Luca Quagliato, Jiin Seo, Jiheun Hong, Taeyong Lee, Yoon-Sok Chung
{"title":"基于几何和材料参数的双能x线吸收仪对骨质疏松性骨折的综合数据增强分类。","authors":"Luca Quagliato, Jiin Seo, Jiheun Hong, Taeyong Lee, Yoon-Sok Chung","doi":"10.3803/EnM.2024.2211","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Bone fracture risk assessment for osteoporotic patients is essential for implementing early countermeasures and preventing discomfort and hospitalization. Current methodologies, such as Fracture Risk Assessment Tool (FRAX), provide a risk assessment over a 5- to 10-year period rather than evaluating the bone's current health status.</p><p><strong>Methods: </strong>The database was collected by Ajou University Medical Center from 2017 to 2021. It included 9,260 patients, aged 55 to 99, comprising 242 femur fracture (FX) cases and 9,018 non-fracture (NFX) cases. To model the association of the bone's current health status with prevalent FXs, three prediction algorithms-extreme gradient boosting (XGB), support vector machine, and multilayer perceptron-were trained using two-dimensional dual-energy X-ray absorptiometry (2D-DXA) analysis results and subsequently benchmarked. The XGB classifier, which proved most effective, was then further refined using synthetic data generated by the adaptive synthetic oversampler to balance the FX and NFX classes and enhance boundary sharpness for better classification accuracy.</p><p><strong>Results: </strong>The XGB model trained on raw data demonstrated good prediction capabilities, with an area under the curve (AUC) of 0.78 and an F1 score of 0.71 on test cases. The inclusion of synthetic data improved classification accuracy in terms of both specificity and sensitivity, resulting in an AUC of 0.99 and an F1 score of 0.98.</p><p><strong>Conclusion: </strong>The proposed methodology demonstrates that current bone health can be assessed through post-processed results from 2D-DXA analysis. Moreover, it was also shown that synthetic data can help stabilize uneven databases by balancing majority and minority classes, thereby significantly improving classification performance.</p>","PeriodicalId":11636,"journal":{"name":"Endocrinology and Metabolism","volume":" ","pages":""},"PeriodicalIF":3.9000,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Synthetic Data-Enhanced Classification of Prevalent Osteoporotic Fractures Using Dual-Energy X-Ray Absorptiometry-Based Geometric and Material Parameters.\",\"authors\":\"Luca Quagliato, Jiin Seo, Jiheun Hong, Taeyong Lee, Yoon-Sok Chung\",\"doi\":\"10.3803/EnM.2024.2211\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Bone fracture risk assessment for osteoporotic patients is essential for implementing early countermeasures and preventing discomfort and hospitalization. Current methodologies, such as Fracture Risk Assessment Tool (FRAX), provide a risk assessment over a 5- to 10-year period rather than evaluating the bone's current health status.</p><p><strong>Methods: </strong>The database was collected by Ajou University Medical Center from 2017 to 2021. It included 9,260 patients, aged 55 to 99, comprising 242 femur fracture (FX) cases and 9,018 non-fracture (NFX) cases. To model the association of the bone's current health status with prevalent FXs, three prediction algorithms-extreme gradient boosting (XGB), support vector machine, and multilayer perceptron-were trained using two-dimensional dual-energy X-ray absorptiometry (2D-DXA) analysis results and subsequently benchmarked. The XGB classifier, which proved most effective, was then further refined using synthetic data generated by the adaptive synthetic oversampler to balance the FX and NFX classes and enhance boundary sharpness for better classification accuracy.</p><p><strong>Results: </strong>The XGB model trained on raw data demonstrated good prediction capabilities, with an area under the curve (AUC) of 0.78 and an F1 score of 0.71 on test cases. The inclusion of synthetic data improved classification accuracy in terms of both specificity and sensitivity, resulting in an AUC of 0.99 and an F1 score of 0.98.</p><p><strong>Conclusion: </strong>The proposed methodology demonstrates that current bone health can be assessed through post-processed results from 2D-DXA analysis. Moreover, it was also shown that synthetic data can help stabilize uneven databases by balancing majority and minority classes, thereby significantly improving classification performance.</p>\",\"PeriodicalId\":11636,\"journal\":{\"name\":\"Endocrinology and Metabolism\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2025-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Endocrinology and Metabolism\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.3803/EnM.2024.2211\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENDOCRINOLOGY & METABOLISM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Endocrinology and Metabolism","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3803/EnM.2024.2211","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
Synthetic Data-Enhanced Classification of Prevalent Osteoporotic Fractures Using Dual-Energy X-Ray Absorptiometry-Based Geometric and Material Parameters.
Background: Bone fracture risk assessment for osteoporotic patients is essential for implementing early countermeasures and preventing discomfort and hospitalization. Current methodologies, such as Fracture Risk Assessment Tool (FRAX), provide a risk assessment over a 5- to 10-year period rather than evaluating the bone's current health status.
Methods: The database was collected by Ajou University Medical Center from 2017 to 2021. It included 9,260 patients, aged 55 to 99, comprising 242 femur fracture (FX) cases and 9,018 non-fracture (NFX) cases. To model the association of the bone's current health status with prevalent FXs, three prediction algorithms-extreme gradient boosting (XGB), support vector machine, and multilayer perceptron-were trained using two-dimensional dual-energy X-ray absorptiometry (2D-DXA) analysis results and subsequently benchmarked. The XGB classifier, which proved most effective, was then further refined using synthetic data generated by the adaptive synthetic oversampler to balance the FX and NFX classes and enhance boundary sharpness for better classification accuracy.
Results: The XGB model trained on raw data demonstrated good prediction capabilities, with an area under the curve (AUC) of 0.78 and an F1 score of 0.71 on test cases. The inclusion of synthetic data improved classification accuracy in terms of both specificity and sensitivity, resulting in an AUC of 0.99 and an F1 score of 0.98.
Conclusion: The proposed methodology demonstrates that current bone health can be assessed through post-processed results from 2D-DXA analysis. Moreover, it was also shown that synthetic data can help stabilize uneven databases by balancing majority and minority classes, thereby significantly improving classification performance.
期刊介绍:
The aim of this journal is to set high standards of medical care by providing a forum for discussion for basic, clinical, and translational researchers and clinicians on new findings in the fields of endocrinology and metabolism. Endocrinology and Metabolism reports new findings and developments in all aspects of endocrinology and metabolism. The topics covered by this journal include bone and mineral metabolism, cytokines, developmental endocrinology, diagnostic endocrinology, endocrine research, dyslipidemia, endocrine regulation, genetic endocrinology, growth factors, hormone receptors, hormone action and regulation, management of endocrine diseases, clinical trials, epidemiology, molecular endocrinology, neuroendocrinology, neuropeptides, neurotransmitters, obesity, pediatric endocrinology, reproductive endocrinology, signal transduction, the anatomy and physiology of endocrine organs (i.e., the pituitary, thyroid, parathyroid, and adrenal glands, and the gonads), and endocrine diseases (diabetes, nutrition, osteoporosis, etc.).