doi-asserted-by":"crossref","first-page":"862807","DOI":"10.3389\/fcvm.2022.856875","article-title":"Factors influencing running performance during a marathon: breaking the 2-h barrier","volume":"9","author":"Venturini","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"2026022113594602100_ref7","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1152\/jappl.1991.70.2.683","article-title":"Modeling: optimal marathon performance on the basis of physiological factors","volume":"70","author":"Joyner","year":"2018","journal-title":"J Appl Physiol February"},{"key":"2026022113594602100_ref8","doi-asserted-by":"publisher","first-page":"e36760","DOI":"10.1016\/j.heliyon.2024.e36760","article-title":"Pacing strategies in marathons: a systematic review","volume":"10","author":"Sha","year":"2024","journal-title":"Heliyon"},{"key":"2026022113594602100_ref9","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1093\/oxfordjournals.bmb.a070856","article-title":"Artificial intelligence","volume":"27","author":"Longuet-Higgins","year":"1971","journal-title":"Br Med Bull"},{"key":"2026022113594602100_ref10","doi-asserted-by":"crossref","first-page":"1505692","DOI":"10.3389\/fmed.2024.1505692","article-title":"Evolution of artificial intelligence in healthcare: a 30-year bibliometric study","volume":"11","author":"Xie","year":"2024","journal-title":"Front Med (Lausanne)"},{"key":"2026022113594602100_ref11","doi-asserted-by":"publisher","first-page":"5649","DOI":"10.1007\/s00146-025-02299-6","article-title":"The assisted technology dilemma: a reflection on AI chatbots use and risks while reshaping the peer review process in scientific research","volume":"40","author":"Ben Saad","year":"2025","journal-title":"AI Soc"},{"key":"2026022113594602100_ref12","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.1007\/s00167-013-2686-6","article-title":"The effect of a six-month training program followed by a marathon run on knee joint cartilage volume and thickness in marathon beginners","volume":"22","author":"Hinterwimmer","year":"2014","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"key":"2026022113594602100_ref13","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1113\/jphysiol.2012.247387","article-title":"A prospective randomized longitudinal study involving 6 months of endurance or resistance exercise. Conduit artery adaptation in humans","volume":"591","author":"Spence","year":"2013","journal-title":"J Physiol"},{"key":"2026022113594602100_ref14","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1123\/ijspp.2024-0366","article-title":"Standardizing the quantification of external load across different training modalities: a critical need in sport-science research","volume":"19","author":"Dhahbi","year":"2024","journal-title":"Int J Sports Physiol Perform"},{"key":"2026022113594602100_ref15","doi-asserted-by":"publisher","first-page":"289","DOI":"10.5114\/biolsport.2025.145911","article-title":"Reproducibility and quality of hypertrophy-related training plans generated by GPT-4 and Google Gemini as evaluated by coaching experts","volume":"42","author":"Havers","year":"2025","journal-title":"Biol Sport"},{"key":"2026022113594602100_ref16","doi-asserted-by":"publisher","first-page":"209","DOI":"10.5114\/biolsport.2024.132987","article-title":"Artificial intelligence in sport: exploring the potential of using ChatGPT in resistance training prescription","volume":"41","author":"Washif","year":"2024","journal-title":"Biol Sport"},{"key":"2026022113594602100_ref17","doi-asserted-by":"publisher","first-page":"305","DOI":"10.5114\/biolsport.2024.141063","article-title":"Optimizing athletic performance through advanced nutrition strategies: can AI and digital platforms have a role in ultraendurance sports?","volume":"41","author":"Puce","year":"2024","journal-title":"Biol Sport"},{"key":"2026022113594602100_ref18","doi-asserted-by":"publisher","first-page":"231","DOI":"10.2147\/OAJSM.S141657","article-title":"Physiological and training characteristics of recreational marathon runners","volume":"8","author":"Gordon","year":"2017","journal-title":"Open Access J Sports Med"},{"key":"2026022113594602100_ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/sports8090116","article-title":"Physiological and race pace characteristics of medium and low-level Athens marathon runners","volume":"8","author":"Myrkos","year":"2020","journal-title":"Sports"},{"key":"2026022113594602100_ref20","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1123\/ijspp.2021-0451","article-title":"Defining training and performance caliber: a participant classification framework","volume":"17","author":"McKay","year":"2022","journal-title":"Int J Sports Physiol Perform"},{"key":"2026022113594602100_ref21","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1111\/sms.13725","article-title":"Training for a (half-)marathon: training volume and longest endurance run related to performance and running injuries","volume":"30","author":"Fokkema","year":"2020","journal-title":"Scand J Med Sci Sports"},{"key":"2026022113594602100_ref22","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1260\/1747-9541.6.2.273","article-title":"Distribution of training volume and intensity of elite male and female track and marathon runners","volume":"6","author":"Enoksen","year":"2011","journal-title":"Int J Sports Sci Coach"},{"key":"2026022113594602100_ref23","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1249\/00005768-199109000-00013","article-title":"Training intensity of elite male distance runners","volume":"23","author":"Robinson","year":"1991","journal-title":"Med Sci Sports Exerc"},{"key":"2026022113594602100_ref24","first-page":"21","article-title":"The accuracy of heart rate-based zone training using predicted versus measured maximal heart rate","volume":"14","author":"Marx","year":"2018","journal-title":"Int J Res Ex Phys"},{"key":"2026022113594602100_ref25","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s40798-022-00438-7","article-title":"The training characteristics of world-class distance runners: an integration of scientific literature and results-proven practice","volume":"8","author":"Haugen","year":"2022","journal-title":"Sports Med Open"},{"key":"2026022113594602100_ref26","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1186\/s40798-024-00717-5","article-title":"Quantitative analysis of 92 12-week sub-elite marathon training plans","volume":"10","author":"Knopp","year":"2024","journal-title":"Sports Med Open"},{"key":"2026022113594602100_ref27","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1123\/ijspp.2021-0435","article-title":"Training periodization, methods, intensity distribution, and volume in highly trained and elite distance runners: a systematic review","volume":"17","author":"Casado","year":"2022","journal-title":"Int J Sports Physiol Perform"},{"key":"2026022113594602100_ref28","doi-asserted-by":"crossref","first-page":"53","DOI":"10.2165\/00007256-200232010-00003","article-title":"The scientific basis for high-intensity interval training: optimising training programmes and maximising performance in highly trained endurance athletes","volume":"32","author":"Laursen","year":"2002","journal-title":"Sports Med"},{"key":"2026022113594602100_ref29","first-page":"229","article-title":"Competitive marathon training","volume":"20","author":"Maffulli","year":"1991","journal-title":"J Hum Mov Stud"},{"key":"2026022113594602100_ref30","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.jsams.2019.09.013","article-title":"An evaluation of the training determinants of marathon performance: a meta-analysis with meta-regression","volume":"23","author":"Doherty","year":"2020","journal-title":"J Sci Med Sport"},{"key":"2026022113594602100_ref31","first-page":"170","article-title":"Marathon finishers and non-finishers characteristics. A preamble to success","volume":"41","author":"Yeung","year":"2001","journal-title":"J Sports Med Phys Fitness"},{"key":"2026022113594602100_ref32","doi-asserted-by":"crossref","first-page":"511","DOI":"10.4100\/jhse.2011.63.05","article-title":"Prediction of marathon performance time on the basis of training indices","volume":"6","author":"Tanda","year":"2011","journal-title":"J Hum Sport Exerc"},{"key":"2026022113594602100_ref33","doi-asserted-by":"publisher","first-page":"293","DOI":"10.14198\/jhse.2022.172.05","article-title":"A simple relationship for predicting marathon performance from training: is it generally applicable?","volume":"17","author":"Tanda","year":"2022","journal-title":"J Hum Sport Ex"},{"key":"2026022113594602100_ref34","first-page":"2473","article-title":"Predicting recreational runners\u2019 marathon performance time during their training preparation","volume":"35","author":"Esteve-Lanao","year":"2019","journal-title":"J Strength Cond Res"},{"key":"2026022113594602100_ref35","first-page":"8","article-title":"Running speed during training and percent body fat predict race time in recreational male marathoners","volume":"51","author":"Barandun","year":"2012","journal-title":"Open Access J Sports Med"},{"key":"2026022113594602100_ref37","doi-asserted-by":"publisher","first-page":"e46170","DOI":"10.7759\/cureus.46170","article-title":"An overview of machine learning applications in sports injury prediction","volume":"15","author":"Amendolara","year":"2023","journal-title":"Cureus"},{"key":"2026022113594602100_ref38","doi-asserted-by":"crossref","first-page":"221","DOI":"10.5114\/biolsport.2024.133661","article-title":"Using artificial intelligence for exercise prescription in personalised health promotion: a critical evaluation of OpenAI\u2019s GPT-4 model","volume":"42","author":"Dergaa","year":"2024","journal-title":"Biol Sport"},{"key":"2026022113594602100_ref39","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1519\/JSC.0000000000001152","article-title":"Predicting marathon time using exhaustive graded exercise test in marathon runners","volume":"30","author":"Till","year":"2016","journal-title":"J Strength Cond Res"},{"key":"2026022113594602100_ref36","doi-asserted-by":"crossref","first-page":"90","DOI":"10.5812\/asjsm.34704","article-title":"Predictor variables for marathon race time in recreational female runners","volume":"3","author":"Schmid","year":"2012","journal-title":"Asian J Sports Med"}],"container-title":["British Medical Bulletin"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bmb\/article-pdf\/157\/1\/ldag010\/67064130\/ldag010.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bmb\/article-pdf\/157\/1\/ldag010\/67064130\/ldag010.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:59:57Z","timestamp":1771700397000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bmb\/article\/doi\/10.1093\/bmb\/ldag010\/8494446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,2]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bmb\/ldag010","relation":{},"ISSN":["0007-1420","1471-8391"],"issn-type":[{"value":"0007-1420","type":"print"},{"value":"1471-8391","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,3]]},"published":{"date-parts":[[2026,1,2]]},"article-number":"ldag010"}}