Predicting who will fracture: Exploration of machine learning in the observational Women's Health Initiative Study dataset.
Predicting who will fracture: Exploration of machine learning in the observational Women's Health Initiative Study dataset.
批准号:
10707881
负责人:
ALEX BUI
金额:
$14.1万
依托单位国家:
美国
项目类别:
财政年份:
2022
资助国家:
美国
项目状态:
已结题
起止时间:
2022-09-21 至 2024-08-31
关键词:
AccelerationAgeAreaAssessment toolBayesian NetworkBeliefBone DensityBone TissueCalibrationCessation of lifeCharacteristicsClassificationClinicalDataData SetDeteriorationDiscriminationDiseaseEarly InterventionElectronic Health RecordFemurFractureFutureGoalsGuidelinesIndividualInferiorLifeLogistic RegressionsLongitudinal cohortMachine LearningMenopauseMethodologyMethodsModelingNeckOsteoporosisOsteoporoticOutcomePerformancePopulationPostmenopausePredictive ValueProspective StudiesPublic HealthROC CurveRecommendationRiskRisk AssessmentRisk EstimateRisk FactorsSelf AssessmentSiteSpecificityStratificationTechniquesTestingUnited StatesUnited States Preventative Services Task ForceValidationWomanWomen&aposs Healthage groupagedbonebone fragilitybone lossbone masscandidate selectionchronic paindesigndisabilityelectronic health record systemexperiencefollow-upfracture riskgradient boostinghuman old age (65+)improvedindexinginsightmachine learning modelmachine learning predictionmodel buildingosteoporosis with pathological fractureperformance testspharmacologicpredictive modelingpredictive toolsrandom forestrepositoryrisk predictionscreeningscreening guidelinestool
中文摘要
项目摘要
所有绝经后妇女中有一半将在其剩余的生命中经历与骨质疏松症相关的骨折。
由于这些骨折可能导致残疾、丧失独立性和死亡,因此确定哪些人处于风险中非常重要
进行早期干预和缓解。虽然临床指南支持对女性进行常规骨质疏松症筛查,
年龄≥65岁,仅建议对年龄50-64岁的绝经后年轻女性进行选择性筛查
基于风险评估工具的使用(例如,OST、FRAX、SCORE)。然而,我们已经表明,这些
工具-不是专门为这个年龄组的妇女开发的-不能很好地区分
患有和未患有骨质疏松症(基于骨矿物质密度,BMD)和/或随后骨折的女性。
本项目的目的是探索机器学习(ML),以改善骨质疏松症的风险评估,
年轻的绝经后妇女。既往对骨质疏松症和相关骨折进行了基于ML的分析,
非美国人口和/或规模有限。我们将使用大型妇女健康倡议(WHI)研究
(来自美国的超过160,000人),以开发,验证和比较不同的机器学习
针对年轻绝经后的方法(随机森林;逻辑回归;动态信念网络,DBN)
妇女ML模型将被构建和评估用于两个任务:1)预测老年女性的骨折风险
50-64(目标1);和2)预测骨质疏松症(根据BMD;目标2)。在每种情况下,我们将使用
现有的风险因素,以及从WHI收集的额外变量,以确定新的
可以提高预测能力的功能。我们还将通过构建DBN来评估时态模型的价值,
利用个人过去的观察来指导预测。我们将计算技术性能指标
(e.g.,敏感性、特异性、阳性预测值),并进行误差分析以对比哪些(亚)组
每个模型(in)正确地识别。我们亦会进行敏感度分析,以确定不同
变量对模型预测的鲁棒性的影响。最后,我们计划对模型进行外部验证(目标3
从目标1和2使用电子健康记录(EHR)数据集从加州大学洛杉矶分校和加州大学旧金山分校,调查程度
可运输性。R21的成功执行将:1)开发和测试不同的ML模型,预测主要的
美国女性中的骨质疏松性骨折和骨质疏松症; 2)确定告知风险的潜在其他变量
这些条件;和3)提供洞察力的领域,这种ML模型可以通过分层改进,
阳离子和/或未来的方法。该R21的结果将作为更广泛的
R 01开发更有效的骨折和骨关节炎风险预测模型。
英文摘要
PROJECT ABSTRACT
Half of all postmenopausal women will experience an osteoporosis-related fracture in their remaining lifetimes.
As these fractures can lead to disability, loss of independence, and death, it is important to identify who is at risk
for early intervention and mitigation. While clinical guidelines support routine osteoporosis screening for women
aged ≥65 years, only selective screening is recommended for younger postmenopausal women aged 50-64
based on the use of risk assessment tools (e.g., OST, FRAX, SCORE). However, we have shown that these
tools – which were not specifically developed for women in this age group – do not differentiate well between
women who do and do not have osteoporosis (based on bone mineral density, BMD) and/or subsequent fracture.
The objective of this project is to explore machine learning (ML) to improve osteoporosis risk assessment in
young postmenopausal women. Prior ML-based analyses for osteoporosis and related fractures exist but are on
non-American populations and/or are of limited size. We will use the large Women's Health Initiative (WHI) Study
(>160,000 individuals from the United States), to develop, validate, and compare different machine learning
approaches (random forests; logistic regression; dynamic belief network, DBN) for younger postmenopausal
women. ML models will be constructed and assessed for two tasks: 1) predicting fracture risk in women aged
50-64 (Aim 1); and 2) predicting osteoporosis (per BMD; Aim 2). In each case, we will build ML models using
existing risk factors from current tools, as well as add additional variables collected from the WHI to identify new
features that may improve predictive power. We will also assess the value of temporal model by building DBNs,
using an individual's past observations to guide predictions. We will compute technical performance metrics
(e.g., sensitivity, specificity, positive predictive value) and conduct error analyses to contrast what (sub)groups
each model (in)correctly identifies. We will also perform sensitivity analyses to ascertain the impact of different
variables on the robustness of the model's predictions. Lastly, we plan to externally validate (Aim 3) the models
from Aims 1 & 2 using electronic health record (EHR) datasets from UCLA and UCSF, investigating the degree
of transportability. Successful execution of this R21 will: 1) develop and test different ML models predicting major
osteoporotic fracture and osteoporosis in US women; 2) identify potential additional variables that inform the risk
of these conditions; and 3) provide insight into areas where such ML-models may be improved through stratifi-
cation and/or future methodological approaches. The results from this R21 will serve as a baseline for a broader
R01 to develop more effective predictive models for fracture and osteoporotic risk.
期刊论文(1)
专著(0)
科研奖励(0)
会议论文
Race and Ethnicity and Fracture Prediction Among Younger Postmenopausal Women in the Women's Health Initiative Study.
妇女健康倡议研究中年轻绝经后妇女的种族和民族以及骨折预测。
DOI:
10.1001/jamainternmed.2023.1253
发表时间:
2023
期刊:
JAMA internal medicine
影响因子:
39
作者:
[Crandall,CarolynJ, Larson,JosephC, Schousboe,JohnT, Manson,JoAnnE, Watts,NelsonB, Robbins,JohnA, Schnatz,Peter, Nassir,Rami, Shadyab,AladdinH, Johnson,KarenC, Cauley,JaneA, Ensrud,KristineE]
通讯作者:
Ensrud,KristineE
Building BRIDGEs: Coordinating Standards, Diversity, and Ethics to Advance Biomedical AI
-
批准号:10801686
-
项目类别:
-
资助金额:$58.6万
-
财政年份:2023
-
负责人:ALEX BUI
-
依托单位:
Building BRIDGEs: Coordinating Standards, Diversity, and Ethics to Advance Biomedical AI
-
批准号:10473397
-
项目类别:
-
资助金额:$250.42万
-
财政年份:2022
-
负责人:ALEX BUI
-
依托单位:
Building BRIDGEs: Coordinating Standards, Diversity, and Ethics to Advance Biomedical AI
-
批准号:10655487
-
项目类别:
-
资助金额:$247.75万
-
财政年份:2022
-
负责人:ALEX BUI
-
依托单位:
Biomedical Data Science Training Program for Precision Health Equity
-
批准号:10615779
-
项目类别:
-
资助金额:$47.58万
-
财政年份:2022
-
负责人:ALEX BUI
-
依托单位:
Predicting who will fracture: Exploration of machine learning in the observational Women's Health Initiative Study dataset.
-
批准号:10370048
-
项目类别:
-
资助金额:$16.89万
-
财政年份:2022
-
负责人:ALEX BUI
-
依托单位:
Biomedical Data Science Training Program for Precision Health Equity
-
批准号:10406058
-
项目类别:
-
资助金额:$30.25万
-
财政年份:2022
-
负责人:ALEX BUI
-
依托单位:
Network Core
-
批准号:10285908
-
项目类别:
-
资助金额:$5.28万
-
财政年份:2021
-
负责人:ALEX BUI
-
依托单位:
Network Core
-
批准号:10657821
-
项目类别:
-
资助金额:$6.16万
-
财政年份:2021
-
负责人:ALEX BUI
-
依托单位:
Prediction of Chronic Kidney Disease by Simulation Modeling to Improve the Health of Minority Populations
-
批准号:10523518
-
项目类别:
-
资助金额:$37.44万
-
财政年份:2020
-
负责人:ALEX BUI
-
依托单位:
Prediction of Chronic Kidney Disease by Simulation Modeling to Improve the Health of Minority Populations
-
批准号:10087957
-
项目类别:
-
资助金额:$37.49万
-
财政年份:2020
-
负责人:ALEX BUI
-
依托单位:
Prediction of Chronic Kidney Disease by Simulation Modeling to Improve the Health of Minority Populations
-
批准号:10306323
-
项目类别:
-
资助金额:$37.44万
-
财政年份:2020
-
负责人:ALEX BUI
-
依托单位:
PREMIERE: A PREdictive Model Index and Exchange REpository
-
批准号:10597854
-
项目类别:
-
资助金额:$29.15万
-
财政年份:2019
-
负责人:ALEX BUI
-
依托单位:
PREMIERE: A PREdictive Model Index and Exchange REpository
-
批准号:10228009
-
项目类别:
-
资助金额:$68.24万
-
财政年份:2019
-
负责人:ALEX BUI
-
依托单位:
PREMIERE: A PREdictive Model Index and Exchange REpository
-
批准号:10668938
-
项目类别:
-
资助金额:$67.35万
-
财政年份:2019
-
负责人:ALEX BUI
-
依托单位:
PREMIERE: A PREdictive Model Index and Exchange REpository
-
批准号:10016297
-
项目类别:
-
资助金额:$67.35万
-
财政年份:2019
-
负责人:ALEX BUI
-
依托单位:
iDISCOVER: Integrated Data Science Training in CardioVascular Medicine
-
批准号:10208936
-
项目类别:
-
资助金额:$37.39万
-
财政年份:2018
-
负责人:ALEX BUI
-
依托单位:
iDISCOVER: Integrated Data Science Training in CardioVascular Medicine
-
批准号:10458658
-
项目类别:
-
资助金额:$33.43万
-
财政年份:2018
-
负责人:ALEX BUI
-
依托单位:
J. NRSA Training Core
-
批准号:10655656
-
项目类别:
-
资助金额:$86.67万
-
财政年份:2016
-
负责人:ALEX BUI
-
依托单位:
J. NRSA Training Core
-
批准号:10557299
-
项目类别:
-
资助金额:$83.86万
-
财政年份:2016
-
负责人:ALEX BUI
-
依托单位:
Integrating & Visualizing Clinical, Environmental, and Sensor Data
-
批准号:9077038
-
项目类别:
-
资助金额:$212.06万
-
财政年份:2015
-
负责人:ALEX BUI
-
依托单位:
国内基金
海外基金
登录
查看更多内容
补阳还五汤通过AGE-RAGE通路调控脓毒症免疫失衡的机制与转化研究
-
批准号:JCZRLH202601523
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2026
-
负责人:
-
依托单位:
靶向递送一氧化碳调控AGE-RAGE级联反应促进糖尿病创面愈合研究
-
批准号:JCZRQN202500010
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2025
-
负责人:
-
依托单位:
对香豆酸抑制AGE-RAGE-Ang-1通路改善海马血管生成障碍发挥抗阿尔兹海默病作用
-
批准号:2025JJ70209
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2025
-
负责人:雷芬芳
-
依托单位:
AGE-RAGE通路调控慢性胰腺炎纤维化进程的作用及分子机制
-
批准号:--
-
项目类别:面上项目
-
资助金额:--
-
批准年份:2024
-
负责人:万荣
-
依托单位:
甜茶抑制AGE-RAGE通路增强突触可塑性改善小鼠抑郁样行为
-
批准号:2023JJ50274
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2023
-
负责人:贺志明
-
依托单位:
蒙药额尔敦-乌日勒基础方调控AGE-RAGE信号通路改善术后认知功能障碍研究
-
批准号:--
-
项目类别:地区科学基金项目
-
资助金额:33万元
-
批准年份:2022
-
负责人:都义日
-
依托单位:
补肾健脾祛瘀方调控AGE/RAGE信号通路在再生障碍性贫血骨髓间充质干细胞功能受损的作用与机制研究
-
批准号:--
-
项目类别:面上项目
-
资助金额:52万元
-
批准年份:2022
-
负责人:叶宝东
-
依托单位:
LncRNA GAS5在2型糖尿病动脉粥样硬化中对AGE-RAGE 信号通路上相关基因的调控作用及机制研究
-
批准号:
-
项目类别:省市级项目
-
资助金额:10.0万元
-
批准年份:2022
-
负责人:于海兵
-
依托单位:
围绕GLP1-Arginine-AGE/RAGE轴构建探针组学方法探索大柴胡汤异病同治的效应机制
-
批准号:81973577
-
项目类别:面上项目
-
资助金额:55.0万元
-
批准年份:2019
-
负责人:辛贵忠
-
依托单位:
AGE/RAGE通路microRNA编码基因多态性与2型糖尿病并发冠心病的关联研究
-
批准号:81602908
-
项目类别:青年科学基金项目
-
资助金额:18.0万元
-
批准年份:2016
-
负责人:刘括
-
依托单位: