[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120956-en":3,"doc-seo-120956-105":30,"detail-sidebar-cat-0-en-105":90},{"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":20,"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},120956,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Machine Learning for Risk Factor Identification and Cardiovascular Mortality Prediction Among Patients with Osteoporosis","Risk prediction tools are widely used in clinical decision-making, yet many existing models are trained on general populations and may not transfer well to high-risk groups such as people with osteoporosis. This study develops and internally validates a cardiovascular mortality risk prediction model specifically for patients with osteoporosis using multiple machine learning approaches. Model results are compared with expert-based alternatives for risk factor identification, discrimination, and calibration, showing superior performance in the osteoporosis population. External validation is recommended to confirm generalizability.","Machine Learning for Risk Factor Identification and Cardiovascular Mortality Prediction Among Patients with  \nOsteoporosis  \nSeyed Alireza Hasheminasab, Daniel Prieto-Alhambra, Marta Pineda Moncusi, Sara Khalid  \nAbstract—Risk prediction tools are increasingly popular aids in clinical decision-making. However, the underlying models are often trained on data from general patient cohorts and may not be representative of and suitable for use with targeted patient groups in actual clinical practice, such as in the case of osteoporosis patients who may be at elevated risk of mortality. We developed and internally validated a cardiovascular mortality risk prediction model tailored to individuals with osteoporosis using a range of machine learning models. We compared the performance of machine learning models with existing expert-based models with respect to data-driven risk factor identification, discrimination, and calibration. The proposed models were found to outperform existing cardiovascular mortality risk prediction tools for the osteoporosis population. External validation of the model is recommended.  \nClinical Relevance—This study presents the performance of machine learning models for cardiovascular death prediction among osteoporotic patients as well as the risk factors identified by the models to be important predictors.  \nI. INTRODUCTION  \nOsteoporosis (OP) is a health condition that involves bone deterioration; it can significantly impact a patient’s quality of life and can increase the risk of comorbidity and mortality [1] . Due to concerns about the risk of cardiovascular events inpatients with osteoporosis, some studies have investigated the risk of cardiovascular disease (CVD) among patients with OP [2, 3] . Findings indicate an increased risk of CVD-related mortality due to myocardial infarction (MI) and stroke in individuals with low bone mineral density, motivating the need for the identification of OP patients at high risk of cardiovascular disease and improving the performance of existing cardiovascular risk prediction tools for OP patients to support clinical decision-making and ultimately enhance patient outcomes [3] .  \nMost CVD risk prediction tools are based on data and assumptions that are compatible with the general population and may not be entirely consistent with OP patient characteristics [4-10] . For instance, although there are common risk factors between CVD and OP such as age, obesity, and type 2 diabetes, some well-known risk factors of osteoporosis such as low weight or female gender can present a protective effect against CVD risk [11-14] . Recently attempts to develop CVD risk models tailored to the OP population have been made using routine clinical data [2] .  \nAuthors are with the Centre for Statistics in Medicine, Nuffield Department of Orthopedics, Rheumatology and Musculoskeletal Sciences (NDORMS), University of Oxford, Oxford, U.K (e-mail: [alireza.hasheminasab@ndorms.ox.ac.uk](alireza.hasheminasab@ndorms.ox.ac.uk))  \nThe increasing availability of clinical data in the form of large-scale electronic health records has amplified the interest in machine learning (ML) models for clinical risk prediction [15, 16]; with some literature favouring ML over traditional techniques, particularly to account for complex interactions within a wide range of patient characteristics [17-21] .  \nIn this paper, we aimed to compare machine-learning models with existing approaches for risk factor identification and risk prediction of CVD death. Proposed models were compared with a reference model based on QRISK - a widely known CVD risk prediction tool used in clinical practice [9, 10] . We further analysed the impact of training sample size on model performance.  \nII. METHODOLOGY  \nA. Data Source  \nThe Clinical Practice Research Datalink (CPRD) GOLD dataset contains anonymized electronic primary care records for a total of 21 million patients in the UK of which approximately 9 million are eligible for li","cbCaiqVBdr98zB1V","https://ap.wps.com/l/cbCaiqVBdr98zB1V","pdf",410585,1,4,"English","en",105,"# Introduction\n## Osteoporosis and cardiovascular risk context\n## Motivation for tailored risk prediction\n# Methodology\n## Data source and linkage\n## Study population\n## Outcome definition\n## Pre-processing and candidate features","[{\"question\":\"Why do existing cardiovascular risk prediction tools need adaptation for osteoporosis patients?\",\"answer\":\"Most tools are derived from assumptions and data compatible with the general population, which may not match osteoporosis-specific characteristics, where some factors can have different associations with cardiovascular risk.\"},{\"question\":\"What was the study outcome used for cardiovascular mortality prediction?\",\"answer\":\"Cardiovascular death was defined as recorded stroke or myocardial infarction as the primary cause of death.\"},{\"question\":\"How did the researchers build and evaluate the machine learning models?\",\"answer\":\"They used linked clinical records from the CPRD dataset to create a candidate feature set, developed several machine learning models, and compared performance against an expert-based reference model (QRISK) across risk factor identification, discrimination, and calibration.\"}]","Machine Learning for Risk Factor Identification and Cardiovascular Mortality Prediction Among Patients with Osteoporosis | PDF",1785733055,10,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":28},"machine-learning-for-risk-factor-identification-and-cardiovascular-mortality-prediction-among-patients-with-osteoporosis","",{"@graph":36,"@context":84},[37,53,67],{"@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":21},"https://docshare.wps.com/document/machine-learning-for-risk-factor-identification-and-cardiovascular-mortality-prediction-among-patients-with-osteoporosis/120956/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why do existing cardiovascular risk prediction tools need adaptation for osteoporosis patients?","Question",{"text":74,"@type":75},"Most tools are derived from assumptions and data compatible with the general population, which may not match osteoporosis-specific characteristics, where some factors can have different associations with cardiovascular risk.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What was the study outcome used for cardiovascular mortality prediction?",{"text":79,"@type":75},"Cardiovascular death was defined as recorded stroke or myocardial infarction as the primary cause of death.",{"name":81,"@type":72,"acceptedAnswer":82},"How did the researchers build and evaluate the machine learning models?",{"text":83,"@type":75},"They used linked clinical records from the CPRD dataset to create a candidate feature set, developed several machine learning models, and compared performance against an expert-based reference model (QRISK) across risk factor identification, discrimination, and calibration.","https://schema.org",{"og:url":52,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"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":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]