[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124113-en":3,"doc-seo-124113-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124113,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Predicting Daily Recovery During Long-Term Endurance Training Using Machine Learning Analysis - Paper","Purpose: Determine whether machine learning models can predict endurance athletes’ perceived morning recovery status (AM PRS) and day-to-day heart rate variability (HRV) change using routinely collected training, dietary intake, sleep, HRV, and subjective well-being measures. Methods: Daily monitoring of 43 athletes for 12 weeks (3572 days) informed global and individualized models, benchmarked against an intercept-only baseline. Results: Group models reduced error versus baseline; individual performance varied widely, implying person-specific predictors. Conclusion: Group-level recovery can be predicted from commonly measured variables, while improving individual accuracy likely needs additional data.","European Journal of Applied Physiology (2024) 124:3279–3290  \n[https://doi.org/10.1007/s00421-024-05530-2](https://doi.org/10.1007/s00421-024-05530-2)  \nPredicting daily recovery during long‑term endurance training using machine learning analysis  \nJeffrey A. Rothschild1,2 · Tom Stewart1 · Andrew E. Kilding1 · Daniel J. Plews1  \nReceived: 9 September 2022 / Accepted: 14 June 2024 / Published online: 20 June 2024 © The Author(s) 2024  \nAbstract  \nPurpose The aim of this study was to determine if machine learning models could predict the perceived morning recovery status (AM PRS) and daily change in heart rate variability (HRV change) of endurance athletes based on training, dietary intake, sleep, HRV, and subjective well-being measures.  \nMethods Self-selected nutrition intake, exercise training, sleep habits, HRV, and subjective well-being of 43 endurance athletes ranging from professional to recreationally trained were monitored daily for 12 weeks (3572 days of tracking) . Global and individualized models were constructed using machine learning techniques, with the single best algorithm chosen for each model. The model performance was compared with a baseline intercept-only model.  \nResults Prediction error (root mean square error [RMSE]) was lower than baseline for the group models (11.8 vs. 14.1 and 0.22 vs. 0.29 for AM PRS and HRV change, respectively) . At the individual level, prediction accuracy outperformed the baseline model but varied greatly across participants (RMSE range 5.5–23.6 and 0.05–0.44 for AM PRS and HRV change, respectively) .  \nConclusion At the group level, daily recovery measures can be predicted based on commonly measured variables, with a small subset of variables providing most of the predictive power. However, at the individual level, the key variables may vary, and additional data may be needed to improve the prediction accuracy.  \nKeywords Training load monitoring · Cycling · Running · Triathlon · Nutrition · Sleep · HRV  \nAbbreviations  \nHR Heart rate  \nHRV Heart rate variability KNN K-nearest neighbors  \nLASSO Least absolute shrinkage and selection operator MARS Multivariate adaptive regression spline NNET Neural network  \nPRS Perceived recovery status RMSE Root mean squared error  \nsRPE Session rating of perceived exertion SVM Support vector machine  \nCommunicated by Philip D Chilibeck.  \n* Jeffrey A. Rothschild [Jeffrey.Rothschild@aut.ac.nz](Jeffrey.Rothschild@aut.ac.nz)  \n1 Sports Performance Research Institute New Zealand (SPRINZ), Auckland University of Technology, Auckland, New Zealand  \n2 High Performance Sport New Zealand, Auckland, New Zealand  \nIntroduction  \nCoaches and athletes routinely monitor a range of metrics with the hope of gaining insight into how an athlete responds to their training. These can include measures of training load (duration and intensity), heart rate variability (HRV), sleep, diet, and daily measures of subjective well-being, among others (Bourdon et al. 2017). Despite careful planning, there can still be large discrepancies between the training stimulus prescribed by coaches and experienced by athletes (Voet et al. 2021). Improved understanding of an athlete’s training response could allow a training plan to be better tailored to an individual’s needs, help minimize the risks of non-functional overreaching, illness, and/or injury (Halson 2014), and improve the adaptive response to training (Figueiredo et al. 2022 ; Nuuttila et al. 2022) .  \nTraining load refers to the combination of training volume and intensity, and can be measured and classified as either external or internal depending on whether the measurable aspects occur externally or internally to the athlete (Impellizzeri et al. 2019). External training loads are characterized  \nby measures such as distance, power, or speed, whereas internal loads can be represented by heart rate (HR), blood lactate, and session rating of perceived exertion (sRPE)(Halson 2014). Internal load reflects the relative phys","cbCaid1LlxBJiZyP","https://ap.wps.com/l/cbCaid1LlxBJiZyP","pdf",1631974,1,12,"English","en",105,"# Introduction\n## Training load and athlete response\n## Nutrition, sleep, and subjective well-being\n# Methods\n## Participants and daily monitoring\n## Model construction and baseline comparison\n# Results\n## Group-level prediction performance\n## Individual-level variability\n# Conclusion\n## Practical implications for tailoring recovery monitoring","[{\"question\":\"What recovery outcomes were predicted in the study?\",\"answer\":\"The models targeted perceived morning recovery status (AM PRS) and daily change in heart rate variability (HRV change) in endurance athletes.\"},{\"question\":\"How was the dataset collected and how long was tracking conducted?\",\"answer\":\"Forty-three endurance athletes were monitored daily for 12 weeks, generating 3572 days of tracking covering training, diet, sleep, HRV, and subjective well-being.\"},{\"question\":\"Did the machine learning models outperform a baseline?\",\"answer\":\"Yes. Group models produced lower prediction error than an intercept-only baseline for both AM PRS and HRV change, while individual accuracy exceeded the baseline but varied substantially across participants.\"}]","Predicting Daily Recovery During Long-Term Endurance Training Using Machine Learning Analysis - Paper | PDF",1785820480,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-daily-recovery-during-long-term-endurance-training-using-machine-learning-analysis-paper","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-daily-recovery-during-long-term-endurance-training-using-machine-learning-analysis-paper/124113/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What recovery outcomes were predicted in the study?","Question",{"text":75,"@type":76},"The models targeted perceived morning recovery status (AM PRS) and daily change in heart rate variability (HRV change) in endurance athletes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the dataset collected and how long was tracking conducted?",{"text":80,"@type":76},"Forty-three endurance athletes were monitored daily for 12 weeks, generating 3572 days of tracking covering training, diet, sleep, HRV, and subjective well-being.",{"name":82,"@type":73,"acceptedAnswer":83},"Did the machine learning models outperform a baseline?",{"text":84,"@type":76},"Yes. Group models produced lower prediction error than an intercept-only baseline for both AM PRS and HRV change, while individual accuracy exceeded the baseline but varied substantially across participants.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]