从智能手机数字人体测量学预测骨矿物质含量：评估现有应用并开发新的预测模型

IF 1.7 4区医学 Q4 ENDOCRINOLOGY & METABOLISM

Journal of Clinical Densitometry Pub Date : 2024-10-24 DOI:10.1016/j.jocd.2024.101537

Austin J. Graybeal , Sydney H. Swafford , Abby T. Compton , Megan E. Renna , Tanner Thorsen , Jon Stavres

{"title":"从智能手机数字人体测量学预测骨矿物质含量：评估现有应用并开发新的预测模型","authors":"Austin J. Graybeal , Sydney H. Swafford , Abby T. Compton , Megan E. Renna , Tanner Thorsen , Jon Stavres","doi":"10.1016/j.jocd.2024.101537","DOIUrl":null,"url":null,"abstract":"<div><div><em>Introduction/Background:</em> Bone mineral content (BMC) is most commonly evaluated using dual-energy X-ray absorptiometry (DXA), but there are several challenges that limit use of DXA during routine care. Breakthroughs in digital imaging now allow smartphone applications to automate important anthropometrics that can predict several body composition components. However, it is unknown whether the anthropometrics automated using smartphone applications can predict DXA-derived BMC.</div><div><em>Methodology:</em> A total of 214 participants (129 F, 85 M) had BMC measurements collected from an existing proprietary prediction equation, embedded within a smartphone application (MeThreeSixty), and evaluated against DXA. LASSO regression was then used to develop a new BMC prediction equation using the anthropometric estimates produced by the smartphone application in a portion of the participants (n = 174), which was subsequently evaluated against DXA in the remaining sample (n = 40). BMC z-scores were calculated and used to identify the prevalence of <em>low BMC</em> for the existing and newly developed smartphone prediction equations and evaluated against DXA-derived z-scores.</div><div><em>Results:</em> Neither BMC estimates (R<sup>2</sup>: 0.72; RMSE: 376 g) nor BMC z-scores (R<sup>2</sup>: 0.55; RMSE: 1.09 SD) produced from the existing propriety prediction equation demonstrated equivalence with DXA in the combined sample. Moreover, the existing prediction equation had a 69.6 % accuracy of identifying <em>low BMC</em>. LASSO regression for the newly developed smartphone prediction model produced the following equation:</div><div>BMC (g) = -2020.769 + 60.902(<em>Black=1, 0=all other races</em>) – 180.364(<em>Asian=1, 0=all other races</em>) + 24.433(<em>height</em>) + 1.702(<em>weight</em>) + 2.92(<em>shoulder circumference</em>) + 0.258(<em>arm surface area</em>) – 715.29(<em>waist circumference/(BMI<sup>2/3</sup> x height<sup>1/2</sup>)</em>).</div><div>BMC (R<sup>2</sup>: 0.91; RMSE: 209 g) and BMC z-scores (R<sup>2</sup>: 0.85; RMSE: 0.61) produced from the newly developed equation in the testing sample demonstrated equivalence with DXA and had a 92.5 % accuracy of identifying <em>low BMC</em>.</div><div><em>Conclusions:</em> Smartphone anthropometrics provide accurate and clinically relevant BMC measurements outside of an advanced setting through the use of our newly-developed smartphone prediction model.</div></div>","PeriodicalId":50240,"journal":{"name":"Journal of Clinical Densitometry","volume":"28 1","pages":"Article 101537"},"PeriodicalIF":1.7000,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting bone mineral content from smartphone digital anthropometrics: evaluation of an existing application and the development of new prediction models\",\"authors\":\"Austin J. Graybeal , Sydney H. Swafford , Abby T. Compton , Megan E. Renna , Tanner Thorsen , Jon Stavres\",\"doi\":\"10.1016/j.jocd.2024.101537\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div><em>Introduction/Background:</em> Bone mineral content (BMC) is most commonly evaluated using dual-energy X-ray absorptiometry (DXA), but there are several challenges that limit use of DXA during routine care. Breakthroughs in digital imaging now allow smartphone applications to automate important anthropometrics that can predict several body composition components. However, it is unknown whether the anthropometrics automated using smartphone applications can predict DXA-derived BMC.</div><div><em>Methodology:</em> A total of 214 participants (129 F, 85 M) had BMC measurements collected from an existing proprietary prediction equation, embedded within a smartphone application (MeThreeSixty), and evaluated against DXA. LASSO regression was then used to develop a new BMC prediction equation using the anthropometric estimates produced by the smartphone application in a portion of the participants (n = 174), which was subsequently evaluated against DXA in the remaining sample (n = 40). BMC z-scores were calculated and used to identify the prevalence of <em>low BMC</em> for the existing and newly developed smartphone prediction equations and evaluated against DXA-derived z-scores.</div><div><em>Results:</em> Neither BMC estimates (R<sup>2</sup>: 0.72; RMSE: 376 g) nor BMC z-scores (R<sup>2</sup>: 0.55; RMSE: 1.09 SD) produced from the existing propriety prediction equation demonstrated equivalence with DXA in the combined sample. Moreover, the existing prediction equation had a 69.6 % accuracy of identifying <em>low BMC</em>. LASSO regression for the newly developed smartphone prediction model produced the following equation:</div><div>BMC (g) = -2020.769 + 60.902(<em>Black=1, 0=all other races</em>) – 180.364(<em>Asian=1, 0=all other races</em>) + 24.433(<em>height</em>) + 1.702(<em>weight</em>) + 2.92(<em>shoulder circumference</em>) + 0.258(<em>arm surface area</em>) – 715.29(<em>waist circumference/(BMI<sup>2/3</sup> x height<sup>1/2</sup>)</em>).</div><div>BMC (R<sup>2</sup>: 0.91; RMSE: 209 g) and BMC z-scores (R<sup>2</sup>: 0.85; RMSE: 0.61) produced from the newly developed equation in the testing sample demonstrated equivalence with DXA and had a 92.5 % accuracy of identifying <em>low BMC</em>.</div><div><em>Conclusions:</em> Smartphone anthropometrics provide accurate and clinically relevant BMC measurements outside of an advanced setting through the use of our newly-developed smartphone prediction model.</div></div>\",\"PeriodicalId\":50240,\"journal\":{\"name\":\"Journal of Clinical Densitometry\",\"volume\":\"28 1\",\"pages\":\"Article 101537\"},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-10-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Clinical Densitometry\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1094695024000702\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENDOCRINOLOGY & METABOLISM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Clinical Densitometry","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1094695024000702","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}

引用次数: 0

摘要

简介/背景：骨矿物质含量（BMC）最常用双能 X 射线吸收测量法（DXA）进行评估，但在日常护理过程中，DXA 的使用受到一些挑战的限制。现在，数字成像技术取得了突破性进展，智能手机应用程序可以自动进行重要的人体测量，预测身体成分的几个组成部分。然而，使用智能手机应用程序自动进行的人体测量是否能预测从 DXA 导出的 BMC 还不得而知：方法：共 214 名参与者（129 名女性，85 名男性）通过现有的专有预测方程收集了 BMC 测量值，将其嵌入智能手机应用程序（MeThreeSixty）中，并根据 DXA 进行评估。然后，利用智能手机应用程序对部分参与者（n = 174）进行的人体测量估算结果，采用 LASSO 回归方法建立了一个新的 BMC 预测方程，并随后根据 DXA 对其余样本（n = 40）进行了评估。对现有的和新开发的智能手机预测方程计算了BMC z-scores，用于确定低BMC的流行率，并与DXA得出的z-scores进行了对比评估：在综合样本中，现有专有预测方程得出的 BMC 估计值（R2：0.72；RMSE：376 g）和 BMC z-scores（R2：0.55；RMSE：1.09 SD）均未显示出与 DXA 的等效性。此外，现有预测方程识别低 BMC 的准确率为 69.6%。对新开发的智能手机预测模型进行 LASSO 回归得出以下公式：BMC（克）= -2020.769 + 60.902（黑人=1，0=所有其他种族）- 180.364（亚洲人=1，0=所有其他种族）+ 24.433（身高）+ 1.702（体重）+ 2.92（肩围）+ 0.在测试样本中，根据新开发的方程得出的 BMC（R2：0.91；RMSE：209 g）和 BMC z 分数（R2：0.85；RMSE：0.61）与 DXA 相当，识别低 BMC 的准确率为 92.5%：结论：通过使用我们新开发的智能手机预测模型，智能手机人体测量学可在高级环境之外提供准确且与临床相关的 BMC 测量值。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Predicting bone mineral content from smartphone digital anthropometrics: evaluation of an existing application and the development of new prediction models

Introduction/Background: Bone mineral content (BMC) is most commonly evaluated using dual-energy X-ray absorptiometry (DXA), but there are several challenges that limit use of DXA during routine care. Breakthroughs in digital imaging now allow smartphone applications to automate important anthropometrics that can predict several body composition components. However, it is unknown whether the anthropometrics automated using smartphone applications can predict DXA-derived BMC.

Methodology: A total of 214 participants (129 F, 85 M) had BMC measurements collected from an existing proprietary prediction equation, embedded within a smartphone application (MeThreeSixty), and evaluated against DXA. LASSO regression was then used to develop a new BMC prediction equation using the anthropometric estimates produced by the smartphone application in a portion of the participants (n = 174), which was subsequently evaluated against DXA in the remaining sample (n = 40). BMC z-scores were calculated and used to identify the prevalence of low BMC for the existing and newly developed smartphone prediction equations and evaluated against DXA-derived z-scores.

Results: Neither BMC estimates (R²: 0.72; RMSE: 376 g) nor BMC z-scores (R²: 0.55; RMSE: 1.09 SD) produced from the existing propriety prediction equation demonstrated equivalence with DXA in the combined sample. Moreover, the existing prediction equation had a 69.6 % accuracy of identifying low BMC. LASSO regression for the newly developed smartphone prediction model produced the following equation:

BMC (g) = -2020.769 + 60.902(Black=1, 0=all other races) – 180.364(Asian=1, 0=all other races) + 24.433(height) + 1.702(weight) + 2.92(shoulder circumference) + 0.258(arm surface area) – 715.29(waist circumference/(BMI^2/3 x height^1/2)).

BMC (R²: 0.91; RMSE: 209 g) and BMC z-scores (R²: 0.85; RMSE: 0.61) produced from the newly developed equation in the testing sample demonstrated equivalence with DXA and had a 92.5 % accuracy of identifying low BMC.

Conclusions: Smartphone anthropometrics provide accurate and clinically relevant BMC measurements outside of an advanced setting through the use of our newly-developed smartphone prediction model.

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

Journal of Clinical Densitometry 医学-内分泌学与代谢

CiteScore

4.90

自引率

8.00%

发文量

审稿时长

90 days

期刊介绍： The Journal is committed to serving ISCD''s mission - the education of heterogenous physician specialties and technologists who are involved in the clinical assessment of skeletal health. The focus of JCD is bone mass measurement, including epidemiology of bone mass, how drugs and diseases alter bone mass, new techniques and quality assurance in bone mass imaging technologies, and bone mass health/economics. Combining high quality research and review articles with sound, practice-oriented advice, JCD meets the diverse diagnostic and management needs of radiologists, endocrinologists, nephrologists, rheumatologists, gynecologists, family physicians, internists, and technologists whose patients require diagnostic clinical densitometry for therapeutic management.