Clinical Decision Transformer：通过目标验证推荐预期治疗
Clinical Decision Transformer: Intended Treatment Recommendation through Goal Prompting
摘要：
随着近年来在需要上下文感知的任务中取得的成就，基础模型已被用于处理来自电子健康记录（EHR）系统的大规模数据。然而，先前的基于基础模型的临床推荐系统具有模仿临床医生的行为的有限目的，并且没有直接考虑缺失值的问题。在本文中，我们提出了临床决策Transformer（CDT），推荐系统，产生一系列的药物，以达到所需的范围内的临床状态作为目标提示。为此，我们进行了目标条件排序，它生成了预先设定未来目标状态的治疗历史的子序列，并训练CDT对达到该目标状态所需的顺序药物进行建模。对于在准入内和准入间的上下文嵌入，我们采用了基于GPT的架构，具有准入式注意掩码和列嵌入。在一个实验中，我们从EHR系统中提取了一个糖尿病数据集，其中包含4788名患者的治疗历史。我们观察到CDT根据目标提示范围（例如，NormalA1c、LowerA1c和HigherA1c），与行为克隆的情况相反。据我们所知，这是第一个从目标激励的角度探讨临床建议的研究。有关代码和其他信息，请参见https://clinical-decision-transformer.github.io。
英文摘要：
With recent achievements in tasks requiring context awareness, foundation models have been adopted to treat large-scale data from electronic health record (EHR) systems. However, previous clinical recommender systems based on foundation models have a limited purpose of imitating clinicians' behavior and do not directly consider a problem of missing values. In this paper, we propose Clinical Decision Transformer (CDT), a recommender system that generates a sequence of medications to reach a desired range of clinical states given as goal prompts. For this, we conducted goal-conditioned sequencing, which generated a subsequence of treatment history with prepended future goal state, and trained the CDT to model sequential medications required to reach that goal state. For contextual embedding over intra-admission and inter-admissions, we adopted a GPT-based architecture with an admission-wise attention mask and column embedding. In an experiment, we extracted a diabetes dataset from an EHR system, which contained treatment histories of 4788 patients. We observed that the CDT achieved the intended treatment effect according to goal prompt ranges (e.g., NormalA1c, LowerA1c, and HigherA1c), contrary to the case with behavior cloning. To the best of our knowledge, this is the first study to explore clinical recommendations from the perspective of goal prompting. See https://clinical-decision-transformer.github.io for code and additional information.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
