Predicting who will fracture: Exploration of machine learning in the observational Women's Health Initiative Study dataset.

预测谁会骨折：观察性妇女健康倡议研究数据集中机器学习的探索。

• 批准号: 10370048
• 负责人: ALEX BUI
• 金额: $ 16.89万
• 依托单位: UNIVERSITY OF CALIFORNIA LOS ANGELES
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-21 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10370048
• 关键词: Advisory Committees; Age; Area; Assessment tool; Bayesian Network; Belief; Bone Density; Bone Tissue; Cessation of life; Characteristics; Classification; Clinical; Data; Data Set; Deterioration; Discrimination; Disease; Early Intervention; Electronic Health Record; Fracture; Future; Goals; Guidelines; Individual; Inferior; Lead; Life; Logistic Regressions; Longitudinal cohort; Machine Learning; Menopause; Methodology; Methods; Modeling; Neck; Osteoporosis; Osteoporotic; Outcome; Performance; Pharmacology; Population; Postmenopause; Predictive Value; Preventive service; Prospective Studies; Public Health; ROC Curve; Risk; Risk Assessment; Risk Estimate; Risk Factors; Self Assessment; Sensitivity and Specificity; Site; Stratification; System; Techniques; Testing; United States; Validation; Woman; Women' s Health; age group; aged; base; bone fragility; bone loss; bone mass; chronic pain; design; disability; experience; follow-up; fracture risk; gradient boosting; human old age (65+); improved; indexing; insight; machine learning model; machine learning prediction; model building; osteoporosis with pathological fracture; performance tests; predictive modeling; predictive tools; random forest; repository; risk prediction; screening; screening guidelines; tool

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.

项目摘要 半数绝经后女性在其余生中将经历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危险之中非常重要 以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50-64岁的年轻绝经后女性进行选择性筛查 基于风险评估工具（例如 OST、FRAX、SCORE）的使用。然而，我们已经证明，这些 工具——并不是专门为这个年龄段的女性开发的——不能很好地区分 患有或未患有骨质疏松症（基于骨矿物质密度，BMD）和/或随后骨折的女性。 该项目的目标是探索机器学习（ML）以改善骨质疏松症风险评估 年轻的绝经后妇女。先前存在基于机器学习的骨质疏松症和相关骨折分析，但仍在进行中 非美国人口和/或规模有限。我们将利用大型女性健康倡议 (WHI) 研究 （来自美国的超过 160,000 人），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） 女性。将针对两项任务构建和评估 ML 模型：1）预测老年女性的骨折风险 50-64（目标 1）； 2) 预测骨质疏松症（根据 BMD；目标 2）。在每种情况下，我们都会使用以下方法构建 ML 模型 现有工具中的现有风险因素，以及添加从 WHI 收集的其他变量来识别新的风险因素 可以提高预测能力的功能。我们还将通过构建 DBN 来评估时间模型的价值， 使用个人过去的观察来指导预测。我们将计算技术性能指标 （例如敏感性、特异性、阳性预测值）并进行误差分析以对比哪些（子）组 每个模型都能正确识别。我们还将进行敏感性分析，以确定不同因素的影响 影响模型预测稳健性的变量。最后，我们计划对模型进行外部验证（目标 3） 目标 1 和 2 使用 UCLA 和 UCSF 的电子健康记录 (EHR) 数据集，调查学位 的可运输性。成功执行此 R21 将：1）开发和测试不同的 ML 模型来预测专业 美国女性的骨质疏松性骨折和骨质疏松症； 2) 识别告知风险的潜在附加变量 这些条件； 3）深入了解此类 ML 模型可以通过分层进行改进的领域 阳离子和/或未来的方法论方法。 R21 的结果将作为更广泛的基线 R01 开发更有效的骨折和骨质疏松风险预测模型。