基于强化学习的医疗预测监测动态特征选择
Dynamic feature selection in medical predictive monitoring by reinforcement learning
- Tsinghua University（清华大学）
- Institute for Precision Medicine, Tsinghua University（清华大学精准医学研究院）
- Center for Big Data and Clinical Research（大数据与临床研究中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对多变量时间序列医疗预测监测中静态特征选择方法无法有效利用时序信息的问题，提出基于强化学习的动态特征选择方法，在最大成本限制下优化策略生成合成数据更新模型，实验证明其在严格成本限制下优于基线方法。
AI中文摘要：
本文研究了多变量时间序列场景中的动态特征选择，这在临床预测监测中很常见，其中每个特征对应一项生化检测结果。许多现有的特征选择方法无法有效利用时间序列信息，主要是因为它们是为静态数据设计的。我们的方法通过为每位患者选择时变的特征子集来解决这一局限。具体而言，我们采用强化学习在最大成本限制下优化策略。随后使用训练好的策略生成的合成数据更新预测模型。该方法能无缝集成不可微的预测模型。我们在包含回归和分类任务的大规模临床数据集上进行了实验。结果表明，我们的方法优于强大的特征选择基线，尤其是在面临严格的成本限制时。论文被接收后将发布代码。
英文摘要：
In this paper, we investigate dynamic feature selection within multivariate time-series scenario, a common occurrence in clinical prediction monitoring where each feature corresponds to a bio-test result. Many existing feature selection methods fall short in effectively leveraging time-series information, primarily because they are designed for static data. Our approach addresses this limitation by enabling the selection of time-varying feature subsets for each patient. Specifically, we employ reinforcement learning to optimize a policy under maximum cost restrictions. The prediction model is subsequently updated using synthetic data generated by trained policy. Our method can seamlessly integrate with non-differentiable prediction models. We conducted experiments on a sizable clinical dataset encompassing regression and classification tasks. The results demonstrate that our approach outperforms strong feature selection baselines, particularly when subjected to stringent cost limitations. Code will be released once paper is accepted.
