{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:06:15Z","timestamp":1792785975128,"version":"4.5.0"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,2,4]],"date-time":"2024-02-04T00:00:00Z","timestamp":1707004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100006545","name":"National Institute on Minority Health and Health Disparities","doi-asserted-by":"publisher","award":["R21MD013681"],"award-info":[{"award-number":["R21MD013681"]}],"id":[{"id":"10.13039\/100006545","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Institute of Aging","award":["R01AG080017"],"award-info":[{"award-number":["R01AG080017"]}]},{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["P20GM121325"],"award-info":[{"award-number":["P20GM121325"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study aimed to enhance the fracture risk prediction accuracy in major osteoporotic fractures (MOFs) and hip fractures (HFs) by integrating genetic profiles, machine learning (ML) techniques, and Bayesian optimization. The genetic risk score (GRS), derived from 1,103 risk single nucleotide polymorphisms (SNPs) from genome-wide association studies (GWAS), was formulated for 25,772 postmenopausal women from the Women's Health Initiative dataset. We developed four ML models: Support Vector Machine (SVM), Random Forest, XGBoost, and Artificial Neural Network (ANN) for binary fracture outcome and 10-year fracture risk prediction. GRS and FRAX clinical risk factors (CRFs) were used as predictors. Death as a competing risk was accounted for in ML models for time-to-fracture data. ML models were subsequently fine-tuned through Bayesian optimization, which displayed marked superiority over traditional grid search. Evaluation of the models' performance considered an array of metrics such as accuracy, weighted F1 Score, the area under the precision-recall curve (PRAUC), and the area under the receiver operating characteristic curve (AUC) for binary fracture predictions, and the C-index, Brier score, and dynamic mean AUC over a 10-year follow-up period for fracture risk predictions. We found that GRS-integrated XGBoost with Bayesian optimization is the most effective model, with an accuracy of 91.2% (95% CI: 90.4\u201392.0%) and an AUC of 0.739 (95% CI: 0.731\u20130.746) in MOF binary predictions. For 10-year fracture risk modeling, the XGBoost model attained a C-index of 0.795 (95% CI: 0.783\u20130.806) and a mean dynamic AUC of 0.799 (95% CI: 0.788\u20130.809). Compared to FRAX, the XGBoost model exhibited a categorical net reclassification improvement (NRI) of 22.6% (P\u00a0=\u2009.004). A sensitivity analysis, which included BMD but lacked GRS, reaffirmed these findings. Furthermore, portability tests in diverse non-European groups, including Asians and African Americans, underscored the model's robustness and adaptability. This study accentuates the potential of combining genetic insights and optimized ML in strengthening fracture predictions, heralding new preventive strategies for postmenopausal women.<\/jats:p>","DOI":"10.1093\/jbmr\/zjae025","type":"journal-article","created":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T16:22:11Z","timestamp":1706890931000},"page":"462-472","source":"Crossref","is-referenced-by-count":18,"title":["Enhanced osteoporotic fracture prediction in postmenopausal women using Bayesian optimization of machine learning models with genetic risk score"],"prefix":"10.1093","volume":"39","author":[{"given":"Qing","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics (Dr. Qing Wu , Jingyuan Dai), College of Medicine, , Columbus, OH 43210 , United States"},{"name":"The Ohio State University , Jingyuan Dai), College of Medicine, , Columbus, OH 43210 , United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyuan","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics (Dr. Qing Wu , Jingyuan Dai), College of Medicine, , Columbus, OH 43210 , United States"},{"name":"The Ohio State University , Jingyuan Dai), College of Medicine, , Columbus, OH 43210 , United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,2,4]]},"reference":[{"issue":"3","key":"2024050213185468000_ref1","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1359\/jbmr.061113","article-title":"Incidence and economic burden of osteoporosis-related fractures in the United States, 2005-2025","volume":"22","author":"Burge","year":"2007","journal-title":"J Bone Miner Res"},{"key":"2024050213185468000_ref2","volume-title":"Bone Health and Osteoporosis: A Report of the Surgeon General","author":"Office of the Surgeon General (US)","year":"2004"},{"key":"2024050213185468000_ref3","first-page":"4207","article-title":"Prediction of hip fracture in post-menopausal women using artificial neural network approach","volume":"2017","author":"Ho-Le","year":"2017","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"9","key":"2024050213185468000_ref4","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1111\/j.1532-5415.2004.52410.x","article-title":"Long-term prediction of incident hip fracture risk in elderly white women: study of osteoporotic fractures","volume":"52","author":"Taylor","year":"2004","journal-title":"J Am Geriatr Soc"},{"issue":"2","key":"2024050213185468000_ref5","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1038\/s41588-018-0302-x","article-title":"An atlas of genetic influences on osteoporosis in humans and mice","volume":"51","author":"Morris","year":"2019","journal-title":"Nat Genet"},{"issue":"11","key":"2024050213185468000_ref6","doi-asserted-by":"crossref","first-page":"2445","DOI":"10.1001\/archinte.1989.00390110045010","article-title":"Lifetime risks of hip, Colles\u2019, or vertebral fracture and coronary heart disease among white postmenopausal women","volume":"149","author":"Sr","year":"1989","journal-title":"Arch Intern Med"},{"issue":"5","key":"2024050213185468000_ref7","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1016\/j.bone.2009.01.373","article-title":"FRAX and its applications to clinical practice","volume":"44","author":"Kanis","year":"2009","journal-title":"Bone"},{"issue":"2","key":"2024050213185468000_ref8","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/s11606-018-4696-z","article-title":"Predicting fracture risk in younger postmenopausal women: comparison of the garvan and FRAX Risk calculators in the women\u2019s health initiative study","volume":"34","author":"Crandall","year":"2019","journal-title":"J Gen Intern Med"},{"issue":"10","key":"2024050213185468000_ref9","doi-asserted-by":"crossref","first-page":"2103","DOI":"10.1007\/s00198-022-06435-6","article-title":"Update of the fracture risk prediction tool FRAX: a systematic review of potential cohorts and analysis plan","volume":"33","author":"Vandenput","year":"2022","journal-title":"Osteoporos Int"},{"issue":"1","key":"2024050213185468000_ref10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41413-021-00143-3","article-title":"Twelve years of GWAS discoveries for osteoporosis and related traits: advances, challenges and applications","volume":"9","author":"Zhu","year":"2021","journal-title":"Bone Res"},{"key":"2024050213185468000_ref11","first-page":"1","article-title":"FRAX-based estimates of 10-year probability of hip and major osteoporotic fracture among adults aged 40 and over: United States, 2013 and 2014","volume":"103","author":"Looker","year":"2017","journal-title":"Natl Health Stat Report"},{"issue":"1","key":"2024050213185468000_ref12","article-title":"Osteoporosis in the European Union: medical management, epidemiology and economic burden. A report prepared in collaboration with the International Osteoporosis Foundation (IOF) and the European Federation of Pharmaceutical Industry Associations (EFPIA)","volume":"8","author":"Hernlund","year":"2013","journal-title":"Arch Osteoporos"},{"issue":"6","key":"2024050213185468000_ref13","first-page":"785","article-title":"NIH Consensus Development Panel on Osteoporosis Prevention, Diagnosis, and Therapy. Osteoporosis prevention, diagnosis, and therapy","volume":"285","year":"2001","journal-title":"JAMA"},{"issue":"9","key":"2024050213185468000_ref14","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1038\/s41576-018-0018-x","article-title":"The personal and clinical utility of polygenic risk scores","volume":"19","author":"Torkamani","year":"2018","journal-title":"Nat Rev Genet"},{"issue":"9","key":"2024050213185468000_ref15","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1038\/s41588-018-0183-z","article-title":"Genome-wide polygenic scores for common diseases identify individuals with risk equivalent to monogenic mutations","volume":"50","author":"Khera","year":"2018","journal-title":"Nat Genet"},{"issue":"3","key":"2024050213185468000_ref16","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/s42979-021-00592-x","article-title":"Machine learning: algorithms, real-world applications and research directions","volume":"2","author":"Sarker","year":"2021","journal-title":"Sn Comput Sci"},{"issue":"3","key":"2024050213185468000_ref17","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1007\/s12525-021-00475-2","article-title":"Machine learning and deep learning","volume":"31","author":"Janiesch","year":"2021","journal-title":"Electron Markets"},{"issue":"8","key":"2024050213185468000_ref18","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0202344","article-title":"Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease","volume":"13","author":"Steele","year":"2018","journal-title":"PLoS One"},{"issue":"1","key":"2024050213185468000_ref19","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TBME.2019.2909027","article-title":"Dynamic-deephit: a deep learning approach for dynamic survival analysis with competing risks based on longitudinal data","volume":"67","author":"Lee","year":"2020","journal-title":"IEEE Trans Biomed Eng"},{"key":"2024050213185468000_ref20","doi-asserted-by":"crossref","DOI":"10.1109\/JBHI.2021.3052441","article-title":"Deep survival machines: fully parametric survival regression and representation learning for censored data with competing risks","volume-title":"IEEE Journal of Biomedical and Health Informatics","author":"Nagpal","year":"2021"},{"issue":"1","key":"2024050213185468000_ref21","first-page":"26","article-title":"Hyperparameter optimization for machine learning models based on bayesian optimization","volume":"17","author":"Wu","year":"2019","journal-title":"J Electron Sci and Technol"},{"issue":"9","key":"2024050213185468000_ref22","doi-asserted-by":"crossref","first-page":"S107","DOI":"10.1016\/S1047-2797(03)00047-4","article-title":"The Women\u2019s Health Initiative Observational Study: baseline characteristics of participants and reliability of baseline measures","volume":"13","author":"Langer","year":"2003","journal-title":"Ann Epidemiol"},{"issue":"9, Supplement","key":"2024050213185468000_ref23","doi-asserted-by":"crossref","first-page":"S18","DOI":"10.1016\/S1047-2797(03)00042-5","article-title":"The women\u2019s health initiative recruitment methods and results","volume":"13","author":"Hays","year":"2003","journal-title":"Ann Epidemiol"},{"issue":"3","key":"2024050213185468000_ref24","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s11914-009-0013-4","article-title":"From relative risk to absolute fracture risk calculation: the FRAX algorithm","volume":"7","author":"McCloskey","year":"2009","journal-title":"Curr Osteoporos Rep"},{"issue":"9","key":"2024050213185468000_ref25","doi-asserted-by":"crossref","first-page":"2759","DOI":"10.1038\/s41596-020-0353-1","article-title":"Tutorial: a guide to performing polygenic risk score analyses","volume":"15","author":"Choi","year":"2020","journal-title":"Nat Protoc"},{"key":"2024050213185468000_ref26","article-title":"Handling imbalanced datasets: a review","volume-title":"GESTS international transactions on computer science and engineering","author":"Kotsiantis"},{"key":"2024050213185468000_ref27","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1613\/jair.1.11192","article-title":"SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary","volume":"61","author":"Fernandez","year":"2018","journal-title":"J Artif Intell Res"},{"key":"2024050213185468000_ref28","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1007\/978-3-642-17103-1_60","volume-title":"Classification, Clustering, and Data Mining Applications","author":"Acu\u00f1a","year":"2004"},{"issue":"4","key":"2024050213185468000_ref29","article-title":"Data-driven discovery of probable Alzheimer\u2019s disease and related dementia subphenotypes using electronic health records","volume":"4","author":"Xu","year":"2020","journal-title":"Learn Health Syst"},{"key":"2024050213185468000_ref30","article-title":"Breast cancer risk prediction using electronic health records","volume-title":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","author":""},{"key":"2024050213185468000_ref31","article-title":"Hyper-parameter optimization: a review of algorithms and applications","volume-title":"arXiv preprint arXiv:2003.05689","author":"Yu"},{"key":"2024050213185468000_ref32","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.neucom.2020.07.061","article-title":"On hyperparameter optimization of machine learning algorithms: theory and practice","volume":"415","author":"Yang","year":"2020","journal-title":"Neurocomputing"},{"key":"2024050213185468000_ref33","article-title":"Grid search, random search, genetic algorithm: a big comparison for NAS","volume-title":"arXiv preprint arXiv:1912.06059","author":"Liashchynskyi"},{"key":"2024050213185468000_ref34","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"2024050213185468000_ref35","article-title":"Bayesian optimization is superior to random search for machine learning hyperparameter tuning: analysis of the black-box optimization challenge 2020","volume-title":"NeurIPS 2020 Competition and Demonstration Track","author":"Turner"},{"issue":"Pt A","key":"2024050213185468000_ref36","article-title":"Explainable diabetes classification using hybrid Bayesian-optimized TabNet architecture","volume":"151","author":"Joseph","year":"2022","journal-title":"Comput Biol Med"},{"key":"2024050213185468000_ref37","volume-title":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","author":"Firdaus"},{"issue":"5","key":"2024050213185468000_ref38","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s00138-020-01078-1","article-title":"Hyper-parameter optimization of deep learning model for prediction of Parkinson\u2019s disease","volume":"31","author":"Kaur","year":"2020","journal-title":"Mach Vis Appl"},{"issue":"6","key":"2024050213185468000_ref39","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1093\/aje\/kwx374","article-title":"Performance of the net reclassification improvement for nonnested models and a novel percentile-based alternative","volume":"187","author":"McKearnan","year":"2018","journal-title":"Am J Epidemiol"},{"issue":"10","key":"2024050213185468000_ref40","doi-asserted-by":"crossref","first-page":"2049","DOI":"10.1007\/s00198-021-05900-y","article-title":"The clinician\u2019s guide to prevention and treatment of osteoporosis","volume":"33","author":"LeBoff","year":"2022","journal-title":"Osteoporos Int"},{"issue":"4","key":"2024050213185468000_ref41","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1007\/s00223-020-00734-y","article-title":"Machine learning approaches for fracture risk assessment: a comparative analysis of genomic and phenotypic data in 5130 older men","volume":"107","author":"Wu","year":"2020","journal-title":"Calcif Tissue Int"},{"key":"2024050213185468000_ref42","article-title":"Trends in Genetic Tests Provided Under Medicare Part B Indicate Areas of Possible Concern","year":"2021"},{"issue":"1","key":"2024050213185468000_ref43","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1038\/s41523-017-0035-5","article-title":"The WISDOM Study: breaking the deadlock in the breast cancer screening debate","volume":"3","author":"Esserman","year":"2017","journal-title":"NPJ Breast Cancer"},{"key":"2024050213185468000_ref44","article-title":"The eMERGE Network: a consortium of biorepositories linked to electronic medical records data for conducting genomic studies","volume-title":"BMC medical genomics","author":""},{"issue":"7","key":"2024050213185468000_ref45","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1003152","article-title":"Development of a polygenic risk score to improve screening for fracture risk: a genetic risk prediction study","volume":"17","author":"Forgetta","year":"2020","journal-title":"PLoS Med"},{"issue":"1","key":"2024050213185468000_ref46","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/s13073-021-00838-6","article-title":"Improved prediction of fracture risk leveraging a genome-wide polygenic risk score","volume":"13","author":"Lu","year":"2021","journal-title":"Genome Med"}],"container-title":["Journal of Bone and Mineral Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jbmr\/advance-article-pdf\/doi\/10.1093\/jbmr\/zjae025\/57137032\/zjae025.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jbmr\/article-pdf\/39\/4\/462\/57373021\/zjae025.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jbmr\/article-pdf\/39\/4\/462\/57373021\/zjae025.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,2]],"date-time":"2024-05-02T09:20:19Z","timestamp":1714641619000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jbmr\/article\/39\/4\/462\/7600498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,4]]},"references-count":46,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2,4]]},"published-print":{"date-parts":[[2024,5,2]]}},"URL":"https:\/\/doi.org\/10.1093\/jbmr\/zjae025","relation":{},"ISSN":["0884-0431","1523-4681"],"issn-type":[{"value":"0884-0431","type":"print"},{"value":"1523-4681","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,4]]},"published":{"date-parts":[[2024,2,4]]}}}