Methods for High-Dimensional Statistical Inference and Individualized Risk Prediction under Semi-Competing Risks

半竞争风险下的高维统计推断和个体化风险预测方法

• 批准号: 10249946
• 负责人: Harrison Reeder
• 金额: $ 3.49万
• 依托单位: HARVARD SCHOOL OF PUBLIC HEALTH
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2022-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10249946
• 关键词: Address; Admission activity; Affect; Algorithms; Birth; Caring; Characteristics; Clinical; Code; Collaborations; Computer software; Data; Data Sources; Decision Making; Developed Countries; Developing Countries; Development; Disease; Early Intervention; Electronic Health Record; Equilibrium; Event; Fellowship; Fetal health; Future; Goals; Health; Healthcare; Infant; Israel; Joints; Journals; Lasso; Machine Learning; Manuscripts; Maternal Health; Medical center; Methodology; Methods; Modeling; Modernization; Mothers; Neonatal Mortality; Neural Network Simulation; Outcome; Patient Care; Patients; Peer Review; Performance; Pre-Eclampsia; Pregnancy; Pregnant Women; Premature Birth; Probability; Publications; Publishing; Quality of Care; Reproducibility; Research; Research Personnel; Risk; Risk Factors; Software Tools; Source; Statistical Methods; Survival Analysis; Techniques; Time; Woman; Work; deep learning; experience; falls; feedforward neural network; fetal; flexibility; genomic data; high dimensionality; improved; improved outcome; individual patient; insight; interactive tool; interest; large datasets; machine learning method; method development; multidimensional data; neonatal health; neonatal morbidity; novel; outcome prediction; personalized decision; personalized health care; personalized predictions; personalized risk prediction; predictive modeling; prevent; prospective; risk prediction; risk stratification; simulation; skills; statistical and machine learning; tailored health care; theories; tool; unborn child; user-friendly

Project Summary/Abstract Patient care has been transformed by the availability of high-dimensional sources like electronic health records (EHR) and genomic data, allowing health care decisions to be tailored to individual patients. Statistical methods have been developed to efficiently use such high dimensional data, but critical gaps still remain. Several common models for survival analysis have recently been extended to accommodate high-dimensional variable selection and machine learning prediction methods, but similar tools have not yet been developed for the setting of semi- competing risks. In the semi-competing risks setting, interest focuses on jointly modeling both a terminal time- to-event outcome, as well as a non-terminal time-to-event outcome which can only occur for subjects who have not yet experienced the terminal event. Examples of this exist in severe pregnancy-related diseases such as pre-eclampsia (PE - further described below). PE and subsequent delivery are natural semi-competing risks, as PE can develop before delivery, but not after. Current methods do not provide analysts with data-driven tools for uncovering important covariates from high-dimensional data, and clinicians lack meaningful, personalized predictions of patients' joint probability of experiencing one or both outcomes prospectively through time. This proposal addresses these methodological gaps with tools for high-dimensional inference and prediction. In Aim 1, I will address the challenge of variable selection by developing a suite of regularized estimators for se- lecting important covariates from large datasets into a semi-competing risks model, and evaluating performance by simulation. In Aim 2, I will create a deep feed forward neural network modeling framework for predicting individual patients' joint probabilities of experiencing one or both outcomes of interest across future time points. Together, these aims will improve personalization of health care decisions. Software will be developed that provides researchers practical and user-friendly tools for applying these methods. In Aim 3, I will apply these approaches for semi-competing risks to evaluate risk of PE, which is globally a leading cause of maternal and fetal/neonatal mortality and morbidity. Using EHR pregnancy data from 50,000 births between 2011-2020, I will use the proposed variable selection methods to develop a model identifying risk factors for PE along with factors affecting time-to-delivery among PE patients. Through this work, I will also build a deep learning model in order to jointly predict maternal PE and NICU admission of the infant, yielding personalized prediction plots to facilitate care decisions that balance maternal and fetal health risks. For ease of use by clinicians and patients, I will disseminate this prediction model using an interactive online tool.

项目总结/摘要 电子健康记录等高维资源的可用性改变了患者护理 (EHR)和基因组数据，使医疗保健决策能够为个体患者量身定制。统计方法 已经开发出有效地使用这种高维数据，但仍然存在关键的差距。几种常见 生存分析的模型最近已经扩展到适应高维变量选择 和机器学习预测方法，但类似的工具尚未开发用于设置半 竞争风险。在半竞争的风险设置，兴趣集中在联合建模两个终端时间- 至事件结局，以及非终末至事件时间结局，仅发生于 还没有经历过终点事件。这方面的例子存在于严重的妊娠相关疾病，如 先兆子痫（PE -下文进一步描述）。PE和随后的交付是自然的半竞争性风险， 因为PE可以在分娩前发展，但不能在分娩后发展。目前的方法没有为分析师提供数据驱动的工具 从高维数据中发现重要的协变量，临床医生缺乏有意义的，个性化的 预测患者随时间前瞻性经历一种或两种结局的联合概率。 该提案通过高维推理和预测工具解决了这些方法上的差距。 在目标1中，我将通过为se开发一套正则化估计来解决变量选择的挑战， 从大型数据集中选择重要的协变量到半竞争风险模型中，并评估性能 通过仿真在目标2中，我将创建一个深度前馈神经网络建模框架，用于预测 个体患者在未来时间点经历一种或两种感兴趣结局的联合概率。 总之，这些目标将改善医疗保健决策的个性化。将开发软件， 为研究人员应用这些方法提供了实用和用户友好的工具。在目标3中，我将应用这些 评估PE风险的半竞争性风险方法，PE是全球孕产妇死亡的主要原因， 胎儿/新生儿死亡率和发病率。使用2011-2020年期间5万例出生的EHR妊娠数据， 将使用所提出的变量选择方法来开发一个识别PE风险因素的模型，其中沿着 影响PE患者分娩时间的因素。通过这项工作，我还将建立一个深度学习模型 为了联合预测母亲PE和婴儿的NICU入院，产生个性化的预测图， 促进平衡孕产妇和胎儿健康风险的护理决策。为了便于临床医生和患者使用， 我将使用交互式在线工具传播这个预测模型。

项目成果

Characterizing quantile-varying covariate effects under the accelerated failure time model.

• DOI: 10.1093/biostatistics/kxac052
• 发表时间: 2023-01
• 期刊: Biostatistics
• 影响因子: 2.1
• 作者: Harrison T. Reeder;Kyu Ha Lee;S. Haneuse

Smartphone GPS signatures of patients undergoing spine surgery correlate with mobility and current gold standard outcome measures.

• DOI: 10.3171/2021.2.spine202181
• 发表时间: 2021-12-01
• 期刊: JOURNAL OF NEUROSURGERY-SPINE
• 影响因子: 2.8
• 作者: Boaro, Alessandro;Leung, Jeffrey;Reeder, Harrison T.;Siddi, Francesca;Mezzalira, Elisabetta;Liu, Gang;Mekary, Rania A.;Lu, Yi;Groff, Michael W.;Onnela, Jukka-Pekka;Smith, Timothy R.
• 通讯作者: Smith, Timothy R.

A novel approach to joint prediction of preeclampsia and delivery timing using semicompeting risks.

一种使用半竞争风险联合预测先兆子痫和分娩时间的新方法。

• DOI: 10.1016/j.ajog.2022.08.045
• 发表时间: 2023
• 期刊: American journal of obstetrics and gynecology
• 影响因子: 9.8
• 作者: Reeder,HarrisonT;Haneuse,Sebastien;Modest,AnnaM;Hacker,MicheleR;Sudhof,LeannaS;Papatheodorou,StefaniaI
• 通讯作者: Papatheodorou,StefaniaI