Semi-supervised Approaches to Denoising Electronic Health Records Data for Risk Prediction

项目摘要 虽然临床试验仍然是肿瘤学研究的重要来源，但他们的研究结果可能并不普遍。 由于患者人群有限，因此适用于真实的世界。近年来，随着越来越多的人采用 电子健康记录（EHR）以及EHR与标本生物储存库和其他研究的联系 登记处，集成的大型数据集现在作为转化研究的新来源而存在。这些集成 数据集为开发基于EHR的疾病进展准确预测模型提供了机会 和治疗反应，这可以很容易地纳入临床实践。这些模型也可以是 与来自临床试验的模型形成对比，弥合临床试验与真实的世界之间的差距。 然而，使用这种真实的世界数据（RWD）有效地导出和评估个性化预测模型， 由于实际和方法上的障碍，仍然具有挑战性。例如，经验证的结果 来自EHR的信息，如结肠癌的发展和1年的治疗反应，需要 费力的医疗记录审查，因此通常不容易用于研究。容易出错的天真使用 结果的替代物，如计费代码或程序代码，因为真实结果可能会极大地妨碍 EHR研究的力量，并产生有偏见的结果。半监督的风险预测方法， 噪声代理和少量的人类注释的结果，可以大大提高效用， 用于精准医学研究的EHR。推导出风险模型的精确估计变得更加 当候选特征的数量相对于注释结果的数量不小时，这是具有挑战性的。 EHR风险建模的另一个主要挑战在于可移植性。复杂机器学习模型 在一个EHR系统中训练的EHR在另一个EHR系统中通常达到低准确性，这是由于EHR系统中的异质性。 患者群体和医疗保健系统。可以自动调整模型的迁移学习方法 为一个EHR群组开发以更好地适应另一个EHR群组具有很大的价值。合成信息 多个数据源的数据可以提高证据的质量。然而，从多个EHR的Meta分析 由于患者隐私，EHR队列面临额外的挑战。我们通过发展 目标1中高维预测的半监督风险预测方法;半监督转移 学习方法，在没有黄金标准标签的情况下，在目标人群中进行风险预测建模 learin Aim 2;以及Aim中高维预测建模的分布式学习方法。

Project Summary While clinical trials remain a critical source for oncology research, their study findings may not be gener- alizable to the real world due to the restricted patient population. In recent years, due to the increasing adoption of electronic health records (EHR) and the linkage of EHR with specimen bio-repositories and other research registries, integrated large datasets now exist as a new source for translational research. These integrated datasets open opportunities for developing accurate EHR-based prediction models for disease progression and treatment response, which can be easily incorporated into clinical practice. These models can also be contrasted with models derived from clinical trials, bridging the gap between clinical trials and the real world. However, efficiently deriving and evaluating personalized prediction models using such real world data (RWD) remains challenging due to practical and methodological obstacles. For example, validated outcome information from EHR, such as development of colon cancer and 1-year treatment response, requires laborious medical record review and hence is often not readily available for research. Naive use of error prone surrogates of the outcome, such as billing codes or procedure codes, as the true outcome may greatly hamper the power of EHR studies and produce biased results. Semi-supervised risk prediction methods, leveraging noisy surrogates and a small amount of human annotations on the outcome, may greatly improve the utility of EHR for precision medicine research. Deriving a precise estimate of the risk model becomes even more challenging when the number of candidate features is not small relative to the number of annotated outcomes. Another major challenge with EHR risk modeling lies in the transportability. Complex machine learning models trained in one EHR system often attain low accuracy in another EHR system, due to the heterogeneity in the patient population and healthcare system. Transfer learning methods that can automatically adjust model developed for one EHR cohort to better fit to another EHR cohort is of great value. Synthesizing information from multiple data sources can improve the quality of evidence. However, meta analyzing EHR from multiple EHR cohorts faces an additional challenge due to patient privacy. We address these challenges by developing semi-supervised risk prediction methods with high dimensional predictions in Aim 1; semi-supervised transfer learning methods to enable risk prediction modeling in target populations with no gold standard labels uted learin Aim 2; and distributed learning methods for high dimensional predictive modeling in Aim.