Recent years have witnessed the rapid accumulation of massive electronic medical records (EMRs), which highly support intelligent medical services such as drug recommendation. However, although there are multiple interaction types between drugs, e.g., synergism and antagonism, which can influence the effect of a drug package significantly, prior arts generally neglect the interaction between drugs or consider only a single type of interaction. Moreover, most existing studies generally formulate the problem of package recommendation as getting a personalized scoring function for users, despite the limits of discriminative models to achieve satisfactory performance in practical applications. To this end, in this paper, we propose a novel end-to-endDrugPackageGeneration (DPG) framework, which develops a new generative model for drug package recommendation with considering the interaction effect within drugs that affected by patient conditions. Specifically, we propose to formulate the drug package generation as a sequence generation process. Along this line, we first initialize the drug interaction graph based on medical records and domain knowledge. Then, we design a novel message passing neural network to capture the drug interaction, as well as a drug package generator based on a recurrent neural network. In detail, a mask layer is utilized to capture the impact of patient condition, and the deep reinforcement learning technique is leveraged to reduce the dependence on the drug order. Finally, extensive experiments on a real-world dataset from a first-rate hospital demonstrate the effectiveness of our DPG framework compared with several competitive baseline methods.

Zhi Zheng

Chao Wang

Tong Xu

Dazhong Shen

Penggang Qin

Xiangyu Zhao

Baoxing Huai

Xian Wu

Enhong Chen

ACM Transactions on Information Systems

ACM 信息系统交易 (TOIS) 发表有关信息检索（例如搜索引擎、推荐系统）的论文，其中包含：具有良好经验验证的新的原则性信息检索模型或算法；观察、实验和/或理论研究产生新的见解信息检索或信息搜索；现有信息检索技术的应用说明，阐明了这些技术的优缺点；新的信息检索或信息搜索任务的形式化以及评估这些任务性能的方法；内容的开发（文本、图像、语音、视频等）支持信息检索和信息搜索的分析方法；开发用户信息偏好和交互行为的计算模型；创建和分析信息检索和信息搜索的评估方法； ACM TRANSACTIONS ON INFORMATION SYSTEMS (TOIS) 的信息检索范围因其丰富的创意而吸引了行业从业者，并因其对同事工作的描述而吸引了学术研究人员。

ACM Transactions on Information Systems publishes research papers on information retrieval, such as search engines and recommendation systems. The content includes: well-validated new principled models or algorithms for information retrieval; new insights generated from observational, experimental, and theoretical studies; application examples of existing information retrieval technologies, highlighting their advantages and disadvantages; formalization of new information retrieval or search tasks and methods for evaluating their performance; analytical methods supporting content development (text, images, speech, video, etc.) for information retrieval and search; computational models of user information preferences and interaction behaviors; and the creation and analysis of evaluation methods for information retrieval and search. Due to its rich creativity and in-depth descriptions of peer work, ACM Transactions on Information Systems attracts the attention of both industry practitioners and academic researchers.

《ACM Transactions on Information Systems》发表有关信息检索（如搜索引擎、推荐系统）的研究论文。内容包括：经过良好经验验证的新信息检索模型或算法；通过观察、实验和理论研究获得的新见解；现有信息检索技术的应用示例，阐述其优缺点；新信息检索或信息搜索任务的形式化及其性能评估方法；支持信息检索和搜索的内容开发（文本、图像、语音、视频等）分析方法；用户信息偏好和交互行为的计算模型；信息检索和搜索评估方法的创建与分析。由于其丰富的创意和对同行研究的深入描述，《ACM Transactions on Information Systems》吸引了行业从业者和学术研究人员的关注。

Category	Quartile
计算机科学	2
计算机科学, 计算机信息系统	2

Interaction-aware Drug Package Recommendation via Policy Gradient

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info