使用机器学习模型表征卡塔尔生物库参与者的低股骨颈骨密度。

IF 2.2 3区 医学 Q2 ORTHOPEDICS
Nedhal Al-Husaini, Rozaimi Razali, Amal Al-Haidose, Mohammed Al-Hamdani, Atiyeh M Abdallah
{"title":"使用机器学习模型表征卡塔尔生物库参与者的低股骨颈骨密度。","authors":"Nedhal Al-Husaini, Rozaimi Razali, Amal Al-Haidose, Mohammed Al-Hamdani, Atiyeh M Abdallah","doi":"10.1186/s12891-025-08726-5","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Identifying determinants of low bone mineral density (BMD) is crucial for understanding the underlying pathobiology and developing effective prevention and management strategies. Here we applied machine learning (ML) algorithms to predict low femoral neck BMD using standard demographic and laboratory parameters.</p><p><strong>Methods: </strong>Data from 4829 healthy individuals enrolled in the Qatar Biobank were studied. The cohort was split 60% and 40% for training and validation, respectively. Logistic regression algorithms were implemented to predict femoral neck BMD, and the area under the curve (AUC) was used to evaluate model performance. Features associated with low femoral neck BMD were subjected the statistical analysis to establish associated risk.</p><p><strong>Results: </strong>The final predictive model had an AUC of 86.4% (accuracy 79%, 95%CI: 77.98-80.65%) for the training set and 85.9% (accuracy 78%, 95% CI: 75.92-80.61%) for the validation set. Sex, body mass index, age, creatinine, alkaline phosphatase, total cholesterol, and magnesium were identified as informative features for predicting femoral neck BMD. Age (odds ratio (OR) 0.945, 95%CI: 0.945-0.963, p < 0.001), alkaline phosphatase (OR 0.990, 95%CI: 0.986-0.995, p < 0.001), total cholesterol (OR 0.845, 95%CI: 0.767-0.931, p < 0.001), and magnesium (OR 0.136, 95%CI: 0.034-0.571, p < 0.001) were inversely associated with BMD, while BMI and creatinine were positively associated with BMD (OR 1.116, 95%CI: 1.140-1.192, p < 0.001 and OR 1.031, 95%CI: 1.022-1.039, p < 0.001, respectively).</p><p><strong>Conclusion: </strong>Several biological determinants were found to have a significant global effect on BMD with a reasonable effect size. By combining standard demographic and laboratory variables, our model provides proof-of-concept for predicting low BMD. This approach suggests that, with further validation, an ML-driven model could complement or potentially reduce the need for imaging when assessing individuals at risk for low BMD, which is an important component of fracture risk prediction.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9189,"journal":{"name":"BMC Musculoskeletal Disorders","volume":"26 1","pages":"492"},"PeriodicalIF":2.2000,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12085013/pdf/","citationCount":"0","resultStr":"{\"title\":\"Characterizing low femoral neck BMD in Qatar Biobank participants using machine learning models.\",\"authors\":\"Nedhal Al-Husaini, Rozaimi Razali, Amal Al-Haidose, Mohammed Al-Hamdani, Atiyeh M Abdallah\",\"doi\":\"10.1186/s12891-025-08726-5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Identifying determinants of low bone mineral density (BMD) is crucial for understanding the underlying pathobiology and developing effective prevention and management strategies. Here we applied machine learning (ML) algorithms to predict low femoral neck BMD using standard demographic and laboratory parameters.</p><p><strong>Methods: </strong>Data from 4829 healthy individuals enrolled in the Qatar Biobank were studied. The cohort was split 60% and 40% for training and validation, respectively. Logistic regression algorithms were implemented to predict femoral neck BMD, and the area under the curve (AUC) was used to evaluate model performance. Features associated with low femoral neck BMD were subjected the statistical analysis to establish associated risk.</p><p><strong>Results: </strong>The final predictive model had an AUC of 86.4% (accuracy 79%, 95%CI: 77.98-80.65%) for the training set and 85.9% (accuracy 78%, 95% CI: 75.92-80.61%) for the validation set. Sex, body mass index, age, creatinine, alkaline phosphatase, total cholesterol, and magnesium were identified as informative features for predicting femoral neck BMD. Age (odds ratio (OR) 0.945, 95%CI: 0.945-0.963, p < 0.001), alkaline phosphatase (OR 0.990, 95%CI: 0.986-0.995, p < 0.001), total cholesterol (OR 0.845, 95%CI: 0.767-0.931, p < 0.001), and magnesium (OR 0.136, 95%CI: 0.034-0.571, p < 0.001) were inversely associated with BMD, while BMI and creatinine were positively associated with BMD (OR 1.116, 95%CI: 1.140-1.192, p < 0.001 and OR 1.031, 95%CI: 1.022-1.039, p < 0.001, respectively).</p><p><strong>Conclusion: </strong>Several biological determinants were found to have a significant global effect on BMD with a reasonable effect size. By combining standard demographic and laboratory variables, our model provides proof-of-concept for predicting low BMD. This approach suggests that, with further validation, an ML-driven model could complement or potentially reduce the need for imaging when assessing individuals at risk for low BMD, which is an important component of fracture risk prediction.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>\",\"PeriodicalId\":9189,\"journal\":{\"name\":\"BMC Musculoskeletal Disorders\",\"volume\":\"26 1\",\"pages\":\"492\"},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2025-05-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12085013/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC Musculoskeletal Disorders\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s12891-025-08726-5\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ORTHOPEDICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Musculoskeletal Disorders","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12891-025-08726-5","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ORTHOPEDICS","Score":null,"Total":0}
引用次数: 0

摘要

背景:确定低骨密度(BMD)的决定因素对于了解潜在的病理生物学和制定有效的预防和管理策略至关重要。在这里,我们应用机器学习(ML)算法使用标准人口统计学和实验室参数来预测股骨颈骨密度低。方法:对卡塔尔生物库4829名健康个体的数据进行研究。该队列分为60%和40%,分别用于培训和验证。采用Logistic回归算法预测股骨颈骨密度,采用曲线下面积(AUC)评价模型性能。对与股骨颈骨密度低相关的特征进行统计分析,以确定相关的风险。结果:最终的预测模型对于训练集的AUC为86.4%(准确率79%,95%CI: 77.98 ~ 80.65%),对于验证集的AUC为85.9%(准确率78%,95%CI: 75.92 ~ 80.61%)。性别、体重指数、年龄、肌酐、碱性磷酸酶、总胆固醇和镁被确定为预测股骨颈骨密度的信息特征。年龄(比值比(OR) 0.945, 95%CI: 0.945-0.963, p)结论:几种生物决定因素对骨密度有显著的整体影响,且效应量合理。通过结合标准人口统计学和实验室变量,我们的模型为预测低骨密度提供了概念验证。该方法表明,通过进一步验证,机器学习驱动的模型可以补充或潜在地减少在评估低骨密度风险个体时对成像的需求,这是骨折风险预测的重要组成部分。临床试验号:不适用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Characterizing low femoral neck BMD in Qatar Biobank participants using machine learning models.

Background: Identifying determinants of low bone mineral density (BMD) is crucial for understanding the underlying pathobiology and developing effective prevention and management strategies. Here we applied machine learning (ML) algorithms to predict low femoral neck BMD using standard demographic and laboratory parameters.

Methods: Data from 4829 healthy individuals enrolled in the Qatar Biobank were studied. The cohort was split 60% and 40% for training and validation, respectively. Logistic regression algorithms were implemented to predict femoral neck BMD, and the area under the curve (AUC) was used to evaluate model performance. Features associated with low femoral neck BMD were subjected the statistical analysis to establish associated risk.

Results: The final predictive model had an AUC of 86.4% (accuracy 79%, 95%CI: 77.98-80.65%) for the training set and 85.9% (accuracy 78%, 95% CI: 75.92-80.61%) for the validation set. Sex, body mass index, age, creatinine, alkaline phosphatase, total cholesterol, and magnesium were identified as informative features for predicting femoral neck BMD. Age (odds ratio (OR) 0.945, 95%CI: 0.945-0.963, p < 0.001), alkaline phosphatase (OR 0.990, 95%CI: 0.986-0.995, p < 0.001), total cholesterol (OR 0.845, 95%CI: 0.767-0.931, p < 0.001), and magnesium (OR 0.136, 95%CI: 0.034-0.571, p < 0.001) were inversely associated with BMD, while BMI and creatinine were positively associated with BMD (OR 1.116, 95%CI: 1.140-1.192, p < 0.001 and OR 1.031, 95%CI: 1.022-1.039, p < 0.001, respectively).

Conclusion: Several biological determinants were found to have a significant global effect on BMD with a reasonable effect size. By combining standard demographic and laboratory variables, our model provides proof-of-concept for predicting low BMD. This approach suggests that, with further validation, an ML-driven model could complement or potentially reduce the need for imaging when assessing individuals at risk for low BMD, which is an important component of fracture risk prediction.

Clinical trial number: Not applicable.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
BMC Musculoskeletal Disorders
BMC Musculoskeletal Disorders 医学-风湿病学
CiteScore
3.80
自引率
8.70%
发文量
1017
审稿时长
3-6 weeks
期刊介绍: BMC Musculoskeletal Disorders is an open access, peer-reviewed journal that considers articles on all aspects of the prevention, diagnosis and management of musculoskeletal disorders, as well as related molecular genetics, pathophysiology, and epidemiology. The scope of the Journal covers research into rheumatic diseases where the primary focus relates specifically to a component(s) of the musculoskeletal system.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信