Variational Bayes latent class approach for EHR-based phenotyping with large real-world data
University College Dublin(都柏林大学学院);The Insight Centre for Data Analytics, University College Dublin(洞察数据分析中心,都柏林大学学院);School of Mathematics & Statistics, University College Dublin(数学与统计学院,都柏林大学学院);School of Medicine, University College Dublin(医学院,都柏林大学学院)
Brian Buckley, Adrian O'Hagan, Marie Galligan
备注:
28 pages, 11 figures, submitted to Frontiers in Mathematics and Statistics. arXiv admin note: substantial text overlap with arXiv:2303.13619
我们研究了现有变分贝叶斯(VB)和马尔可夫链蒙特卡洛(MCMC)软件的性能与特征,以探索现有方法的实用性并为临床从业者提供指导。研究采用两个案例研究全面探究这些方法,覆盖多种真实世界数据场景。首先,我们使用公开的Pima Indian diabetes(皮马印第安人糖尿病)数据,全面对比了逻辑回归的各类VB实现。其次,我们采用包含约100万糖尿病患者的大规模真实世界数据集Optum(TM) EHR(Optum电子健康记录),将分析拓展至包含离散与连续变量的大规模、高度不平衡数据。在第二个案例研究中,我们实现了融合潜类分析(LCA)与回归的贝叶斯患者表型复合模型。研究发现,与条件共轭平均场方法相比,临床数据中常见的若干数据特征(如稀疏性)会显著影响自动VB方法的后验精度。我们还发现,对于两类模型而言,自动VB方法要实现准确的后验估计需要投入更多精力、掌握更多技术知识,且与闭式VB方法相比,其对停止时间高度敏感。我们的结果表明,若用VB替代蒙特卡洛方法,患者表型复合贝叶斯模型更易应用于真实世界研究。它有望成为决策支持的独特实用工具,尤其适用于金标准生物标志物数据稀缺的罕见病场景——此时可利用先验知识辅助模型诊断,还可提示何时有必要开展生物标志物检测。
英文摘要:
We investigate the performance and characteristics of currently available VB and MCMC software to explore the practicability of available approaches and provide guidance for clinical practitioners. Two case studies are used to fully explore the methods covering a variety of real-world data. First, we use the publicly available Pima Indian diabetes data to comprehensively compare VB implementations of logistic regression. Second, a large real-world data set, Optum(TM) EHR with approximately one million diabetes patients extended the analysis to large, highly unbalanced data containing discrete and continuous variables. A Bayesian patient phenotyping composite model incorporating latent class analysis (LCA) and regression was implemented with the second case study. We find that several data characteristics common in clinical data, such as sparsity, significantly affect the posterior accuracy of automatic VB methods compared with conditionally conjugate mean-field methods. We find that for both models, automatic VB approaches require more effort and technical knowledge to set up for accurate posterior estimation and are very sensitive to stopping time compared with closed-form VB methods. Our results indicate that the patient phenotyping composite Bayes model is more easily usable for real-world studies if Monte Carlo is replaced with VB. It can potentially become a uniquely useful tool for decision support, especially for rare diseases where gold-standard biomarker data is sparse but prior knowledge can be used to assist model diagnosis and may suggest when biomarker tests are warranted.
Bayesian Profile Regression using Variational Inference to Identify Clusters of Multiple Long-Term Conditions Conditioning on Mortality in Population-Scale Data
Health Data Research UK, Swansea University Medical School, Swansea University(英国健康数据研究中心,斯旺西大学医学院,斯旺西大学);Department of Statistics, University of Warwick(华威大学统计系);Department of Pharmacology and Therapeutics, University of Liverpool(利物浦大学药理学与治疗学系);Division of Cancer and Genetics, Cardiff University(卡迪夫大学癌症与遗传学部)
Enhancing Phenotype Discovery in Electronic Health Records through Prior Knowledge-Guided Unsupervised Learning
University of Pennsylvania Perelman School of Medicine(宾夕法尼亚大学佩雷尔曼医学院);National Heart, Lung, and Blood Institute (NHLBI), National Institutes of Health(美国国立卫生研究院国家心肺血液研究所);Brown University(布朗大学)