用专家知识提升医疗领域小数据下的强化学习模型精度
Expert-Guided POMDP Learning for Data-Efficient Modeling in Healthcare
- 将模糊专家模型转化为伪计数，融入EM算法优化参数估计
- 在低数据和高噪声下，性能优于标准EM算法
- 适合医疗等数据稀缺场景的智能建模，临床可解释性强
从有限数据中学习部分可观测马尔可夫决策过程（POMDP）的参数是一项重大挑战。我们提出一种名为模糊最大后验期望最大化（Fuzzy MAP EM）的新方法，通过将专家定义的模糊模型生成的模糊伪计数引入期望最大化（EM）框架，将问题自然重构为最大后验（MAP）估计，从而在数据稀缺环境下有效引导学习。在合成医学模拟中，该方法在低数据和高噪声条件下均持续优于标准EM算法。此外，在重症肌无力病例研究中，该算法成功恢复出具有临床合理性的POMDP模型，展现出其在医疗数据高效建模中的实际应用潜力。
原文摘要 · Abstract (English)
Learning the parameters of Partially Observable Markov Decision Processes (POMDPs) from limited data is a significant challenge. We introduce the Fuzzy MAP EM algorithm, a novel approach that incorporates expert knowledge into the parameter estimation process by enriching the Expectation Maximization (EM) framework with fuzzy pseudo-counts derived from an expert-defined fuzzy model. This integration naturally reformulates the problem as a Maximum A Posteriori (MAP) estimation, effectively guiding learning in environments with limited data. In synthetic medical simulations, our method consistently outperforms the standard EM algorithm under both low-data and high-noise conditions. Furthermore, a case study on Myasthenia Gravis illustrates the ability of the Fuzzy MAP EM algorithm to recover a clinically coherent POMDP, demonstrating its potential as a practical tool for data-efficient modeling in healthcare.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。