Inria Paris, Paris, 75012, France; Centre de Recherche des Cordeliers, Inserm, Université Paris Cité, Sorbonne Université, Paris, 75006, France.
Inria Paris, Paris, 75012, France; Centre de Recherche des Cordeliers, Inserm, Université Paris Cité, Sorbonne Université, Paris, 75006, France; Hôpital Necker, Assistance Publique - Hôpitaux de Paris, Paris, 75015, France.
Artif Intell Med. 2024 Nov;157:102994. doi: 10.1016/j.artmed.2024.102994. Epub 2024 Oct 2.
Clinical diagnoses are typically made by following a series of steps recommended by guidelines that are authored by colleges of experts. Accordingly, guidelines play a crucial role in rationalizing clinical decisions. However, they suffer from limitations, as they are designed to cover the majority of the population and often fail to account for patients with uncommon conditions. Moreover, their updates are long and expensive, making them unsuitable for emerging diseases and new medical practices.
Inspired by guidelines, we formulate the task of diagnosis as a sequential decision-making problem and study the use of Deep Reinforcement Learning (DRL) algorithms to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from Electronic Health Records (EHRs), which we name a diagnostic decision pathway. We apply DRL to synthetic yet realistic EHRs and develop two clinical use cases: Anemia diagnosis, where the decision pathways follow a decision tree schema, and Systemic Lupus Erythematosus (SLE) diagnosis, which follows a weighted criteria score. We particularly evaluate the robustness of our approaches to noise and missing data, as these frequently occur in EHRs.
In both use cases, even with imperfect data, our best DRL algorithms exhibit competitive performance compared to traditional classifiers, with the added advantage of progressively generating a pathway to the suggested diagnosis, which can both guide and explain the decision-making process.
DRL offers the opportunity to learn personalized decision pathways for diagnosis. Our two use cases illustrate the advantages of this approach: they generate step-by-step pathways that are explainable, and their performance is competitive when compared to state-of-the-art methods.
临床诊断通常是通过遵循专家学院编写的指南推荐的一系列步骤来进行的。因此，指南在使临床决策合理化方面起着至关重要的作用。然而，它们存在局限性，因为它们旨在涵盖大多数人群，并且通常无法考虑到患有罕见病症的患者。此外，它们的更新周期长且成本高昂，因此不适合新兴疾病和新的医疗实践。
受指南的启发，我们将诊断任务表述为一个序列决策问题，并研究使用深度强化学习（DRL）算法来学习从电子健康记录（EHR）中获得正确诊断所需执行的最佳动作序列，我们将其命名为诊断决策路径。我们将 DRL 应用于合成但逼真的 EHR，并开发了两个临床用例：贫血诊断，其决策路径遵循决策树模式，以及系统性红斑狼疮（SLE）诊断，其遵循加权标准评分。我们特别评估了我们的方法对噪声和缺失数据的鲁棒性，因为这些数据在 EHR 中经常出现。
在这两个用例中，即使数据不完美，我们最好的 DRL 算法的表现也与传统分类器相当，其优势在于能够逐步生成通向建议诊断的路径，这既可以指导又可以解释决策过程。
DRL 为个性化诊断决策路径的学习提供了机会。我们的两个用例说明了这种方法的优势：它们生成可解释的逐步路径，并且与最先进的方法相比，其性能具有竞争力。
