[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119300-en":3,"doc-seo-119300-105":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},119300,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","ESTIMATION OF THE BONE BIOLOGICAL AGE USING MACHINE LEARNING","The study aims to identify the best method for assessing bone biological age to enable earlier detection of bone diseases such as osteoporosis. Machine learning and neural network approaches are evaluated using biomarkers including BMI, bone mass density, fracture risk assessment tool outputs for multiple bones, and trabecular bone score. Biomarker-age relationships are analyzed with Pearson and Spearman correlations. Models are trained and tested using linear regression, k-nearest neighbors, boosting, ensembles, and a two-neural-network approach, with boosting-based models achieving the best MAE and correlation results.","Original Research Article: full paper  \n(2025), \"EUREKA: Physics and Engineering\"  \nNumber 1  \nESTIMATION OF THE BONE BIOLOGICAL AGE USING  \nMACHINE LEARNING  \nVolodymyr Slipchenko*  \nDepartment of Digital Technologies in Energy 1  \n[ddpolytechnic2016@gmail.com](ddpolytechnic2016@gmail.com)  \nNataliia Grygorieva  \nDepartment of Clinical Physiology and Pathology of the Musculoskeletal System2  \nLiubov Poliahushko  \nDepartment of Digital Technologies in Energy 1  \nАnna Musiіenko  \nDepartment of Clinical Physiology and Pathology of the Musculoskeletal System2  \nVolodymyr Rudyk  \nDepartment of Digital Technologies in Energy 1  \nVladyslav Shatylo  \nDepartment of Digital Technologies in Energy 1  \n1National Technical University of Ukraine \"Igor Sikorsky Kyiv Polytechnic Institute\"  \n37 Beresteiskyi ave., Kyiv, Ukraine, 03056  \n2D. F. Chebotarev Institute of Gerontology of the NAMS of Ukraine  \n67 Vyshhorodska str., Kyiv, Ukraine, 04114  \n*Corresponding author  \nAbstract  \nThe study aims to identify the best method for assessing the bone biological age, which can help detect bone diseases like osteoporosis early. The focus is on machine learning methods and neural networks, using data such as body mass index, data on bone mass density, and the fracture risk assessment tool of various bones in the body, as well as the trabecular bone score as biomarkers. The correlation of biomarkers with age was verified using Pearson and Spearman correlation coefficients. The training part of the processed dataset was fed into various machine learning models based on different methods (linear regression, k-nearest neighbors, boosting, ensembles, etc.), followed by accuracy testing on the test set. Additionally, the method for assessing biological age based on two neural networks was tested. The best results were shown by machine learning models based on the boosting method, such as XGBRegressor, LGBMRegressor, and CatBoostRegressor, with MAE ranging from 2.1 to 2.2 and a correlation coefficient from 0.93 to 0.94, which indicates high accuracy given the limited dataset. The method utilizing two neural networks did not show the expected increase in accuracy (MAE 3.5 and a correlation coefficient of 0.90) . It also did not perform significantly worse, indicating the method’s lack of optimization for this task while highlighting its versatility in assessing biological age. The study’s results made it possible to increase the accuracy of the assessment of the bone biological age: MAE from 3.67 to 2.1, correlation coefficient from 0.88 to 0.94, compared with a similar study. Also, the results provided important information on determining the BA of bones based on data from Ukrainian citizens, contributing to the development of the biological age field in Ukraine.  \nKeywords: biological age, bone age, BMD, neural networks, machine learning.  \nDOI: 10.21303/2461-4262.2025.003656  \n1. Introduction  \nOsteoporosis is the most common bone diseases in humans. It can be characterized asa widespread age-related disease associated with low bone mass density (BMD) and systemic  \n175  \nOriginal Research Article: full paper  \n(2025), \"EUREKA: Physics and Engineering\"  \nNumber 1  \ndisruption of bone mass and microarchitecture, predisposing individuals to an increased risk of fractures [1].  \nIn the USA, about 10 million Americans over the age of 50 suffer from osteoporosis, and another 34 million are at increased risk of developing it. In the UK, one in two women and one in five men over the age of 50 are affected [2] . In India, various studies indicate that 25 % to 62 % of postmenopausal women (approximately over 50 years old) also suffer from osteoporosis [3] .  \nFor Ukrainian citizens, the data is similarly alarming: according to studies by the D. F. Chebotarev Institute of Gerontology and the Ukrainian Scientific Medical Center for Osteoporosis Problems, osteoporosis is observed in 13 % of women aged 50–59 years, in 25 % of women aged 60–69 years, 50 % in the 70–79","cbCaivHqbP82T4oF","https://ap.wps.com/l/cbCaivHqbP82T4oF","pdf",2663904,1,12,"English","en",105,"# Introduction\n## Background and relevance of osteoporosis\n## Chronological age vs biological age\n## Biological age vs bone age\n## Biomarkers for biological age assessment","[{\"question\":\"What is the goal of estimating bone biological age in this study?\",\"answer\":\"To determine an optimal method for assessing bone biological age, supporting early detection of bone diseases such as osteoporosis.\"},{\"question\":\"Which data and biomarkers are used as inputs for machine learning models?\",\"answer\":\"BMI, bone mass density, fracture risk assessment tool data for various bones, and trabecular bone score are used as biomarkers.\"},{\"question\":\"Which model types performed best for predicting bone biological age?\",\"answer\":\"Boosting-based machine learning models (e.g., XGBRegressor, LGBMRegressor, CatBoostRegressor) provided the strongest performance in MAE and correlation metrics.\"}]","ESTIMATION OF THE BONE BIOLOGICAL AGE USING MACHINE LEARNING | PDF",1785723592,30,{"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},"estimation-of-the-bone-biological-age-using-machine-learning","",{"@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/estimation-of-the-bone-biological-age-using-machine-learning/119300/",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","2026-08-03",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 is the goal of estimating bone biological age in this study?","Question",{"text":75,"@type":76},"To determine an optimal method for assessing bone biological age, supporting early detection of bone diseases such as osteoporosis.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data and biomarkers are used as inputs for machine learning models?",{"text":80,"@type":76},"BMI, bone mass density, fracture risk assessment tool data for various bones, and trabecular bone score are used as biomarkers.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model types performed best for predicting bone biological age?",{"text":84,"@type":76},"Boosting-based machine learning models (e.g., XGBRegressor, LGBMRegressor, CatBoostRegressor) provided the strongest performance in MAE and correlation metrics.","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"]