[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118188-en":3,"doc-seo-118188-105":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},118188,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Learning from Machine Learning - Prediction of Age-Related Athletic Performance Decline Trajectories","Age-related decline in physical performance varies strongly between individuals, yet the determinants of individual decline rates and trajectory prediction remain poorly understood. Conventional linear or quadratic regressions often produce high errors for single athletes. This study tests whether a machine-learning model can predict a master athlete’s performance development from a single measurement and outperforms average or individually shifted decline curves. Results use a multilayer neuronal network and provide visualization-based insights into factors shaping decline trajectories.","GeroScience (2021) 43:2547–2559  \n[https://doi.org/10.1007/s11357-021-00411-4](https://doi.org/10.1007/s11357-021-00411-4)  \nLearning from machine learning: prediction of age‑related athletic performance decline trajectories  \nChristoph Hoog Antink  ·  \nAnne K. Braczynski  · Bergita Ganse   \nReceived: 12 May 2021 / Accepted: 23 June 2021 / Published online: 9 July 2021 © The Author(s) 2021  \nAbstract Factors that determine individual agerelated decline rates in physical performance are poorly understood and prediction poses a challenge. Linear and quadratic regression models are usually applied, but often show high prediction errors for individual athletes. Machine learning approaches may deliver more accurate predictions and help to identify factors that determine performance decline rates. We hypothesized that it is possible to predict the performance development of a master athlete from a single measurement, that prediction by a machine learning approach is superior to prediction by the average decline curve or an individually shifted decline curve,  \nC. Hoog Antink  \nTU Darmstadt, Biomedical Engineering (KIS*MED), Darmstadt, Germany  \nA. K. Braczynski  \nDepartment of Neurology, RWTH Aachen University Hospital, Aachen, Germany  \nA. K. Braczynski  \nInstitut für physikalische Biologie, Heinrich-Heine University Düsseldorf, Düsseldorf, Germany  \nB. Ganse (*)  \nInnovative Implant Development, Department of Surgery, Saarland University, Homburg, Germany [e-mail: Bergita.ganse@uks.eu](e-mail: Bergita.ganse@uks.eu)  \nB. Ganse  \nDepartment of Trauma, Hand and Reconstructive Surgery, Saarland University, Homburg, Germany  \nand that athletes with a higher starting performance show a slower performance decline than those with a lower performance. The machine learning approach was implemented using a multilayer neuronal network. Results showed that performance prediction from a single measurement is possible and that the prediction by a machine learning approach was superior to the other models. The estimated performance decline rate was highest in athletes with a high starting performance and a low starting age, as well as in those with a low starting performance and high starting age, while the lowest decline rate was found for athletes with a high starting performance and a high starting age. Machine learning was superior and predicted trajectories with significantly lower prediction errors compared to conventional approaches. New insights into factors determining decline trajectories were identified by visualization of the model outputs. Machine learning models may be useful in revealing unknown factors that determine the age-related performance decline.  \nKeywords Artificial intelligence · Track and field · Big data · Longevity · Ageing · Prediction  \nIntroduction  \nThe inherent ageing process is associated with declines in physical performance that can partially be mitigated but currently not stopped or reversed [1, 2] .  \nFrailty and sarcopenia, as well as chronic diseases, such as the metabolic syndrome, are often connected to a reduced quality of life in old age [3, 4] . Athletic performance declines in an almost linear fashion up until around the age of 70 years [5], when the decline progressively accelerates [6–10] . Physical performance decline trajectories vary among individuals, as reflected in longitudinal data [6, 11, 12] . People who participate in competitive sports longer were shown to experience a slower performance decline [13–15] . Further underlying factors for differences in individual decline trajectories are, however, poorly understood and their prediction thus poses a challenge. Asan example, it is not clear whether athletes who perform better have a slower performance decline rate. In addition, the influences of diseases and injuries on the performance decline trajectories in various sports are unknown, despite the high relevance of this knowledge in an ageing society.  \nLarge datasets and big-data approache","cbCaipebG0R6y4tR","https://ap.wps.com/l/cbCaipebG0R6y4tR","pdf",2102062,1,13,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"Why is predicting individual age-related athletic performance decline challenging?\",\"answer\":\"Individual performance decline trajectories vary across people, and the relevant characteristics associated with faster or slower decline are not well understood. As a result, prediction for a single athlete is difficult, and conventional regressions often yield high errors.\"},{\"question\":\"What approach does the study evaluate for predicting decline trajectories?\",\"answer\":\"The study implements a machine-learning model using a multilayer neuronal network. It tests prediction from a single measurement and compares it with the average decline curve and an individually shifted decline curve.\"},{\"question\":\"What did the results show about prediction accuracy and decline rates?\",\"answer\":\"Performance prediction from a single measurement was feasible, and the machine-learning approach produced significantly lower prediction errors than conventional models. Estimated decline rates were highest for combinations of high starting performance with low starting age, and low starting performance with high starting age.\"}]","Learning from Machine Learning - Prediction of Age-Related Athletic Performance Decline Trajectories | PDF",1785682086,33,{"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},"learning-from-machine-learning-prediction-of-age-related-athletic-performance-decline-trajectories","",{"@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/learning-from-machine-learning-prediction-of-age-related-athletic-performance-decline-trajectories/118188/",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","2026-08-02",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},"Why is predicting individual age-related athletic performance decline challenging?","Question",{"text":75,"@type":76},"Individual performance decline trajectories vary across people, and the relevant characteristics associated with faster or slower decline are not well understood. As a result, prediction for a single athlete is difficult, and conventional regressions often yield high errors.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What approach does the study evaluate for predicting decline trajectories?",{"text":80,"@type":76},"The study implements a machine-learning model using a multilayer neuronal network. It tests prediction from a single measurement and compares it with the average decline curve and an individually shifted decline curve.",{"name":82,"@type":73,"acceptedAnswer":83},"What did the results show about prediction accuracy and decline rates?",{"text":84,"@type":76},"Performance prediction from a single measurement was feasible, and the machine-learning approach produced significantly lower prediction errors than conventional models. Estimated decline rates were highest for combinations of high starting performance with low starting age, and low starting performance with high starting age.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]