Data and Information Integration for Risk Prediction in the Era of Big Data

大数据时代的数据与信息融合风险预测

• 批准号: 10480872
• 负责人: Jinbo Chen
• 金额: $ 39.54万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-20 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10480872
• 关键词: Address; Adopted; Big Data; Biological Markers; Breast Cancer Risk Factor; Calibration; Clinical Research; Communities; Data; Data Set; Ensure; Estrogens; Evaluation; Feasibility Studies; Fruit; Gestational Diabetes; Goals; Hormonal; Individual; Logistic Regressions; Logistics; Malignant Neoplasms; Measures; Methods; Modeling; Outcome; Patients; Plague; Population; Publications; Research Design; Risk; Sampling; Sampling Studies; Source; Statistical Methods; Target Populations; Time; Validation; base; biomarker evaluation; breast density; case control; cost effective; design; disorder prevention; epidemiology study; flexibility; improved; innovation; metabolomics; model building; novel; outcome prediction; precision medicine; predictive modeling; predictive test; risk prediction; risk prediction model; user friendly software

Abstract Toward precision medicine and precision disease prevention, the overarching goal of this proposal is to develop innovative statistical methods for accurate risk prediction. We address three challenges that plague studies on the value of candidate risk predictors that adds to established predictors for improved predictive accuracy: there is often a lack of independent validation data, the source population for the study sample and the target population of prediction are often different, no statistical methods are currently available for developing risk prediction models using individually-matched case-control data, and there is a lack of statistical methods for helping assess study feasibility beyond standard power calculation for testing predictor-outcome association. On the other hand, data and information that are external to the study may well exist and can be exploited to alleviate these challenges. For example, a model with only standard predictors often exists and has been validated, and the distribution of standard risk predictors in the target population of prediction is often available. We propose that external data and information can be exploited to address the above-mentioned challenges for candidate predictor evaluation, and develop innovative statistical methods to bring this idea to fruition. Considering prediction of a binary outcome, we propose a novel method to building logistic prediction models that are guaranteed to calibrate well in the target population, an innovative method for risk prediction with individually matched case-control data, and a method to project the added value of candidate predictors to help assess study feasibility. Our methods, accompanied by user-friendly software, will facilitate cost effective and timely predictor evaluation for predicting binary outcomes. Our methods were motivated by and will be applied to several PI Chen's collaborative studies.

摘要 对于精准医学和精准疾病预防，这项提案的总体目标是 发展创新的统计方法，以准确预测风险。我们应对以下三个挑战 对候选风险预测因子的价值进行的鼠疫研究，这些候选风险预测因子添加到已建立的预测因子中以进行改进 预测准确性：通常缺乏独立的验证数据，即 研究样本和目标人群的预测往往不同，没有统计方法 目前可用于使用单独匹配的病例对照数据开发风险预测模型， 而且缺乏统计方法来帮助评估超出标准权力的研究可行性 测试预测者-结果关联性的计算。另一方面，数据和信息是 这项研究的外部因素很可能存在，并可被利用来缓解这些挑战。例如，一个 只有标准预测因子的模型经常存在，并已得到验证，而标准预测因子的分布 风险预测器在目标人群的预测中往往是可用的。我们建议外部数据和 可以利用信息来解决候选预测者面临的上述挑战 评估，并开发创新的统计方法，以实现这一想法。考虑 对于二元结果的预测，我们提出了一种新的方法来建立Logistic预测模型，该模型 保证在目标人群中很好地校准，这是一种创新的风险预测方法， 单独匹配的病例对照数据，以及将候选预测因素的附加值投影到 帮助评估研究的可行性。我们的方法，伴随着用户友好的软件，将降低成本 用于预测二元结果的有效和及时的预测者评估。我们的方法的动机是 并将应用于几个皮晨的合作研究。