A comprehensive pharmaceutical recommendation system was designed based on the patients and drugs features extracted from Drugs.com and Druglib.com. First, data from these databases were combined, and a dataset of patients and drug information was built. Secondly, the patients and drugs were clustered, and then the recommendation was performed using different ratings provided by patients, and importantly by the knowledge obtained from patients and drug specifications, and considering drug interactions. To the best of our knowledge, we are the first group to consider patients conditions and history in the proposed approach for selecting a specific medicine appropriate for that particular user. Our approach applies artificial intelligence (AI) models for the implementation. Sentiment analysis using natural language processing approaches is employed in pre-processing along with neural network-based methods and recommender system algorithms for modeling the system. In our work, patients conditions and drugs features are used for making two models based on matrix factorization. Then we used drug interaction to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs by using data from 2304 patients as a training set, and then we used data from 660 patients as our validation set. After that, we used knowledge from critical information about drugs and combined the outcome of the model into a knowledge-based system with the rules obtained from constraints on taking medicine.

翻译：本文基于Drugs.com和Druglib.com提取的患者与药物特征，设计了一个综合药物推荐系统。首先，整合来自这些数据库的数据，构建了一个包含患者与药物信息的数据集。其次，对患者与药物进行聚类，随后利用患者提供的不同评分进行推荐，更重要的是，结合从患者和药物规格中获取的知识，并考虑药物相互作用。据我们所知，我们是首个在提出的方法中考虑患者状况与病史以选择适合特定用户的特定药物的研究团队。我们的方法采用人工智能模型进行实现。在预处理过程中，运用基于自然语言处理的情感分析方法，并结合基于神经网络的方法及推荐系统算法对系统进行建模。在我们的工作中，利用患者状况与药物特征构建了两个基于矩阵分解的模型。然后，我们利用药物相互作用过滤与其他药物存在严重或轻微相互作用的药物。我们开发了一个深度学习模型，使用来自2304名患者的数据作为训练集，随后将来自660名患者的数据作为验证集。之后，我们利用关键药物信息知识，将模型输出与基于用药约束规则的知识系统相结合。