A Hybrid Recommendation Model for Drug Selection

Medical errors associated with medication pose significant threats to patients' safety, primarily due to the abundance of drug information available on various online healthcare platforms, leading to challenges in identifying relevant drugs. To address this issue, drug recommendation systems have been developed to assist in selecting appropriate medications for specific medical conditions. Collaborative filtering approaches have been widely used to generate personalized recommendations for various applications. They are easy to implement, debug, and provide justifiable reasoning for recommended items, which is not readily accessible in several other recommendation approaches. Regardless of their success, they still need further enhancements to address challenges related to insufficient rating data, such as data sparsity and new item problems. This paper proposes a drug recommendation model that effectively employs drug taxonomy and multi-criteria collaborative filtering to tackle these challenges. Drug taxonomy enhances recommendation quality by offering a more organized and granular representation of drugs, while multi-criteria rating captures the patients' preferences more accurately, enabling accurate recommendations that better match the patient's specific preferences. Experiments conducted on a real-world drug multi-criteria rating dataset demonstrate that the proposed model outperforms baseline recommendation approaches in addressing these challenges and improving prediction accuracy and coverage, making it a valuable tool to assist patients in selecting relevant drugs for their specific medical conditions.