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: 10212944
• 负责人: BOOIL JO
• 金额: $ 55.85万
• 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/10212944
• 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; acceptability and feasibility; 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; prognostic model; risk prediction; 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 随着人们对个性化医疗的兴趣日益浓厚和机器学习的兴起， 预测和预报模型已引起人们的重新关注。在这一发展过程中， 集中在确定患者结局的良好预测因素，尽管同样的严格程度通常 在改善预测结果方面的缺失。大多数流行的监督技术（例如， 正则化逻辑回归及其变体），其可以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个结果。临床 在现实中，患者的结局往往是复杂的、多变量的，并且测量时存在误差。即使目标 是相对明确的单变量结果（例如，死亡，癌症，糖尿病等），导致这种情况的过程 最终结果往往涉及复杂的中间结果，在预测和理解这一点时， 中间过程对于提供有效护理和防止负面最终结果至关重要。 这种情况需要一个灵活的学习框架，可以很容易地将这一重要的，但被忽视的 模型开发方面----在建立预测目标之前更好地描述和建立预测目标 预测模型 针对风险标签作为预测目标，我们提出了一种实用的3阶段学习方法， 我们依次1）生成潜在标签，2）使用显式验证器验证它们，3）继续 有标签数据的监督学习。在Satge 1中使用的潜变量（LV）策略具有很大的 处理复杂结果信息的潜力。LV策略的无监督性质使得 高度灵活数据合成和组织成为可能。同样的性质，然而，也可以看出， 作为深奥的和主观的，这是不可取的情况下，透明度和再现性， 在风险预测等方面具有重要意义。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，而且还可以自动验证和缩小一个大的 候选标签池。目标是建立一个实用和透明的学习系统， 和推理的临床研究和实践，我们形成了一个高度跨学科的研究团队 具有潜在变量建模、机器学习、心理测量学和因果推理沿着的专业知识 具有临床/实质性专业知识。我们精简的学习框架侧重于直接和透明的 验证潜在变量解决方案，以确保风险模型开发人员、临床 研究人员和实践者。该项目的最终目标是通过以下方式改善个性化治疗和护理： 改善风险预测。