A Pragmatic Latent Variable Learning Approach Aligned with Clinical Practice

符合临床实践的实用潜变量学习方法

• 批准号: 10033908
• 负责人: BOOIL JO
• 金额: $ 56.55万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-08 至 2023-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10033908
• 关键词: Address; Anxiety; Anxiety Disorders; Attention; Attention deficit hyperactivity disorder; Brain; Caring; Cessation of life; Clinical; Clinical Research; Communication; Complex; Data; Decision Making; Development; Diabetes Mellitus; Diagnosis; Ensure; Future; Goals; Health; Heart; Hybrids; Hyperglycemia; Intention; Label; Learning; Logistic Regressions; Machine Learning; Malignant Neoplasms; Manic; Measures; Methodology; Methods; Modeling; Motivation; Nature; Outcome; Outcome Measure; Patient-Focused Outcomes; Patients; Performance; Process; Psychometrics; Public Health; Reproducibility; Research; Research Personnel; Risk; Sampling; Science; Side; Structure; Supervision; Symptoms; System; Techniques; Time; Validation; Variant; base; clinical practice; clinical risk; comorbidity; data exploration; flexibility; health care service; high dimensionality; improved; improved outcome; interest; model development; neglect; personalized care; personalized medicine; predictive modeling; prevent; prognostic; risk prediction model; simulation; supervised learning; tool; treatment planning; unsupervised learning

Abstract With growing interest in personalized medicine and the rise of machine learning, constructing good risk prediction and prognostic models has been drawing renewed attention. In this development, much effort is concentrated in identifying good predictors of patient outcomes, although the same level of rigor is often absent in improving the outcome side of prediction. The majority of popular supervised techniques (e.g., regularized logistic regression and its variations), which can be readily applied in risk model development, assumes that the prediction target is a clear single outcome measured at a single time point. In clinical reality, patient outcomes are often complex, multivariate, and measured with errors. Even when a target is a relatively clear univariate outcome (e.g., death, cancer, diabetes, etc), the process that leads to this ultimate outcome often involves complex intermediate outcomes, where predicting and understanding this intermediate process can be crucial in providing effective care and preventing negative ultimate outcomes. The situation calls for a flexible learning framework that can easily incorporate this important but neglected aspect in model development - better characterizing and constructing prediction targets before building prediction models. Focusing on risk labels as prediction targets, we propose a pragmatic 3-stage learning approach, where we sequentially 1) generate latent labels, 2) validate them using explicit validators, and 3) go on with supervised learning with labeled data. Latent variable (LV) strategies used in Satge 1 have great potentials in handling complex outcome information. The unsupervised nature of LV strategies makes highly flexible data synthesis and organization possible. The same nature, however, can also be seen as esoteric and subjective, which is not desirable in situations where transparency and reproducibility are of great concern such as in risk prediction. As a practical solution to this problem, we propose the use of explicit clinical validators, which not only makes LV-based labels closely aligned with contemporary science and clinical practice, but also makes it possible to automatically validate and narrow a large pool of candidate labels. With the goal of developing a practical and transparent system of learning and inference for clinical research and practice, we formed a highly interdisciplinary team of researchers with expertise in latent variable modeling, machine learning, psychometrics and causal inference along with clinical/substantive expertise. Our streamlined learning framework focuses on direct and transparent validation of latent variable solutions to ensure clear communication across risk model developers, clinical researchers and practitioners. The project ultimately aims to improve personalized treatment and care by improving risk prediction.

摘要 随着个性化医疗的兴趣与日俱增和机器学习的兴起，构建良好的风险 预测和预测模型重新引起了人们的关注。在这个发展中，付出了很大的努力 集中于确定对患者结果的良好预测因素，尽管相同水平的严谨性通常 没有改进预测的结果方面。大多数流行的监督技术(例如， 正则化Logistic回归及其变种)，其可容易地应用于风险模型开发， 假设预测目标是在单个时间点测量的明确的单一结果。在临床上 事实上，患者的结果往往是复杂的、多变量的，并用误差来衡量。即使当一个目标 是相对明确的单变量结果(例如，死亡、癌症、糖尿病等)，这是导致这一结果的过程 最终结果通常涉及复杂的中间结果，其中预测和理解这一点 中间过程在提供有效护理和防止消极的最终结果方面可能是至关重要的。 这种情况需要一个fl可扩展的学习框架，可以很容易地结合这一重要但被忽视的学习框架 模型开发方面-在构建之前更好地描述和构建预测目标 预测模型。 以风险标签为预测目标，提出了一种实用的三阶段学习方法， 我们按顺序1)生成潜在标签，2)使用显式验证器验证它们，3)继续 使用带有标签的数据的监督学习。潜变量(LV)策略在SATGE 1中有很大的应用 在处理复杂结果信息方面的潜力。LV策略的无监督性质使得 高度可扩展的fl数据合成和组织成为可能。然而，同样的性质也可以看到 因为深奥和主观，这在透明度和重现性很差的情况下是不可取的 非常令人担忧的，例如在风险预测方面。作为这个问题的实际解决方案，我们建议使用 明确的临床验证者，这不仅使基于LV的标签与当代 科学和临床实践，而且还使自动验证和缩小大型 候选标签池。目标是开发一个实用和透明的学习系统 和推论临床研究和实践，我们组建了一支高度跨学科的研究团队 具有潜变量建模、机器学习、心理测量学和因果推理方面的专业知识 具有临床/实质性专业知识。我们简化的学习框架侧重于直接和透明 验证潜在变量解决方案，以确保风险模型开发人员、临床人员之间的清晰沟通 研究人员和从业者。该项目最终旨在通过以下方式改善个性化治疗和护理 改进风险预测。