文献速递流行病学与生物统计医学人工智能与信息学

将复杂选择规则整合到潜在重叠组Lasso中以构建连贯预测模型

Integrating Complex Selection Rules Into the Latent Overlapping Group Lasso for the Construction of Coherent Prediction Models.
PubMed 文献 · Stat Med · 2025-01-01

医学预测模型常通过惩罚回归进行变量选择,但复杂变量结构难以整合。本文提出将变量结构和预定义纳入要求转化为「选择规则」,并通过潜在重叠组Lasso将复杂规则整合到变量选择中,使最终预测模型遵循给定规则。以高血压患者因房颤住院后接受口服抗凝药发生大出血的连贯预测模型为例进行展示。

要点

  • 将变量结构和预定义纳入要求转化为数学表达的「选择规则」。
  • 通过潜在重叠组Lasso将复杂规则整合到变量选择中,使模型遵循给定规则。
  • 应用于高血压合并房颤住院后口服抗凝患者大出血预测模型构建。

核心结论

  • 通过潜在重叠组Lasso可将复杂选择规则整合到变量选择中,使最终预测模型遵循给定的变量纳入规则。

研究设计与样本

  • 方法学论文,提出将变量结构和预定义纳入要求转化为选择规则并整合到潜在重叠组Lasso的结构化方法,并以高血压患者因房颤住院后接受口服抗凝药发生大出血的预测模型构建为例进行展示。

主要发现

  • 整合自然变量结构和预定义纳入要求到变量选择中,不仅增强模型可解释性,还可能提升预测准确性。
  • 潜在重叠组Lasso可在交互项被选中时强制纳入主项。
  • 变量结构复杂时,将此类结构整合到惩罚回归中具有挑战性。
  • 应用示例中除药物-药物相互作用外,还考虑了抗凝药依从性的替代指标及其与剂量和口服抗凝药剂型的交互作用。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Prediction models are important in medical research, as such models enable health researchers to gain deeper insights into disease epidemiology and clinicians to identify patients at higher risk of adverse outcomes. One commonly employed approach to developing prediction models is variable selection through penalized regression. Integrating natural variable structures and predefined inclusion requirements into variable selection not only enhances model interpretability but can also potentially boost prediction accuracy. For example, the latent overlapping group Lasso can force the inclusion of the main terms in the resulting model if their interaction term is selected. However, when variable structures are complex, it is challenging to integrate such structures into the penalized regression. In this work, we first demonstrate how to convert variable structures and predefined variable inclusion requirements into "selection rules" (which represent rules for which or how variables can be included in the final prediction model) and present these rules mathematically. Then, we provide a structured approach for integrating complex rules into variable selection through the latent overlapping group Lasso so that the resulting prediction model follows the given selection rules. To illustrate our methodology, we applied these techniques to construct a coherent prediction model for major bleeding in hypertensive patients recently hospitalized for atrial fibrillation and subsequently prescribed oral anticoagulants. In this application, we account for a proxy of anticoagulant adherence and its interaction with dosage and the type of oral anticoagulants, in addition to drug-drug interactions.

来源:Stat Med,查看原文。版权归原作者所有。

引用

  1. Wang G, Perreault S, Platt RW, et al. Integrating Complex Selection Rules Into the Latent Overlapping Group Lasso for the Construction of Coherent Prediction Models. Stat Med. 2025. PMID: 40420500. doi:10.1002/sim.70121

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。